arXane › Computer Science › Computer Science
Wednesday, 4 November 2026: 141 new papers, 19 cross-lists and 100 replacements in Computer Vision and Pattern Recognition (cs.CV), in arXiv's order, with full abstracts. The same papers as arXiv's own listing, set as a newspaper; every title links to arXiv.
Reconstructing physical dynamics from fixed sparse sensors and missing frames is a fundamental challenge in scientific research. Sparsity leaves large regions of the field unconstrained, making the inverse problem ill-posed: a model may fit the observed sensors while producing inaccurate off-sensor structures or unreliable predictions between support frames. To this end, we propose PhysFTM---a physics-informed functional Tucker model that parameterizes the Tucker mode factors in reproducing kernel Hilbert spaces (RKHSs) and incorporates PDE constraints through finite-difference residuals evaluated at off-sensor collocation points. These residuals provide additional physical information in regions without direct observational supervision. PhysFTM first reconstructs continuous spatial fields at support frames via an alternating minimization scheme, optimizing the Tucker core tensor and the RKHS-based factors separately. To enable missing-frame reconstruction, PhysFTM constructs a continuous trajectory in Tucker-core space, which is decoded by the learned spatial RKHS-FTM representation to recover the full spatiotemporal field. Experiments on Allen--Cahn, Navier--Stokes, three-dimensional Heat equations, and a three-dimensional gridded Copernicus ocean reanalysis demonstrate accurate 2D/3D reconstruction under two missing-frame protocols. Code is available at https://github.com/liusirzzz/PhysFTM.
Open-set object detection (OSOD) suffers from a fundamental limitation under dense proposal mechanisms: highly overlapping proposals associated with the same object are often assigned contradictory known/unknown predictions. Existing methods perform open-set reasoning independently for each proposal, while ignoring the shared semantics among correlated proposals, resulting in fragmented detections and unstable open-set decisions. In this paper, we reformulate OSOD as an object-centric semantic inference problem, where correlated proposals jointly support a coherent region-level semantic decision. Based on this perspective, we propose OCSI-Net, a unified framework that combines object-centric semantic consistency with geometry-aware uncertainty stabilization. Specifically, OCSI-Net aggregates correlated proposals into structured region clusters and infers region-level semantics from aggregated semantic evidence, thereby enforcing coherent open-set predictions within the same object region. Furthermore, a geometry-aware uncertainty mechanism is introduced to stabilize optimization near open-set transition boundaries. Extensive experiments on multiple benchmarks demonstrate that OCSI-Net consistently achieves state-of-the-art performance, improving the harmonic mean of known and unknown detection by an average of 6.83\% over the second-best method.
Automatic rigging is a fundamental task for both static 3D and dynamic 4D mesh animation, yet existing methods do not provide a unified feedforward solution for these two settings. While static 3D riggers achieve strong quality, they often provide limited control over bone count and become temporally unstable when applied frame by frame to dynamic meshes. Existing 4D methods, in contrast, typically rely on expensive per-sequence optimization. We propose MoTWorld, a template-free, data-efficient framework for unified 3D and 4D skeleton generation. Built on flow matching, MoTWorld generates temporally aligned skeletons for an entire sequence in a single feedforward pass, while naturally handling single-mesh 3D rigging. The model further supports explicit skeleton-count control, uncertainty estimation for candidate selection, and masking-based interpolation, forecasting, and backcasting. To address limited paired 4D rigging data, we adopt a curriculum that initializes from large-scale 3D rigging data and adapts to mid-scale 4D mesh-skeleton data. Experiments show that MoTWorld achieves strong static 3D rigging performance with controllable bone complexity, as well as high-quality and temporally consistent 4D reconstruction and prediction results.
We describe our approach to the LUMPI track of the UrbanTwin Sim2Real LiDAR Challenge, in which a 3D object detector must be trained exclusively on synthetic data and evaluated on unseen real roadside LiDAR, while the synthetic point clouds are simultaneously scored for distributional realism. Our final entry scores 0.4793 combined, from a detection mAP of 0.1333 and a realism score of 0.9126. Our contribution is not a new architecture. Working from a PointPillars baseline, we obtained most of our gains from three sources. First, a diagnosis that small object failure in roadside LiDAR is a localisation problem rather than a detection problem, which led to a parameter free geometric refinement worth 86 percent relative on pedestrian AP. Second, an audit of our own post processing which revealed that a shipped rule was destroying valid predictions, the repair of which produced our single largest detection gain at 335 percent relative on the Van class. Third, treating the realism metrics analytically rather than as a black box, which showed that one of the four components is a closed form function of nine summary statistics. We also report an experimental methodology that we believe is the more transferable result. Because mean AP decomposes into independent per class terms, a single submission can carry several mutually controlled experiments, and a submission assembled entirely from previously measured components has a score that is known before it is sent. We predicted our final score to four decimal places prior to submission. We report negative results at equal length, and give a full account of data provenance and compliance in Section 8, including a full account of every mechanism contributing to the submitted score.
Humans imagine scene changes under hypothetical motions, an ability central to spatial reasoning and robotic planning. However, this capability remains underexplored in vision-language models and world models. We formalize this capability as Counterfactual Spatial Imagination (CSI) and introduce FlowBench, a resource for training and evaluating both, with 428K training examples spanning simulated and real-world scenes, household environments and tabletop manipulation, and diverse question types. A scalable, fully automatic pipeline pairs each hypothetical motion with spatial questions and, in simulation, exact outcome frames and optical flow. For VLMs, proprietary models exhibit an imagination gap, performing worse when motion outcomes must be inferred than when observed, and open-source models perform near chance; fine-tuning Qwen3-VL-8B on FlowBench-Sim-Train raises its accuracy by 29.5 percentage points in simulation and 16.9 on real images, a strong sim-to-real transfer. For world models, training on FlowBench-Sim improves text-to-flow prediction for all four model families we test, raising the accuracy of Psi-0.6 from 52.1% to 61.7%. FlowBench thus serves as a training and evaluation resource for both. Code and datasets are released at https://github.com/liuyifan22/FlowBench.
We describe our approach to the V2X-Real track of the UrbanTwin Sim2Real LiDAR Challenge, in which a 3D object detector must be trained exclusively on synthetic data and evaluated on unseen real roadside LiDAR from an Ouster OS1-64 unit, while the synthetic point clouds are simultaneously scored for distributional realism. Our final entry scores 0.7457 combined, from a detection mAP of 0.4382 and a realism score of 0.9251. Three findings account for most of our result, and all three were diagnostic rather than architectural. First, a coordinate frame mismatch between our predictions and the evaluation ground truth was suppressing detection AP entirely; recovering it took our score from 0.3520 to 0.5147 in a single submission. Second, a single global non maximum suppression threshold was destroying genuine pedestrian detections, because pedestrians occur in groups and a 0.3 IoU threshold applied to a 0.7 m box suppresses distinct neighbouring people; correcting this per class raised overall mAP from 0.0751 to 0.4295. Third, approximately 31 percent of the real reference point cloud consists of null returns encoded as the literal point (0, 0, 0), a format feature entirely absent from our synthetic clouds, which pinned Earth Mover's Distance near its floor until we modelled it. Negative results are reported at equal length, and Section 9 gives a full account of data provenance and compliance. That section also accounts for every mechanism contributing to the submitted score.
Autonomous vehicles require robust perception systems to operate safely under diverse environmental conditions. While cameras provide high-resolution visual data, their performance significantly degrades in low-light and adverse weather. High Definition (HD) radar offers superior reliability and angular resolution under such conditions but lacks rich visual feature recognition. LiDAR, though expensive, delivers highly precise distance measurements and dense point clouds. Each sensor exhibits unique trade-offs, necessitating the development of advanced sensor fusion algorithms to harness complementary strengths while minimizing computational complexity and maintaining accuracy. In this study, the proposed fusion architecture performs early fusion by combining camera images with perspective-view point cloud data from HD radar and LiDAR sensors. The proposed model is trained to detect vehicles and segment free drivable space simultaneously. Experiments are performed on the RADIal dataset where we demonstrate that fusing point cloud data with camera images in front-view surpasses the performances of the most recent standalone and fusion models.
A substantial line of work builds rotation invariance directly into point cloud architectures. We benchmark 10 architectures (PointNet, PointNet++, DGCNN, RIConv, RIConv++, RISurConv, PointMLP, PointTransformer, and the equivariant VN-PointNet and VN-DGCNN) across 5 domains under pose, noise, and occlusion, and analyze the results with confirmatory hypothesis tests rather than point estimates. The three rotation-invariant (RI) architectures achieve the best pose robustness but rank among the lowest on noise robustness in 4 of 5 domains. We ask whether this cost is intrinsic to invariance or specific to how invariance is obtained. We retrain all 10 architectures unchanged, with a simple invariance loss on the embedding and three training seeds each, and evaluate all models on the independently designed ModelNet40-C. Invariance training transfers narrowly but reliably. It improves exactly the corruption families its perturbations target wherever the baseline has headroom (mean occlusion +10.5, lidar +13.4 percentage points of accuracy). At matched training budget the best standard backbone and the best RI architecture end on par on unseen corruptions (within 2.5 percentage points in every seed), and invariance-trained RIConv++ is the most seed-stable top model. Once rotation augmentation is widened, standard backbones concede only a flat, angle-independent accuracy offset under full-sphere rotation. We release the benchmark along with a package for analyzing point cloud robustness and reproducing our results.
Surgical scene understanding is pivotal for computer-assisted intervention, yet demands compositional reasoning across instruments, anatomy, and workflow. Existing surgical vision-language models rely on instruction tuning with large-scale question-answer pairs, entailing laborious data curation and costly retraining. To bridge this gap, we propose SurgEye, a perception-reasoning framework that grounds reasoning in a vision foundation model without instruction tuning. Specifically, we devise Routed Multi-Task Perception (RMP) that routes the vision foundation model through task-specific pathways learned from public perception labels, producing spatial and temporal evidence. We further introduce Agentic Compositional Reasoning (ACR) that employs a frozen large language model to coordinate RMP specialists and temporal memory as callable tools, composing evidence across tasks and time into grounded answers. Moreover, we construct SurgEye-Bench spanning eight surgical procedures, pairing each question with perception labels for verifiable evaluation. Extensive experiments demonstrate that SurgEye outperforms state-of-the-arts in surgical reasoning. The source code will be available.
Effective world modeling requires compressing salient history information that facilitates future prediction. However, most existing approaches inherit tokenization and conditioning mechanisms from video generation, where objectives are centered around perceptual realism rather than predictive utility. This discrepancy limits the world model's effectiveness, especially in environments dominated by visual nuisances or task-irrelevant background details. To this end, we introduce Compression Forcing (CF), a general framework that aligns history compression with the predictive objective of world modeling. Compression Forcing features Dynamics-Aware Tokenization (DAT), a novel tokenization method that compresses history observations into a sequence ordered by decreasing dynamics saliency. Built on a diffusion backbone, this structure enables Hierarchical History Guidance (HG-H), allowing selective amplification of dynamics-salient information during inference. Extensive experiments across various environments demonstrate improved prediction fidelity, physical realism, and downstream decision-making performance, establishing Compression Forcing as a highly flexible and effective approach for world modeling.
Transfer learning from pretrained backbones has become standard practice in multi-sensor computer vision---yet two questions remain open: which pretrained weights transfer best to multi-sensor setups, and can in-domain pretraining outperform off-the-shelf solutions? Frameworks like MultiMAE demonstrate the utility of masked autoencoding in a multi-modal context, but rely entirely on dense, model-derived modalities. It is unclear how robustly these methods translate to real-world applications that use physical sensors, where the aggregation of diverse public datasets for large-scale pretraining inherently introduces modality sparsity. To investigate this systematically, we curate a multi-sensor autonomous driving collection of $2.82M$ images from 16 publicly available datasets, incorporating both physical hardware modalities (RGB, LWIR, NIR, Event) and model-derived modalities (Stereo Depth, Segmentation). We use this collection for in-domain pretraining based on the MultiMAE approach. We adapt MultiMAE's loss formulation to accommodate sparse samples, and study the effect of an enforced encoder bottleneck for modality alignment and of additional losses specific to dense reconstruction (SSIM and FFT). We then systematically compare against common pretrained backbones (ViT, MAE, DINO and MultiMAE) across downstream sensor fusion tasks. We find that MultiMAE is a surprisingly strong out-of-the-box baseline, transferring effectively even to modalities it has never seen, while our targeted modifications yield incremental but consistent improvements on multi-sensor transfer and overall robustness.
Intracardiac flow is driven by complex, and time-varying cardiac motion and interaction with the heart valves, producing complex flow features that may provide valuable information for disease diagnosis and treatment planning. 4D Flow MRI enables non-invasive, time-resolved measurement of three-dimensional cardiovascular velocity fields. However, substantial noise and limited spatial and temporal resolution limit its ability to accurately resolve flow features. We propose 4D-MRAR (4D Magnetic Resonance Augmented Reconstruction), a deep learning (DL) method to super-resolve and denoise 4D Flow MRI data. Unlike prior DL methods that train and infer on static vascular regions, our method predicts intracardiac flow within hearts undergoing large deformation. Moreover, it uniquely allows for simultaneous super-resolution in 3D space and time. The method combines a residual convolutional neural network, a recurrent neural network, and an implicit neural field to predict high-resolution velocity and pressure fields while efficiently enforcing the governing equations of fluid flow during training. Trained on a synthetic dataset obtained from computational fluid dynamics (CFD) simulations of left ventricle (LV) flow, our method generalizes to synthetic whole-heart 4D flow MRI data, and demonstrated promising performance on real 4D Flow MRI. The produced super-resolved flow fields exhibit significantly improved accuracy and greater consistency with the governing equations of blood flow compared with prior methods.
Cross-Domain Few-Shot Segmentation (CD-FSS) aims to segment objects from unseen domains using only a few annotated references. Recent Segment Anything Model (SAM)-based methods have advanced CD-FSS, yet their reference-target visual matching is highly sensitive to target appearance variations. SAM3 introduces text-conditioned segmentation, enabling natural-language descriptions to guide segmentation across target images, but directly using the category name as the condition still yields unstable performance under severe domain shifts. We propose Reference Inversion for SAM3 (RI-SAM3) that leverages SAM3's large-scale vision-language pre-training to learn suitable textual tokens for each target category. RI-SAM3 comprises three core designs: (i) Bi-level Reference Inversion that learns complementary tokens before and after the frozen text encoder: the former remain anchored in SAM3's text space while the latter represent the category more flexibly; (ii) Layer-adaptive Textual Conditioning combines these tokens differently as object queries evolve across decoder layers; and (iii) Presence-aware Confidence Supervision that jointly supervises query confidence and target presence for reliable predictions. With SAM3 frozen, RI-SAM3 optimizes around 12K parameters only per category and it efficiently segments each target in a single forward pass with reusable textual conditioning without per-sample reference-target visual matching. Extensive experiments over multiple widely adopted benchmarks show that RI-SAM3 achieves superior performance consistently in CD-FSS tasks, together with strong robustness, efficiency, and generalization.
Scientific discovery builds on accurate observations interpreted through domain knowledge and reasoning. For scientific 3D data, this requires understanding structures and spatial relationships, from protein contacts to anatomical organization. Existing multimodal benchmarks largely evaluate text and 2D images, while scientific 3D evaluations vary in representations and protocols across disciplines, limiting cross-disciplinary comparison. To assess these foundational capabilities, we introduce ScienceVision, a cross-domain benchmark for scientific 3D understanding and reasoning through expert-level visual question answering (VQA). We construct 250 questions, with 50 each from Biology, Chemistry, Medical Imaging, Mechanical CAD, and Architecture, through a pipeline combining synthetic question generation with domain-expert review and annotation. Each task pairs a native 3D artifact with a scientific question, a specified response format, and a task-specific reference answer, requiring domain knowledge to be applied to geometric or topological evidence. We evaluate 12 models on the same questions in three settings: visual question answering with native 3D artifacts accessed through an agent harness's file and code-execution tools; the same workflow augmented with expert-inspired viewer inspection and measurement tools exposed through the Model Context Protocol (MCP); and visual question answering from prescribed rendered 2D images using an agent harness. All settings use the same task-specific deterministic final-answer scoring. The inspection environment supports view changes, target isolation, and slice inspection. In this main comparison, the best mean answer score is 0.53 out of 1. Mean scores in the native-artifact workflow without additional MCP tools exceed those in the rendered-image workflow for every model, by 17.2 percentage points on average.
Capturing an image in a low-light environment produces a weak, noisy sensor signal. Low-light image enhancement (LLIE) aims to restore it. Auto white balance (AWB) is also required for every image, and the same noisy signal degrades its ability to infer the scene illuminant. LLIE is typically performed first, followed by AWB, but this strategy remains largely unexamined because existing low-light datasets span a narrow range of illuminants and lack illuminant ground truth for evaluating AWB. We address this with CHROMA-MILL, a RAW dataset of 50 scenes captured with a DSLR and smartphone under four calibrated illuminants at eleven intensity levels. Because light is additive, we blend these captures in the linear RAW domain to synthesize physically valid illuminant mixtures with exact chromaticity ground truth. Benchmarking on this data, we find joint correction is best, and introduce CTI-Retinexformer, which supervises an illumination map, a chromaticity prediction, and an illumination-invariant scene embedding, outperforming the best cascade by 0.7 dB PSNR$_L$ and 1.1 $\Delta E_{00}$.
Large 3D repositories make it easy to collect assets, but difficult to determine whether they can be reused reliably across scene assembly, editing, rendering, game production, and training-data construction. An asset can look plausible in RGB while hiding disconnected geometry, problematic UV organization, or materials that fail to resolve correctly after import. We introduce Diagnostic Rendered Evidence (DRE): aligned beauty, wireframe, and UV-seam-plus-wireframe views scored by pass-specific frozen ViT classifiers and combined through late fusion. On 1,234 human labeled TexVerse assets, nested grouped evaluation achieves 86.36% balanced accuracy and 88.32% bad-asset recall. On a separate, balanced 764 external reference test, DRE achieved 88.9% balanced reference-label accuracy. Our method requires only an imported asset and renderer-derived evidence, without repository identity, creator, popularity, text, or source metadata at inference. Our results support cross-corpus portability and show that purpose built diagnostic views expose defects that just the beauty views can miss. Webpage: https://rbz-99.github.io/is-this-3d-asset-usable/
AI-generated images have reached unprecedented realism, while instruction-driven AI editors re-synthesize images for local changes, leaving no splice boundary to localize. Most detectors are black boxes with unverifiable verdicts and generalize poorly because adapting a backbone on the detection distribution memorizes generator-specific fingerprints that quickly become obsolete. Specialist detectors built on pure-vision representations, particularly DINOv3, generalize well across generators, but explainable methods forgo this advantage: jointly training one multimodal model for classification and language generation subjects its visual representation to the language objective. We therefore require that explanation training cannot alter the verdict. We introduce FOX, which first builds and locks a specialist DINOv3 detector, then uses its representation to guide a lightweight VLM toward forensic explanation. A joint-embedding predictor maps locked visual evidence into a frozen text encoder's semantic space, producing guidance that the VLM verbalizes on demand. FOX achieves 97.4 mean AUC across 14 unseen generators, 69.8 BERTScore on XPlainVerse, and 56.1 on LOKI.
Vision-language models (VLMs) increasingly support construction hazard monitoring, yet their frequent false alarms remain poorly understood. This study investigates whether false struck-by hazard warnings arise from failures in object recognition, spatial relation encoding, or hazard decisions dominated by learned co-occurrence priors. We evaluated Qwen2.5-VL-7B and InternVL3.5-8B using 355 counterfactual worker-excavator scene pairs with controlled spatial proximity and worker-removal variants, combining behavioral analysis, internal representation probing, causal interventions, and decision correction. Both models recognized the entities and encoded their spatial relations (out-of-fold AUROC: 0.82 and 0.91), assigning higher hazard scores to near than far scenes in 79% and 73% of pairs. Nevertheless, 74% and 100% of far scenes were falsely classified as hazardous. Removing the worker reduced Qwen's hazard rate to 11%, while worker presence exerted 2.4- and 3.2-times greater influence on hazard scores than spatial proximity in the respective models. Attention-head interventions, neuron-level interventions, and activation steering failed to eliminate this co-occurrence bias. However, conditioning hazard decisions on the model's own spatial-relation representation improved Qwen's specificity from 0.36 to 0.58 at matched sensitivity, outperforming threshold recalibration. These findings reveal that VLM struck-by false alarms stem primarily from decision-making failures rather than deficiencies in object recognition or spatial encoding, suggesting that future efforts should prioritize conditioning hazard decisions on encoded spatial evidence rather than further improving visual recognition alone.
Accurate prediction of Prostate Imaging Reporting and Data System (PI-RADS) scores from multiparametric MRI (mpMRI) remains challenging, more so than clinically significant prostate cancer (csPCa) detection. Given the importance of lesion location in PI-RADS scoring, we evaluated whether incorporating prostate zonal masks improves PI-RADS prediction and csPCa detection across multiple architectures (3D ResNet-18, ResNet-50, and ViT) using a large-scale internal dataset. Anatomical guidance generally improved performance across architectures, with the best results achieved by ResNet-18 with 2-zone guidance for PI-RADS prediction (QWK = 0.511) and ResNet-50 with 5-zone guidance for csPCa detection (AUC = 0.809). Fine-tuned results on external datasets further demonstrated the benefits of anatomical guidance. Furthermore, models with anatomical guidance improved the utility of model-predicted PI-RADS scores for PI-RADS-based csPCa detection (positive defined as PI-RADS>=3). Combining model-predicted and expert-assigned PI-RADS scores significantly increased the AUC from 0.711 to 0.756 (p < 0.05), suggesting that AI-derived PI-RADS scores may provide complementary information to expert assessment for csPCa detection. Overall, our findings highlight the value of incorporating prostate zonal anatomy into deep learning-based prostate MRI assessment.
Long-horizon video generation is increasingly moving toward autoregressive rollout, where each newly generated segment becomes part of the evidence used for future prediction. Recent causal decoders, long-context training, and KV-cache mechanisms have extended feasible duration, but most inference pipelines still decide the visible past implicitly through recent windows, compressed caches, or external memory. This raises a direct question: \textbf{can the choice of which past frames or segments to show to the decoder be treated as an explicit test-time decision?} We answer this question with \textsc{ReCR}, a training-free method that formulates autoregressive video decoding as representation-guided context rewriting. At each step, \textsc{ReCR} builds a selected visible context from the generated history by using internal decoder representations to favor context units that match the global rollout state, avoid redundancy with the recent continuation, preserve temporal boundary coverage, and widen the range of spatial layouts in view. The selected units are then mapped onto a compact causal axis before decoding the next block. Across long-horizon text-to-video benchmarks, \textsc{ReCR} consistently improves multiple autoregressive backbones under matched visible-token budgets. Empirical analyses such as representation-space diagnostics and transition-count prompt switching further show that improving what remains visible is an effective path toward more stable long-video decoding.
Dynamic driving scene reconstruction has made remarkable strides in recent years by leveraging generative priors, particularly in the quality of novel trajectory rendering. Nevertheless, a significant gap remains between the generated data and real-world sensor observations, severely hindering further improvements in reconstruction fidelity. In this paper, we present ReconDreamer#, a self-evolving framework that synergizes reconstruction and generation for dynamic driving scenes, which substantially bridges the gap between synthesized novel trajectory data and recorded real-world observations. Within this self-evolving closed-loop framework, the generative and reconstruction models mutually reinforce each other through iterative refinement, ultimately yielding a significant enhancement in the 3D representation capability of the reconstruction model. Additionally, we introduce a geometry-prior-based adaptive ground model to further enhance the rendering quality of the reconstruction model. To validate the effectiveness of the proposed method, we conduct comprehensive evaluations on Waymo, nuScenes, PandaSet, and EUVS benchmarks. Specifically on Waymo, at a 6-m lateral shift, ReconDreamer# improves NTA-IoU and NTL-IoU by 8.8% and 3.0%, respectively, and reduces FID by 15.1% relative to ReconDreamer++.
Medicinal plants are usually identified using practitioners' experience, but reproducible, image based methods can complement this knowledge. We present MEDIPI (MEDIcinal Plant Identification), a statistical machine learning approach that classifies medicinal plant leaves from photographs. From each leaf image we extract 52 interpretable features covering shape, texture, color, and a new scagnostics category. We then classify leaves using a three level hierarchy: shape, then edge type, then species. We also release MedLEA, an open R package with 1,099 leaf images of 31 Sri Lankan medicinal plant species. On this dataset, a hierarchical Random Forest achieved the best overall accuracy (100%) in our comparison of hierarchical and non-hierarchical approaches and eight algorithms: Random Forest, XGBoost, Gradient Boosting, linear discriminant analysis, k-nearest neighbor, support vector machine, probabilistic neural network, and artificial neural network. Adding texture, color, and scagnostic features to shape features raised shape level accuracy from 90% to 97%. Linear discriminant analysis plots show how the trained model separates leaf shapes. Accuracy dropped sharply (23-50%) when training and test data came from different datasets, so generalization across datasets remains a challenge.
Online 3D Gaussian mapping enables fast and high-fidelity novel view synthesis, with broad applications in augmented reality, robotics, and autonomous systems. However, many current methods assume static scenes or filter out dynamics as outliers. In this paper, we study in-view scene changes where objects are manipulated in front of the camera within a single online sequence, unlike prior works that detect changes outside the camera view or between separate captures. This setting entangles transient and persistent dynamics, as objects can be distractors while moving and persistent once they settle. While recent studies start to address distractors by removing them for clean static background, in-view scene changes remain underexplored. To resolve this, we present SettleSplat, a monocular mapping system that maintains up-to-date 3D Gaussian maps under such changes. Specifically, we lift coarse per-pixel uncertainty into Gaussian dynamicity field, then prune transient ones. For persistent changes, we derive geometric contradictions weighted by parameter-free rendered depth uncertainty to separate true changes from under-optimized regions. On Bonn and Co-Fusion, SettleSplat achieves consistent 3D Gaussian maps, outperforming current baselines on both full images and change regions while maintaining comparable speed.
Deep-learning-based mass detectors usually downsample mammograms, trading fine image detail for lower computational cost. However, published studies cannot reveal how much accuracy this trade-off sacrifices, since they also differ in architecture, preprocessing, and evaluation protocol. In this work, we isolated the effect of input resolution in a controlled study on the VinDr-Mammo dataset, training 18 detectors at six input resolutions ranging from 512 x 416 to 1600 x 1280 pixels, for 108 model-resolution combinations. Whole mammograms were resized without cropping or tiling. For each model, preprocessing, model initialization, augmentation, and evaluation procedures were kept fixed across resolutions. Detection accuracy was evaluated by mAP50 on the 219 mass-positive images of the official test split, and 57 combinations with test mAP50 of at least 0.60 were analyzed. From the lowest to the highest resolution, median mAP50 rose from 0.626 to 0.660 and the best mAP50 from 0.670 to 0.709. The best result, achieved by DINO with a ConvNeXt-S backbone, is the highest mAP50 reported to date on mass-positive VinDr-Mammo images. Gains were concentrated in small masses: for the smallest third of lesions, median mAP50 rose by 0.074 (from 0.367 to 0.441), compared with 0.007 and 0.032 for medium and large masses. Median training time increased from 0.45 to 1.40 h, and median inference time from 23.6 to 113.7 ms per image. Therefore, higher input resolution mainly benefits the small masses that are hardest to detect, at a computational cost that remains practical.
Self-attention has become the standard for modern sequence modeling, enabling Transformers to model long-range dependencies across a wide range of modalities. Despite these advances, its quadratic cost with respect to sequence length remains a significant computational bottleneck. Recent work addresses this limitation by introducing linear variants of self-attention, namely with kernel approximations of the softmax operator. However, their first-order aggregation restricts expressivity and struggles to capture higher-order structure. We propose Linear Stochastic Attention (LiSA), a linear attention plug-in module that enables higher-order token interactions via a stochastic diffusion process based on truncated random walks. LiSA incorporates adaptive locality, favoring semantically similar neighbors to preserve fine-grained structures, while maintaining stable and efficient training. We conduct extensive experiments on classification, semantic segmentation, and object detection tasks and show improved results over state-of-the-art methods.
Semi-supervised cardiac image segmentation aims to exploit abundant unlabeled images together with limited annotations, but the reliability of pseudo-label supervision is highly uneven across spatial regions. In a dual-network setting, interior regions are usually more stable, whereas boundary regions, low-confidence areas, and disagreements between networks can introduce noisy supervision. However, existing methods typically impose uniform supervision on all unlabeled pixels, overlooking reliability differences and limiting discriminative learning in challenging areas. To address this issue, we propose R2CL (Reliability-Role Collaborative Learning), a framework for semi-supervised cardiac image segmentation. R2CL models confidence relationships between two networks to assign roles to unlabeled regions: mutually uncertain regions are used for entropy regularization, confidence-discrepant regions for directional knowledge transfer, and mutually confident regions as reliable supervision anchors. Reliability-Role Mixed Cross Learning (RR-MCL) implements these roles through region-mixed training, directional cross-network supervision, and entropy regularization over mutually uncertain regions. Reliability-Transition Prototype Contrastive Learning (RT-PCL) constructs query features from foreground-adjacent reliability-transition regions and learns network-specific class prototypes from mutually confident regions, improving feature discrimination around ambiguous boundaries. High-confidence Context Refinement (HCR) exploits reliable interior pixels and trusted dense blocks within mutually confident regions to complement stable contextual supervision. R2CL achieves stable improvements in region-overlap and boundary-related metrics across multiple datasets, with more evident advantages on the foreground-sparse MVAA-CT dataset.
Streaming 3D reconstruction must maintain geometric quality over long inputs within a fixed GPU budget. A pretrained recurrent model provides bounded state, but freezing its backbone also fixes its learned state-observation interactions. We introduce Mamba3R, a jointly designed state-memory adapter that provides a trainable adaptation path without updating the backbone or task heads. A selective state-space mixer jointly transforms native state features and a fixed-capacity auxiliary memory, explicit read and write paths carry information across frames, and a decomposed feedback path regulates what the added memory feeds back. Only 1.28 million adapter parameters are trained. Under a shared periodic-reset protocol, it lowers trajectory error and improves accumulated surface and depth accuracy over recurrent baselines on public indoor and outdoor datasets and robot-recorded traversals, gaining up to 40 percent on one metric. Matched comparisons support both the choice of the mixing operator and the utility of carrying the auxiliary memory across frames. Allocated memory remains unchanged and throughput moves by at most 1.4 percent from one to two thousand frames. Replaying its recorded traversals offline, the platform's RTX 4060 averages 11.7 frames per second within 5.1 GiB with the same checkpoint, a mean throughput covering the 10 Hz sensor rate.
Foot ulcers are a leading cause of lower limb amputation, and the highest burden often falls on low and middle income regions where specialists and computing hardware are both scarce. Wound monitoring tools are most useful there when they are accurate yet small enough to run on ordinary devices, but accuracy usually comes from heavy networks. We present LINDA, a compact model that grounds segmentation in an explicit structural prior instead of raw intensity. A Local Self-Similarity (LSS) map, computed directly from the image and stable under local lighting changes, is fused into a ResNet-34 encoder, and a small Liquid Time-Constant module refines the boundary over four iterative steps. With every model trained under one protocol on the FUSeg 2021 dataset, LINDA obtains the best Dice (86.68\%), IoU (79.67\%), and boundary accuracy (HD95 6.37 pixels) in our comparison while using only 25.70M parameters, fewer than the U-Net and transformer baselines. As the LSS map is a fixed function of the input, it exposes the structural cues the model follows in a readable form. Together this makes LINDA an accurate, inspectable, and lightweight option for wound assessment in resource-constrained care.
Separating touching nuclei requires local boundary detail, while cell type classification requires broader morphological context. These requirements also vary with the surrounding tissue environment. We propose the Tissue-Conditioned Adaptive Cross-Branch Interaction Network (TCINet), a single-stage model with Task-Specific Feature Adapters (TSFA) and Tissue-Conditioned Task-Aware Cross-Branch Interaction (TC-TACBI). TSFA produces branch-specific features at skip connections, and TC-TACBI controls three asymmetric paths among nucleus-presence (NP), horizontal-vertical (HV), and nucleus-type (NT) branches using predicted tissue probabilities. On PanNuke under standard three-fold cross-validation, TCINet achieves multiclass and binary panoptic quality scores of 0.519 and 0.692, respectively. Zero-shot tests on MoNuSeg yield a detection F1 score of 0.876. On PanNuke fold 0, adding TC-TACBI increases mPQ from 0.505 to 0.525. Code is available at https://github.com/celestial1321/TCINet.
Diffusion-based data augmentation has emerged as a powerful strategy for addressing data-scarce image classification. Recent pipelines typically adapt a pretrained text-to-image diffusion model to a limited number of class examples and subsequently sample synthetic images using diverse textual prompts. However, in extreme data-scarce regimes such as long-tailed single-sample settings, this approach suffers from a dual failure mode: the generated samples often lack discriminative foreground details crucial for classifier training, and the adapted class prior can bias the early denoising process, causing output images to exhibit similar patterns despite varying text prompts. To overcome these limitations, we propose a sampling-side framework of two complementary components that simultaneously enhance fine details and diversity. First, Mask-Guided Reference (MGR) Attention updates only foreground value tokens with reference features via zero-shot segmentation, limiting reference influence to the target object and mitigating excessive global feature injection. Second, Repulsive Noise Optimization (RNO) encourages initial noise trajectories to diverge from dominant generative modes of the adapted model, enabling target prompts to express broader contextual variation. Extensive evaluations show consistent improvements, with the largest gains in long-tailed single-sample settings of up to 2.50 and 2.94 points on CUB-LT IF100, and further robustness across few-shot and background-shift evaluations.
Counterfactual sketch animation explores how a static sketch evolves under a hypothetical intervention. We present CounterSketch, a physics-grounded framework that transforms natural-language ``What if...?'' queries into physically plausible sketch animations. The framework integrates VLM-guided scene grounding, causal event-chain reasoning, constraint-based trajectory generation, and verification. It models physical transitions to update the scene graph, computes continuous object trajectories, and validates them against physical, geometric, and semantic constraints. The verified trajectories are then projected into object-level motion bounding boxes to guide downstream sketch-video synthesis. Experiments on CounterSketchBench (80 questions) demonstrate that physics-grounded trajectories provide stronger motion guidance than direct VLM predictions.
High-resolution range profiles (HRRPs) provide compact radar target representations but exhibit strong aspect sensitivity, complicating class-incremental recognition when historical data are unavailable. Changes in viewing aspect shift scattering-peak locations and amplitudes, while reflector groups may produce responses resembling ships. Existing dynamic expansion methods can also incur substantial parameter and memory overhead. To address these challenges, we propose P-SER, a Physical Consistency-Constrained Scattering Expandable Representation framework for exemplar-free class-incremental HRRP recognition. P-SER reconstructs dominant scattering points from complex-valued sum- and azimuth-difference-channel HRRPs and observation geometry. The reconstructed spatial structure, target extent, and energy distribution are used to derive class-level scattering prototypes and sample-level saliency priors, providing physically grounded constraints for feature learning and old-class knowledge retention. A primitive scatterer dictionary further characterizes local strong-scattering mechanisms and calibrates uncertain ship--reflector predictions at inference. Meanwhile, lightweight residual adapters are incrementally introduced into a shared HRRP backbone to learn new classes with limited model growth. Experiments on simulated and measured HRRP datasets show that P-SER delivers competitive recognition performance without retaining old-class exemplars, while maintaining physical consistency, interference robustness, knowledge retention, and model scalability.
Semi-supervised medical image segmentation aims to train reliable segmentation models using limited labeled data and abundant unlabeled data. However, existing methods typically rely on prediction confidence or model consistency to estimate pseudo-label reliability, but these criteria are insufficient to characterize both semantic reliability and geometric plausibility. To address this issue, we propose ProGeo-RC, a prototype-guided semantic reliability and geometric error calibration framework for semi-supervised medical image segmentation. ProGeo-RC consists of two key modules: Prototype-guided Semantic Reliability Estimation (PSRE) and Structured Semantic-Geometric Error Calibration (S-SGEC). PSRE uses probabilistic class prototypes to estimate the semantic reliability of unlabeled predictions and calibrate pixel-wise teacher pseudo labels, while S-SGEC introduces signed-distance-field-based geometric constraints to refine ambiguous boundaries and suppress spurious foreground responses outside target structures. Experiments on the ACDC and MVAA-CT datasets show that ProGeo-RC achieves better performance compared with representative semi-supervised segmentation methods. Under the 10\% labeled setting on ACDC, ProGeo-RC improves DSC and Jaccard by 0.37\% and 0.49\% over the corresponding second-best results, while reducing 95HD and ASD by 0.61 and 0.21, respectively. These results indicate that joint semantic reliability estimation and geometric error calibration can provide more reliable pseudo supervision for semi-supervised medical image segmentation.
Promptable perception, from GroundingDINO to Rex-Omni, puts one model behind one prompt interface and returns coordinates for any localisation task. Every model in that line was built for photographs; none has been given a sketch. We present Sketch-Omni, to our knowledge the first perception MLLM built to work on sketches and from them. On a sketch, the sketch is the image, and text prompts detect, point, resolve object and spatial referring expressions, and ground affordances in it. From a sketch, the sketch is the prompt, and a drawing of one object localises that object in a photograph, even among several of the same category, a query that neither a category name nor a photo exemplar can pose. Two obstacles stand in the way. A photo-trained model's attention is tuned to colour and texture, which a sketch does not have, and no dataset pairs a drawing with the one instance it depicts among others of its kind. We build the training data instead of collecting it. An edge detector turns every labelled photograph into a sketch-like drawing that keeps the photograph's labels, and two constructions produce sketch-to-photo instance pairs from existing data. On top of this, photo-guided relation alignment passes each photograph and its edge sketch through the same model and trains the sketch pass to reproduce how the photograph pass relates phrases to patches and patches to each other. Not one training label is drawn by hand. Sketch-Omni reaches 91.4 F1 on sketch-prompted localisation against 81.8 for the strongest general-purpose MLLM, with a lead that doubles when the photograph holds several instances of the queried category, and it is best in 39 of 40 evaluation cells across six tasks. Code, model, and a hand-annotated benchmark of 2754 sketch-to-photo links will be released.
Can an LLM directly edit the weights of a diffusion-based image-restoration model to \emph{improve} restoration quality---without gradients, paired data, or fine-tuning? Recent experiments show frontier LLMs can fix structural bugs by modifying as little as \(0.016\%\) of parameters, but cannot instill new capabilities. We ask whether weight-space programming (WSP) can move from \emph{debugging} to \emph{improvement} in the precise-regression setting of image restoration (deblurring, super-resolution, denoising, inpainting). Restoration diffusion UNets present a middle ground: low-level signal-processing layers are concentrated enough for targeted weight-direction edits, while high-level semantic layers remain distributed and resistant to sparse modification. We propose three technical conjectures: (C1) an LLM can localize the layer behind a quality gap (over-smoothing, color shift, hallucinated texture) within a 200 forward-pass budget; (C2) editing a small set of identified weight directions (e.g., scaling high-frequency filter norms, correcting output-bias channels) can measurably improve PSNR and perceptual quality; (C3) a recursive loop---diagnose \(\rightarrow\) edit \(\rightarrow\) evaluate \(\rightarrow\) re-diagnose---can compound gains across rounds, forming a minimal recursive self-improvement (RSI) loop for vision. We analyze the required AI capability (arguing targeted edits need not superintelligence, while general capability generation does) and detail the challenges of precise pixel-level regression. We provide a PyTorch-style deployment pipeline and outline a benchmark. This manuscript is conjectural, intended to open a new subtopic for image restoration.
Chest radiography (CXR) diagnosis is critical for thoracic disease assessment, yet challenged by the need to identify subtle lesions and co-occurring abnormalities across regions. While recent vision-language models can actively observe local regions, existing preference-based methods supervise each observation by its immediate effect on the current diagnosis, failing to capture how each observation and stopping decision contributes to the final diagnosis. To address this issue, we propose GroundSeek-CXR, an active CXR diagnosis framework that learns observation and stopping decisions by retrospectively evaluating them with the final diagnosis. Specifically, we first devise a Retrospective Diagnostic Evaluation (RDE) that scores observation and stop candidates from offline Monte Carlo tree search through independent continuations. Moreover, we design a Retrospective Gap-weighted Preference Optimization (RGPO) that learns from retrospective-score preferences weighted by their score gaps, prioritizing actions that improve diagnostic accuracy. Extensive experiments demonstrate that our GroundSeek-CXR framework outperforms state-of-the-art methods, and improves abnormal-image sample-F1 by 4.48% over immediate-score preference learning.
Long-range 3D object detection remains difficult for autonomous vehicles because LiDAR returns become sparse and camera evidence weakens with distance, while automotive radar keeps returning measurements far beyond both. We present CLOCs-R, an extension of the CLOCs candidate-level fusion framework that adds radar evidence to camera-LiDAR rescoring. Radar returns are accumulated over several sweeps, compensated for ego-motion, and associated with each pre-NMS 3D candidate through a range-dependent gate. Compact features summarizing support, Doppler speed and spread, range residual, and offset are then appended to every camera-LiDAR pair before a lightweight fusion network rescores the candidates. We first verify that our fusion implementation reproduces CLOCs on KITTI. We then evaluate on the daytime clear-weather subset of the aiMotive dataset, reporting distance-binned metrics out to 200 m with frozen SECOND and Cascade R-CNN detectors. Camera-LiDAR CLOCs improves on SECOND up to 50 m but degrades beyond it. A residual scoring variant, introduced post hoc, corrects SECOND's score instead of replacing it and recovers most of this loss. Radar consistently improves BEV AP at 30-50 m (0.857 to 0.870), but beyond 50 m its gain is small (+0.003 center-distance AP), within seed variation, and CLOCs-R with residual scoring is statistically tied with LiDAR-only SECOND. Our analysis attributes the limited long-range benefit to weak separation of true and false detections by radar features, scarce far-range training positives, poor camera evidence at distance, and missing LiDAR proposals that rescoring cannot recover. We report all as-designed and post hoc results side by side.
In-image machine translation (IIMT) replaces text in an image with its translation while preserving the surrounding visual context. Existing task-specific models achieve convincing performance but require massive paired training images before and after translation. As advanced text-to-image (T2I) models have reached a practically usable level of multilingual text generation, we argue that this capability can be transferred to IIMT and present FlowTranslator. It is a training-free IIMT framework that first employs an OCR model and an LLM to generate the translation prompt, which is injected into the T2I-based diffusion model. To optimize the accurate and natural generation of translated text, we introduce two trajectory controls: Region Coupling Release (RCR) partially decorrelates target-branch noise inside the text region early in the trajectory, while Coupling Expansion (CE) amplifies the emerging edit displacement mid-trajectory. Under the EasyOCR read-back protocol, FlowTranslator achieves average PRIM BLEU and COMET scores of 20.6 and 57.2, respectively, substantially outperforming the strong training-based baseline UniTranslator. On the more challenging and realistic whole-image ScenePair photographs translated into Chinese, it reaches 40.1\% exact-match accuracy and surpasses existing editing systems, some of which only address the text-rendering stage rather than the complete IIMT task. These results establish flow-based editing as a strong, fully training-free baseline for IIMT.
Camera object detectors lose recall in rain, fog, snow and sand, and the confidence threshold at which a detector is deployed decides how many objects it misses and how many false alarms it raises. We study how a frozen detector should make this decision in adverse weather. We first reproduce SeqCRC, a conformal object detector whose first step calibrates the confidence threshold by conformal risk control (CRC), and use that step, calibrated separately in each weather condition, as our baseline. With YOLOv8x it keeps the held-out miss fraction within a 20% budget in every DAWN weather bin, where a single global threshold fails in fog, but the false alarms it needs are an output rather than a choice: from 1.6 to 117 per image across DAWN and BDD100K conditions. We then propose a calibrated trade-off dial. One setting, $\lambda$, the number of false alarms accepted to avoid one missed object, selects the expected-cost-optimal decision rule: either one score threshold, or a per-detection rule that keeps a box when its calibrated probability of being a real object, estimated by gradient-boosted trees from the detector's own per-box outputs, is at least $1/(1+\lambda)$. F-score preferences map onto the same dial, and CRC applied to $\lambda$ itself is planned to restore a per-condition miss guarantee. The dial is fitted once on BDD100K train and graded only on BDD100K val and DAWN.
Steel scrap composition estimation is an important part of yield planning and fair supplier compensation. Measuring the composition of a multi-ton pile is an inherently laborious process, so the assessment is often left to trained human operators. Recent works tackle composition-level tasks, but require structured acquisition and multi-stage preprocessing. We study a simpler approach to steel scrap load assessment by aggregating features from sparse, handheld views of the pile. On 600 out-of-fold piles, frozen DINOv2 tokens aggregated uniformly across views reach 13.4% total variation (TV) distance against operator estimates. Most remaining error lies in allocation among four thickness-defined heavy melting scrap (HMS) classes, yet image-dependent allocation reduces within-HMS TV from 25.1% under a training-set split prior to 11.2%. Due to the lack of public datasets and benchmarks for predicting composition, external evaluation relies on the public DOES dataset intended for classification. A classifier using the same frozen features reaches 93.97% accuracy, exceeding the published results we compare against. The composition model also aligns with related DOES categories without adaptation.
Whole-slide multiple instance learning can predict diagnostic and prognostic labels from tissue composition while making limited use of spatial organization. Providing coordinates or a graph does not establish that a trained predictor uses tissue neighborhoods. We examine this gap as spatial blindness and hypothesize that early composition learning can weaken supervision of a spatial pathway. We introduce ResTopoMIL, which freezes a learned composition predictor before training a graph residual with a coordinate-reassignment separation loss. Permutation and information analyses distinguish architectural symmetry, available spatial information and the proposed optimization mechanism. On a controlled spatial task, staged training achieved an AUC of 0.987, compared with 0.684 for the same jointly trained architecture. Performance remained high on a composition-only task. Across four WSI classification and five survival benchmarks, ResTopoMIL improved mean primary performance on eight tasks; four improvements remained significant after Holm-adjusted patient-cluster tests. Coordinate-free residual controls recovered some of the gains, while neighborhood destruction reduced performance close to the composition anchor. Neighborhood-preserving transformations and anatomy-stratified perturbations further characterized this dependence. These results support fixing a composition reference as a practical intervention for learning spatial corrections, while retaining additional appearance capacity as a contributing explanation.
Despite recent advances in camera-based online HD map construction, these systems remain susceptible to sensor failures due to their reliance on onboard cameras. In contrast, satellite images remain available independently of real-time sensing conditions as they are cached offline. Existing methods utilizing satellite images, however, primarily leverage them under nominal conditions, without explicitly addressing them as redundancy when a sensor degrades. To address this gap, we propose ReSMap, a redundancy-aware camera-satellite fusion framework for robust online HD map construction. Our framework explicitly leverages satellite images as a complementary source to improve robustness against camera failures. A Predict-then-Fuse (PTF) module fuses camera and satellite BEV features by using each branch's own prediction confidence as a per-pixel reliability weight, with no learned router. An Object-Centric Cooperative Multi-modal Query (OCMQ) decoder then extends this per-modality separation to the query level: each modality cross-attends only to its own BEV, and per-modality updates are merged through a learned per-token gate. Our model achieves state-of-the-art performance on nuScenes across all splits and range settings. More importantly, it also sets the new state-of-the-art under camera-failure scenarios, demonstrating that satellite images serve not only as a strong prior but as practical redundancy for robust online HD mapping.
Purpose: Despite advances in 3D surgical scene understanding, semantic simultaneous localisation and mapping (SLAM) remains under-explored for two key reasons. First, it requires solving three challenging tasks in parallel: camera pose tracking, high-fidelity deformable reconstruction, and semantic mapping, making progress particularly demanding. Second, the scarcity of datasets providing the necessary ground truth to evaluate all three tasks comprehensively under conditions that closely reflect real surgical procedures environments. Method: We propose EndoS3, a Gaussian Splatting-based semantic SLAM framework that uses instance masks to guide all three tasks. An instance-level motion decomposition module separates static and dynamic instances by evaluating residual flow after compensating for camera motion, accounting for flow noise and comparing motion across neighbouring instances. The camera is tracked against the static Gaussians, while an instance-aware warp field gives each dynamic instance its own control nodes and deformation network. A semantic node allocation module redistributes a fixed node budget across instances according to their size and non-rigidity. We also introduce CRCD++, an ex-vivo Cholecystectomy dataset with RGB-D frames, camera pose and instance annotations for full semantic SLAM evaluation. Results: EndoS3 surpasses all state-of-the-art general-purpose and surgical semantic SLAM methods in tracking, reconstruction and semantic mapping on the CRCD++ and SemSup datasets. Conclusion: Semantic-aware motion and deformation modelling is vital to surgical semantic SLAM. EndoS3 and CRCD++ offer a method and benchmark for improved geometric and semantic understanding in endoscopy.
High-fidelity weather editing of 4D scenes can support end-to-end training and closed-loop simulation for autonomous driving. Combining generative image editing with dynamic Gaussian representations enables multi-weather scene reconstruction, but weather-edited images often contain structural distortions. Directly fitting their appearance may propagate errors from teacher images into the reconstructed 4D scene, compromising the original scene structure and temporal continuity. To address these challenges, we propose IGSW, a two-stage framework that combines intrinsic-decoupled 4D Gaussian scene modeling with structure-preserving weather refinement. In Stage I, background Gaussian appearance is decomposed into weather-shared albedo and normals and weather-specific irradiance and residuals. Weather teacher images generated by a diffusion-based image editing model and intrinsic maps estimated by a diffusion-based inverse renderer provide feature-level soft supervision for stable structure and illumination changes. In Stage II, a structure-preservation gate combines semantic conflicts with cross-weather intrinsic discrepancies to suppress unreliable teacher regions. Per-Gaussian weather transport variables and target-weather branches then strengthen the desired weather appearance over the intrinsic-decoupled scene. Experiments on nuScenes and Waymo show that IGSW achieves the highest content similarity and semantic consistency and the lowest temporal error among the compared methods, while retaining pronounced weather-dependent illumination and atmosphere. The project page is available at https://akaxi6.github.io/IGSW/ .
Scene Graph Generation (SGG) produces structured scene representations, yet its training-time backdoor risk remains unexplored. Unlike classification, SGG exposes a pair-level attack surface that enables selective corruption of relations involving a designated object category. However, because SGG largely relies on localized evidence, globally placed triggers may face difficulty in manipulating such predictions. Recent SGG architectures increasingly incorporate global context to improve scene modeling, which may in turn facilitate such attacks. In this paper, we systematically study this backdoor risk and investigate the role of the global context pathway in backdoor behavior. Concretely, we first instantiate this attack with an effective method, and propose a three-axis evaluation protocol to characterize backdoor behavior. Experiments on Visual Genome with representative open-vocabulary and closed-set SGG models demonstrate the effectiveness of the attack. Mechanistic analyses reveal that the explicit global context pathway serves as a major carrier of the backdoor effect across the evaluated SGG models. In particular, replacing the poisoned global context representation with its clean counterpart during inference sharply suppresses the attack, yielding 100% and 97% reductions in attack success for the OvSGTR family and RelationFormer, respectively. Moreover, training-time interventions in the OvSGTR family show that suppressing trigger signals in this pathway either reduces attack success or substantially degrades utility. Together, these findings suggest that explicit global context designs may pose a backdoor risk in SGG architectures.
A deployable text-to-image diffusion model must hold several capabilities at once, such as instruction following, text rendering and human preference, and must sample in a few steps. Capabilities and few-step sampling are built in separate stages: a full-step model first consolidates capabilities through multi-teacher on-policy distillation, then serves as a fixed teacher for step distillation. Every full-step model we evaluate scores lower once compressed, and the second stage cannot begin until the first finishes. We introduce StepX-OPD, which merges the two stages: one student acquires every capability while learning to sample in a few steps, so frozen specialists supervise it on the states its own rollout visits rather than on a longer trajectory it never runs. Because a decomposition of the rollout's KL weights velocity mismatch most heavily near the clean end, we also regress the student's velocity on the low-noise part of the rollout. Separately, we find that capability integration makes models write prompt words into images on prompts that never asked for text, and we give a variant that lowers it. We evaluate on SD3.5-Medium and FLUX.1-dev across instruction following, text rendering, image quality and human preference. On both architectures, StepX-OPD attains the highest normalized average score among the four-step methods compared and exceeds the forty-step Flow-OPD model, and on SD3.5-Medium it trains with about 37% fewer GPU-hours than sequential DiffusionOPD followed by step distillation.
Many fields of physical interest on the sphere, such as wind, the polarisation of the cosmic microwave background and the shear of weak gravitational lensing, are spin fields, whose values change phase when the local frame rotates. We extend spherical Fourier neural operators (SFNOs) to fields of any spin, through lifted spherical convolutions that are exactly rotationally equivariant. Lifting spin fields to Mackey functions on the rotation group provides the conceptual framework, while computation is performed exactly and efficiently through their harmonic representation and by appealing to sampling theorems on the sphere and rotation group. We construct spin SFNOs (S$^2$FNOs) from these building blocks. We demonstrate empirically that rotational equivariance holds to machine precision for these layers. We achieve state-of-the-art performance on existing benchmarks, and introduce new benchmarks on which spin-aware models outperform their scalar counterparts.
Camera-LiDAR fusion repeatedly uses an extrinsic transform in projection, association, and recursive state estimation. We study whether a targetless correction should be admitted to a downstream consumer only after separate audits of correction quality, confidence ranking, and recursive risk. Our log-disjoint protocol evaluates these stages under synthetic extrinsic drift on Argoverse 2 and treats cross-dataset and odometry experiments as bounded diagnostics. On 27 test-split logs, single-frame Canny alignment is harmful in the mild tier. Multi-frame alignment improves severe-tier rotation by 2.52 degrees but worsens translation by 0.177 m; its declared joint error-magnitude improvement is also negative (-0.158, 95% CI [-0.223, -0.098]), so the rotation gain is not a six-degree-of-freedom correction success. A zero-injection check moves away from the true extrinsic, and solver-disagreement AUROC on selected splits does not yield a validated nonzero-coverage risk-coverage operating point. In a 15-log final system role, the locked conservative policy admits no candidate and equals Raw, whereas Always-correct increases trajectory error. These results support an auditable separation of correction, confidence, and recursive contamination; they do not establish a deployable calibration gate, positive odometry or SLAM improvement, map consistency, or closed-loop safety.
Automated diabetic retinopathy (DR) grading from colour fundus photographs is held back by two compounding challenges: severe class imbalance across five severity grades and the heavy computational cost of large scale architectures in resource constrained clinical settings. We introduce DR-LiteNet, a dual branch hybrid convolutional neural network that tackles both problems at once. The CNN branch extracts 1,280 dimensional deep features through EfficientNetB0, while the handcrafted (HC) branch produces a compact 51 dimensional lesion descriptor capturing vessel density, exudate intensity, texture entropy, and HSV colour histograms. Concatenating both branches yields a 1,331-d hybrid embedding, on which Adaptive SMOTE (ADASYN) is applied during training to synthesise minority class feature vectors, correcting distributional skew without touching the image space. A two phase training protocol first warms up the classification head on balanced features, then fine tunes the full network end to end. Grad CAM saliency maps deliver post-hoc clinical explainability. Tested on APTOS 2019 under five fold stratified cross validation, DR-LiteNet reaches 88.77% +/- 0.61 accuracy, a quadratic weighted kappa (QWK) of 0.884 +/- 0.010, and a macro F1 of 0.792 +/- 0.008 with only 4.69 M parameters beating ResNet50 (23.5 M) by DeltaQWK = 0.022 while staying practical on a single Google Colab T4 GPU. The source code of this project is available at: https://github.com/Nishi-Kanta-Paul/DR-LiteNet.
Accurate lesion segmentation underpins automated dermoscopic analysis: masks enable measurements of asymmetry, border and size. Deployment in primary care or on mobile devices requires a compact network. Existing ultra-light Mamba U-Nets offer global context, but global-modeling cost depends on each Mamba block's resolution, while their local branches rely on a single square kernel. We introduce LCM-UNet, a 33,474-parameter U-shaped network that fuses every skip at its native resolution, restricts bidirectional Mamba to stages at one-sixteenth of the input resolution or coarser, and uses local convolutions at finer scales. A multi-basis reparameterizable adapter augments each local branch during training with dilated, horizontal and vertical depthwise kernels, then folds them into the host kernel before inference. Each skip connection also learns a stage-specific gain. Nine networks were retrained on the official ISIC 2017 and ISIC 2018 partitions under a harmonized protocol, with PH$^2$ reserved for external validation and ablations run on a development split. LCM-UNet achieved Dice scores of 88.62%, 89.73% and 90.46% on ISIC 2017, ISIC 2018 and PH$^2$, respectively, ranking first on both ISIC test sets and second on PH$^2$ among the compared models. In the native-resolution host, removing Mamba from the one-eighth-resolution decoder stage eliminated 63% of Mamba operations, corresponding to 5.3% of all operations, with a Dice change of $-0.03$ percentage points. The adapter improved Dice by 0.48 percentage points over a single host kernel without adding deployed parameters or operations. With latency so far measured only on a GPU, LCM-UNet is a candidate for resource-constrained deployment.
Missing modality imputation aims to synthesize unobserved modalities from observed ones. Existing methods treat each modality as living on its own latent manifold, forcing the generator to learn a long, unstructured jump between them. We present SphereFlow, which takes a fundamentally different view: by projecting all modalities into a shared hyperspherical latent space via a frozen self-supervised encoder, cross-modal imputation reduces to short-range geometric transport between nearby points on the sphere. Realizing this idea with flow matching, however, exposes two geometric conflicts: the standard Gaussian noise source is catastrophically mismatched with the unit-norm data manifold, and the linear interpolation path departs the sphere surface into a region where the decoder has no training signal. We resolve both with simple, geometry-aware modifications: replacing the noise source with the observed-modality latent so that the velocity field learns only the cross-modal displacement, and training the decoder with a time-weighted loss that extends its domain to the near-surface region traversed by the flow. We prove that this data-as-source formulation reduces the worst-case off-manifold deviation from a quantity that grows with the latent dimension to a small, dimension-independent bound governed by inter-modality similarity. Experiments on BraTS multi-modal MRI imputation and CT-MRI translation demonstrate state-of-the-art generation fidelity across all settings, while downstream brain tumor segmentation with our imputed data closes roughly eighty percent of the gap to the full-modality oracle. Code is available at https://github.com/WTHH031230/SphereFlow.
Instruction-based image editors still primarily operate at 1K, whereas practical editing increasingly requires faithful 2K/4K outputs. Dense high-resolution adaptation preserves the editing trajectory but incurs expensive target-source attention; editing at 1K followed by external refinement is cheaper but can separate detail restoration from the editing trajectory. We introduce FLASH, a native high-resolution editor based on sparse cross-resolution denoising. A frozen 1K branch provides a semantic and structural anchor, while a target-resolution branch reconstructs local detail within the same Transformer. An asymmetric topology retains full 1K attention, guides high-resolution queries with spatially aligned low-resolution noisy-target states, and confines high-resolution target-reference interaction to local Halo neighborhoods. Resolution-specific diffusion-state mapping and spatial YaRN adapt the pretrained editor to larger grids. An optional, training-free progressive path replaces early high-resolution denoising with a 1K prefix and completes refinement in the same editor. On VINS-4KEval, the direct model achieves the strongest structural fidelity among the compared methods at both 2K and 4K. A separate 4K forward benchmark with R = 1 records 4.2x faster total forward execution and 25.3x faster attention than dense target-reference attention. Progressive inference reduces end-to-end 4K latency by 30.5%, with a modest quality cost.
The advancement of multimodal learning is heavily constrained by the scarcity and high annotation cost of high-quality instruction data. While raw videos offer an abundant and dynamic source of visual knowledge, transforming them into precise instruction data remains highly challenging. To bridge this gap, we present VidUEU-Agent, an automated pipeline that synthesizes instruction data from raw videos for multimodal understanding, editing, and unified tasks. VidUEU-Agent follows a four-stage pipeline: it performs global perception to filter low-quality shots, mines keyframes and multimodal signals, constructs metadata and routes the metadata to synthesize instruction samples. More importantly, our agent framework can autonomously iterate the data distribution based on downstream training results, thereby optimizing data quality, balance, and training effectiveness. Scaling this pipeline, we construct VidUEU-100K, a large-scale dataset of 100K training samples spanning multiple domains and tasks, providing a robust foundation for developing comprehensive multimodal capabilities. Extensive experiments demonstrate that fine-tuning baseline models on VidUEU-100K yields significant and consistent performance gains across diverse representative benchmarks, validating the effectiveness of our proposed agent framework and dataset.
Natural human-robot interaction requires robots to interpret language and gestures within a 3D environment to support tasks such as pick-and-place and object retrieval. 3D Embodied Reference Understanding (3D-ERU) supports this by identifying the 3D location of a target object from a scene (point-cloud) containing a human pointing gesture and an accompanying language description. However, current 3D-ERU models lack alignment of cross-modal representations and incur high processing costs that increase with the point-cloud's size. To address this, we propose GVT3D, which employs an Embodied Fusion module that jointly models language, gesture, and vision inputs within a shared embedding space, promoting cross-modal alignment. We additionally introduce a foveation approach that selectively processes the point cloud within a coarse region around the estimated pointing direction to reduce computations. GVT3D achieves ~8% higher accuracy and foveation enables 2.95x faster execution while maintaining comparable accuracy, relative to prior 3D-ERU models.
Visualizing multivariate scientific simulation data is essential for understanding complex physical phenomena, yet the massive scale of such data imposes a severe storage bottleneck in high-performance computing environments. Implicit neural representations (INRs) have emerged as a promising continuous alternative to traditional lossy compressors, but existing methods struggle to explicitly capture cross-variable interactions and to adapt to the diverse spectral characteristics of physical variables. To address these limitations, we propose SWAP-INR, an architecture for high-fidelity compression of multivariate, time-varying simulation data. SWAP-INR introduces two key components: (1) The switchable attention path (SWAP) module explicitly models cross-variable interactions through a cross-variable attention layer, then routes each variable to an attention or non-attention path by a deterministic, loss-driven criterion, and prunes the inactive layers for structural compression. (2) The adaptability amplification SIREN (A2-SIREN) replaces rigid frequency scaling with channel-wise learnable modulation, adapting to heterogeneous physical features with negligible overhead. Combined with post-training 16-bit quantization, SWAP-INR achieves state-of-the-art performance on small modular reactor (SMR) datasets and remains competitive on public physics simulation datasets, while maintaining a constrained memory footprint. Our code is https://github.com/hvcl/SWAP-INR.
The edge detection technique is an essential step for aircraft skin milling in aviation manufacturing. Most of the current detection methods focus on traditionally defined edge extraction tasks but disregard the crucial systematic requirement of edge milling. In this paper, we proposed a novel edge detection framework for automatic edge milling of aircraft skins. First, an edge probability detector is proposed by the spatial tangent continuity (STC) to provide the essential reference. Second, we propose a hierarchical branch searching (HBS) method to hierarchically strip the desired milling edges from the raw point cloud, which consists of three graded progressive steps: branch backbone generation, branch extension, and branch pruning. We demonstrate the performance of the proposed method on both synthetic models and aircraft skin workpieces. The proposed method outperforms the other baselines and shows accurate edges for the edge milling task.
Large Vision-Language Models (LVLMs) routinely name objects that are absent from the image. Latent steering can reduce this failure in one model forward pass, but a fixed gate treats early and late decoding steps by the same criterion. We observe that predictive entropy varies sharply within free-running generation, while states that commit to short answers occupy a narrow, confident band. We exploit this temporal mismatch by using uncertainty as a causally available, token-local control signal for an existing steering gate. We propose Entropy-Gated Dynamic Rectification (EGDR), which lowers the intervention threshold when entropy derived from the preceding step's already available logits is high and retains the calibrated operating point when it is low. On LLaVA-1.5-7B, the underlying static gate lowers CHAIR CS/CI from 53.00/15.30 to 32.00/14.30; replacing only its constant threshold with EGDR further lowers them to 29.00/13.60. At a matched 58% intervention rate, the corresponding static control obtains 30.50/14.00. The gain over the static gate holds on LLaVA-NeXT-7B and grows with the generation budget, while POPE scores and general multimodal capability remain effectively unchanged. EGDR requires no additional model forward pass and adds roughly 2% measured latency. Our code is available at https://github.com/alvi-uiu/EGDR.
Moving Object Segmentation (MOS) detects and separates dynamic objects from the static background in a video, which plays a fundamental role in dynamic-scene understanding. Most MOS methods rely on pure visual motion cues alone, such as optical flow or point tracks, which is inherently ambiguous due to the compounded camera and object motions as well as motion-induced appearance changes, e.g. shadows and reflections. Naive fusion of additional information such as depth and semantics, however, cannot leverage their complementarity to the fullest extent. We therefore propose DynOSeg, a novel MOS approach that takes on a two-stage fusion structure. DynOSeg first combines a geometry-aware residual map and depth encoding into a geometric representation of motion, delineating camera motions and object dynamics. We then further incorporate semantic features to refine object understanding. We have additionally curated a diverse training corpus including CARLA-MOS, a new synthetic urban-driving dataset for MOS training. Our experiments show that DynOSeg consistently outperforms published state-of-the-art MOS methods across a diverse range of datasets. Our code and pretrained models can be found at https://github.com/ACFR-RPG/DynOSeg
Unified multimodal models (UMMs) integrate image generation and visual understanding, but are existing single-pathway unlearning methods sufficient to suppress target concepts across both? In this work, we study cross-pathway concept unlearning. Our goal is to prevent a model from both generating images of a target concept and identifying it in input images, while preserving other capabilities. To this end, we introduce UUBench, a diagnostic benchmark covering 30 target concepts and 60 semantically related neighboring concepts. Experiments on representative UMMs show that the evaluated single-pathway methods achieve limited joint forgetting: generation-side editors strongly suppress target generation but yield limited forgetting in visual understanding, while understanding-side baselines struggle to achieve substantial forgetting even in their own pathway. Their direct composition also yields limited joint forgetting. We therefore propose UniForget, achieving joint forgetting rates of 80.0% on BAGEL-7B-MoT and 92.7% on Janus-Pro-7B, outperforming representative baselines. Further analysis reveals trade-offs between joint forgetting and capability preservation.
High-resolution land-cover maps support ecological monitoring, but consistent historical time series remain scarce because aerial imagery varies across years and sensors. We developed a dual-track workflow to produce temporally coherent 1-m land-cover maps from National Agricultural Imagery Program (NAIP) imagery without historical training samples. For higher-quality imagery from 2009-2017, we used a pretrained U-Net/ResNet-34 model and refined boundaries with the Segment Anything Model (SAM). For lower-quality imagery from 2004-2008, we reconstructed land cover through an NLCD-based spatiotemporal bridging and label back-casting pipeline. Evaluation across six counties in North Carolina and Pennsylvania yielded overall accuracies of 0.887 (2014), 0.886 (2017), and 0.733 (2004). Structure, Water, Wetland, and Cropland consistently achieved high F1-scores. The workflow integrates GeoAI and multiple data sources to address temporal heterogeneity in historical aerial imagery, supporting high-resolution land-change analysis and landscape planning across the conterminous United States.
Video Reasoning Segmentation (VRS) aims to infer and segment target objects specified by reasoning queries in videos. Existing methods typically first infer the target and generate a few segmentation tokens for it, which are then fed into a mask decoder for mask prediction. However, such segmentation tokens tend to be both semantically monotonous and spatially ambiguous, making them largely insufficient to represent the target to guide mask prediction. In this paper, we propose an explicit visual object grounding framework for VRS. Specifically, we first propose a spatial-aware prompt generation and refinement scheme, in which we query a multimodal large language model to generate explicit spatial prompts (i.e., bounding box and point set) for the target and then refine them through multi-step dialogue. Furthermore, we introduce a query diversification and alignment module to generate auxiliary queries that describe the same target from different perspectives. We then enforce cross-query consistency between their predicted spatial prompts to alleviate the training bias caused by query limitations. Finally, we select several reliable frames using a prompt-based keyframe selection strategy to support mask decoding and propagation. Extensive experiments on eight datasets demonstrate that our method significantly outperforms state-of-the-art methods. The code is available at https://github.com/viscom-tongji/EVOG.
Audio-based piano transcription is hampered by the sustain pedal and by noisy or missing soundtracks, problems that video-only transcription avoids, since a top-view video shows directly when each key is pressed and released. Most visual transcription networks, however, describe the whole keyboard with one global feature vector and must learn where each key is. In this paper, we propose KeyWise, a lightweight per-key architecture that exploits the known geometry of the keyboard instead of learning it. The rectified keyboard is divided into 88 equal tiles that serve as regions of interest (ROIs), and one small recurrent network, shared by all keys, follows each key over time. On PianoVAM, KeyWise reaches the onset accuracy of the state-of-the-art V2N (95.0% vs. 94.7% onset F1 at 50 ms and 97.8% vs. 97.0% at 100 ms) with 1.3 M instead of 28.2 M parameters, and it runs 4.7 times faster on the same GPU. At 100 ms, it is also significantly more accurate when the key releases (97.0% vs. 95.5% F1) or the velocities (89.4% vs. 84.5% F1) must be correct as well. On PianoYT, KeyWise pre-trained on PianoVAM reaches 69.4% onset F1 at 100 ms, comparable to the best published result, although it needs fine-tuning for new recording conditions.
Vision-language models such as CLIP enable zero-shot classification from arbitrary class names, but under test-time corruptions, their visual encoder projects distorted features onto incorrect textual anchors with high confidence: a phenomenon we term modality bias. Standard entropy minimization reinforces these overconfident errors, which creates a confirmation-bias loop and collapses the predicted label distribution. We propose an online test-time adaptation (TTA) method that breaks this loop at three levels. At the representation level, a frozen self-supervised backbone (e.g., DINO v2) is combined with CLIP through a cross-covariance logit ensemble. CLIP text prototypes are projected into the feature space of this text-free backbone, so the self-supervised branch classifies native image features and is less affected by the text bias of CLIP. At the optimization level, a gated test-time information-maximization objective pairs per-sample sharpening with batch-level diversity, while an adaptive gate excludes unreliable samples from the gradient. At the prediction level, an online logit adjustment corrects the residual class-distribution skew. CDIM outperforms the compared CLIP-based online TTA baselines on ImageNet-C, CIFAR10-C, and CIFAR100-C, and remains competitive in continual and mixed-domain TTA. Extensive analyses and ablation studies verify the contribution of each of its components. Our code is available at https://github.com/B1ueC1oud/CDIM
Few-shot high-resolution range profile (HRRP) recognition is challenged by strong aspect-dependent variation and sparse novel-class support. We propose polarimetric scattering-structure contrastive learning (PSS-CL), which supplies an episodic HRRP encoder with a structured physical training view. Dominant local responses are represented by their soft affinities to canonical polarimetric mechanisms, normalized range locations, and energy contributions. A symmetric cross-view objective transfers this scattering structure to the learned HRRP representation, while episodic prototype learning supports novel-class inference without the physical branch. We conduct Random-aspect and Cross-aspect experiments on a six-class measured dataset. In Cross-aspect 1-, 3-, and 5-shot recognition, PSS-CL achieves 81.73%, 86.92%, and 90.98% mean class accuracy (MCA), respectively, outperforming the best competing results by 5.62%, 3.09%, and 3.56%.
Monocular depth estimation (MDE) has advanced rapidly with the emergence of foundation models such as Depth Anything. Their transformer-based architectures provide strong generalization across diverse scenes and domains, but also incur high computational and memory cost, making efficient deployment challenging. Post-Training Quantization (PTQ) provides an efficient and practical solution for model compression, yet low-bit PTQ remains challenging for MDE models. When applying PTQ to Depth Anything, we identify two key challenges: (i) independently minimizing the quantization error of the query and key projections fails to preserve the attention maps induced by their interaction, and (ii) quantization errors accumulate across layers, resulting in intermediate feature distribution shifts. To address these issues, we propose SPA-Q, a Structure-Preserving Adaptive PTQ framework for MDE, consisting of two main components. First, Attention-Preserving Calibration (APC) determines query and key quantization parameters by matching the full-precision attention distribution. Second, Channel-Wise Distribution Alignment (CWDA) learns channel-wise affine transformations to mitigate quantization-induced distribution shifts, and the learned parameters are absorbed into the weights after training. Experimental results show that SPA-Q consistently outperforms existing PTQ methods under 4-bit quantization, achieving an average 25.9% reduction in AbsRel and a 17.3% improvement in $\delta_1$ across NYUv2 and KITTI datasets.
3D Gaussian Splatting (3DGS) enables real-time novel view synthesis (NVS), but its heavy storage makes compression essential, and both training and compression introduce representation-specific distortions. Since generative compression in many methods treats geometric and color attributes via different parameters, it can induce dimension-specific distortions, motivating multi-dimensional assessment. Moreover, real-world captures generally lack an aligned ground-truth video for a synthesized, continuous camera trajectory, leaving only sparse captured views as references. To enable multi-dimensional quality assessment of 3DGS videos with scarce aligned references, we first present 3DGS-VBench+, a large-scale subjective video quality assessment (VQA) benchmark comprising 3{,}036 3DGS reconstructions, each paired with a rendered video, across 11 real-world and 22 synthetic scenes, generated by 6 representative compression algorithms at systematically designed levels and annotated with 9{,}108 MOSs covering overall, geometry, and color quality. Based on 3DGS-VBench+, we propose 3DGSV-Assessor, a reference-flexible, large multimodal framework that scores all three dimensions in one generation pass and fuses a ranking-based reference cue into the frozen regressor through a bounded gate, supporting both reduced-reference (RR) and no-reference (NR) assessment. Extensive experiments demonstrate state-of-the-art correlation with human perception on 3DGS-VBench+ and strong zero-shot generalization to other NVS benchmarks. The dataset and code will be released at https://github.com/YukeXing/3DGSV-Assessor.
Electroencephalography (EEG)-based visual decoding and reconstruction aims to recover visual information from non-invasive brain signals. But there are challenges due to the complex temporal-frequency characteristics of EEG signals and the difficulty of discrete denoising framework in mapping neural activity to meaningful visual representations. Here, we propose E2I-Flow, an EEG-to-image decoding and reconstruction framework that combines a novel EEG encoder for time-frequency representation learning from EEG features, and conditional flow matching for visual decoding. A stationary-wavelet frequency branch and a temporal-mixing branch are integrated through bidirectional cross-attention and adaptive fusion, with the resulting EEG representations aligned to ground-truth image embeddings using contrastive and mean-squared-error loss supervisions. The aligned EEG representation is then used as a condition for a Transformer-based flow-matching model to predict the corresponding visual embedding for image synthesis. Experimental results show strong zero-shot EEG-to-image retrieval and improved visual reconstruction performance, outperforming several state-of-the-art baselines.
Recent advances in generative models have made synthetic images increasingly photorealistic, posing growing challenges to reliable and generalizable detection of AI-generated images. Existing methods typically rely on holistic image-level classification, which may overlook local artifacts, especially in high-resolution images. To address this limitation, we formulate this task as a falsification-driven multiple instance learning problem, where a single fake patch can falsify the whole image, while a real image requires all patches to be authentic. Based on this formulation, we propose \textit{Learning to Falsify (LTF)}, a hierarchical multiple instance learning framework that models an image as multiple bags of instances across different spatial levels and aggregates their predictions under the falsification-inspired principle. We further introduce Cross-Shuffle during training to encourage the model to learn local artifact evidence rather than image-level shortcuts. Furthermore, we propose the \textit{Falsification-driven Test-time Aggregation Strategy (FATAS)}, a plug-and-play module that extends the same falsification-inspired principle to existing detectors by aggregating patch-level predictions. Extensive experiments demonstrate that LTF achieves strong generalization and robustness across multiple benchmarks, while FATAS substantially improves representative detectors in high-resolution scenarios without retraining. Code is available at https://github.com/HuiGuanLab/LTF.git
Radar-based human sensing typically relies on end-to-end task-specific models trained on hand-chosen signal projections, which generalize poorly across unseen users, tasks, and hardware. We argue that the dominant signal processing choice, the micro-Doppler spectrogram, is a poor starting point for transfer because it keeps the Doppler axis, which carrier frequency rescales, and discards the angular axis, which carrier frequency leaves unchanged. We instead pretrain a convolutional beta-VAE without labels on clutter-removed raw radar measurements from four platforms spanning 60 and 77 GHz and 4 to 12 virtual antennas, aligned by a unified spectral interpolation grid. For every downstream benchmark the encoder stays frozen, and only a small supervised temporal classifier is trained on its embeddings. We compare against supervised models trained end to end on each benchmark and a pretrained radar foundation model across ten settings covering activity, gesture, sign-language, and gait recognition. When the test users and the radar are seen during training, our encoder is best on all five benchmarks. For users never seen in training, it leads on three of four benchmarks, by 4.8 to 23.2 points. On subject-disjoint gait recognition, it is best for each of the four held-out subjects and 8.3 points above the strongest baseline on average, even though its pretraining excluded every recording of this radar. Excluding the test radar from pretraining costs at most 5.3 points on any benchmark. Code is available at https://github.com/jonasmueler/UniversalRadarEncoder_WACV.
Large Vision-Language Models (LVLMs) often process hundreds or thousands of visual tokens, resulting in substantial computational and memory overhead during inference. Existing training-free pruning methods typically estimate token importance using language-model attention, visual attention, or feature similarity. However, these methods treat visual tokens with uniform criteria and overlook that tokens may serve different roles during visual encoding. In this work, we investigate the evolution of visual token roles in LVLMs and observe that tokens progressively transition from local detail carriers to globally referenced representatives as encoding proceeds. Based on this observation, we propose BtsPruner, a training-free role-aware visual token pruning framework that preserves complementary token roles under a fixed budget. Specifically, BtsPruner first identifies the token-role transition point based on the evolution of attention concentration. It then discovers globally referenced representatives from later encoding stages and recursively retrieves local detail tokens from earlier stages to recover complementary fine-grained evidence. Extensive experiments across LLaVA-1.5, LLaVA-NeXT, Qwen-VL, InternVL, and CogVLM demonstrate that BtsPruner achieves superior performance retention under aggressive token reduction. On LLaVA-1.5-7B, BtsPruner preserves 91.6% of the dense model's performance using only 32 of 576 visual tokens (5.6%). In the high-resolution LLaVA-NeXT-7B setting, it achieves up to a 5.95x CUDA-latency speedup.
Synthetic Aperture Imaging (SAI) enables drones to observe forest canopies by warping and averaging multiple displaced views at a common depth. However, occlusion is suppressed rather than eliminated, causing poorly observed regions to appear occupied and leading to systematic biomass overestimation. The Deep Forest project cannot distinguish reconstruction artifacts from real vegetation because its training data relies on measured reflectance points, excluding empty space and preventing the network from learning explicit occupancy boundaries. This thesis addresses the problem by modifying training labels rather than the imaging process. Each simulated scene is rendered twice: as a 9x9 grid of top-down captures for focal-stack generation and as 550 depth-clipped slabs derived from scene geometry to provide occupancy labels, explicitly representing void space as a negative class. A Gazebo pipeline generates procedural forest stands containing 80-200 trees across three species. A pretrained Pix2Pix model translates rendered RGB images into a synthetic near-infrared band, and Light Field Rendering produces aligned focal stacks of 550 planes across three channels. Four architectures were evaluated on a held-out scene. The plain 2D U-Net achieved an IoU of 0.6290, outperforming the volumetric 3D U-Net (0.5707). Established reconstruction methods performed substantially worse: COLMAP achieved 0.3446 and DepthAnything3 0.2959, both after their respective optimal dilation sweeps. An RGB-input variant of the volumetric architecture achieved the highest IoU of 0.6514 without dilation or per-scene calibration. These results highlight the limitations of conventional reconstruction methods, which recover visible surfaces but struggle to infer occupancy within closed canopies.
Most video anomaly understanding (VAU) systems still infer anomaly judgments from evidence collected in a feed-forward way under predefined rules, typically sampled frames, or events clustered from such frames. This protocol fails when the collected evidence is incomplete under imperfect predefined rules, because once reasoning begins the model can no longer search for the missing evidence. We address this limitation with SEEK-VAU, which reframes VAU as an agentic search-and-verify interaction protocol under a bounded search budget: instead of passively reasoning over pre-collected evidence, the policy actively gathers evidence across the three stages of an anomaly event chain (precursor, trigger, and aftermath) and verifies its sufficiency before finalization, turning event-chain completeness into an explicit design rather than an outcome of predefined rules. A bounded budget caps the cost of this search, but does not by itself teach the policy where to look or when to stop. To make this behavior learnable, we introduce evidence-faithful counterfactual verification (EFCV), which rewards selected evidence that remains supportive, compact, and necessary under counterfactual verification. We further introduce SEEK-Bench, featuring video-level episodes with temporal interval annotations, semantic QA and event-chain stage labels. Together, SEEK-VAU and SEEK-Bench establish a strong foundation for evidence-faithful and actively verifiable VAU.
3D semantic scene completion plays a critical role in enabling various downstream tasks within autonomous systems by estimating both missing geometric structures and semantic information in scene data. In this work, we introduce a unique neural framework that integrates state space modeling with diffusion-based generative approaches to enhance 3D point cloud semantic scene completion. We propose \textit{MPath Mamba} diffusion network, leveraging a skip-triple Mamba structure, dimensional decomposition residuals, and multi-directional dilations within multi-path data to efficiently process long-sequence data for feature extraction. The proposed method operates in the conditioned latent space of a variational autoencoder, enhanced by a state-space mechanism to improve 3D point cloud representation and reconstruction. Extensive experiments conducted on the SemanticKITTI benchmark demonstrate that our approach achieves highly competitive performance for 3D point cloud semantic scene completion.
Coarse-to-fine image-to-point-cloud (I2P) registration risks discarding correct but ambiguous patch pairs, while retaining more candidates repeats fine matching over overlapping patches. SparseGraph-I2P aims to improve registration recall by increasing the inlier ratio at the pose solver, using sensor or monocular depth. A Coarse Hypothesis Graph combines appearance with depth-derived first- and second-order compatibility to select a fixed budget of patch pairs. Sparse Fine Matching decodes each queried pixel once and skips pixel--point comparisons covered by an ancestor patch paired with the same point-cloud region. With sensor depth, depth-aware filtering ranks correspondences by SC2 spectral support for a single EPnP solve. With monocular depth, depth or inverse depth is calibrated from correspondence geometry before filtering. SparseGraph-I2P achieves the highest registration recall and lowest latency among the compared methods on RGB-D Scenes V2 and 7-Scenes with sensor depth. With predicted depth, it retains the highest recall on RGB-D Scenes V2 at an additional calibration cost. Code will be released.
Weakly supervised oriented object detection (WS-OOD) aims to reduce the annotation cost of rotated bounding boxes by leveraging cheaper annotations such as horizontal boxes or points. However, these weak annotations provide no explicit orientation information, forcing existing methods to infer object angles through indirect geometric consistency or equivariant constraints. Such indirect supervision often becomes ambiguous and unstable under real-world appearance variations, including illumination changes, color shifts, shadows, and background clutter. In this paper, we present a simple yet effective gradient-guided orientation learning strategy for WS-OOD. Motivated by the observation that the input image itself contains useful orientation priors, our method extracts dominant gradient-based orientation cues from object regions and converts them into pseudo-angle labels for auxiliary supervision, enabling the detector to learn orientation-aware representations without requiring rotated bounding box annotations or extra learnable parameters. Furthermore, since AP can mask substantial angular errors when spatial IoU remains high, we introduce an orientation-aware evaluation metric that incorporates angular discrepancies into the standard AP protocol. Extensive experiments on weakly supervised oriented detection benchmarks demonstrate that the proposed pseudo-angle supervision improves both detection performance and orientation estimation quality, while the proposed metric provides a more faithful assessment of angle prediction than conventional AP alone.
A key challenge in colon capsule endoscopy (CCE) analysis is accurately identifying whether multiple images depict the same polyp, which is critical to avoid over-counting and unnecessary clinical interventions. Additionally, this prevents prolonged follow-up colonoscopies where endoscopists search for duplicate polyps without precise localization. This study presents a novel contrastive learning-based approach to polyp matching using a Siamese neural network architecture. The model was trained on a dataset from the Danish CareForColon2015 trial. The dataset comprises 5,103 image pairs of confirmed same polyp and 5,103 pairs of different polyps, annotated by experienced clinicians. The proposed model employs ResNet variants (ResNet18, ResNet34, ResNet50), DenseNet121 and EfficientNet B0/B3 as backbones and utilizes contrastive learning with cosine vector distance metric for classification. Experimental results demonstrate high classification accuracies of up to 92% and AUC values close to 0.98. These results suggest that automated polyp matching has the potential to reduce polyp over-counting, improve patient risk stratification, and reduce unnecessary follow-up colonoscopies.
Dynamic hand gesture authentication (DHGA) is an emerging biometric technique that contains both physiological and behavioral identity characteristics. However, existing methods primarily rely on convolutional networks or manually designed motion representations, making it difficult to jointly capture fine-grained local identity differences and long-range behavioral dependencies during hand gesture execution. To address these challenges, we propose a two-stream identity representation learning framework, MambaHand Net, to combine CNNs with Mamba for DHGA. The proposed framework consists of a Local Identity Stream (LIS) and a Behavioral Sequential Stream (BSS). The LIS extracts frame-wise local identity cues with a convolutional network, while the BSS preserves spatial tokens from intermediate visual features and constructs first-order and second-order temporal difference sequences to model multi-order behavioral variations. Moreover, the bidirectional Mamba is incorporated into the BSS to model semantic motion across different spatial locations, enabling efficient long-range modeling of hand gesture execution habits. Finally, attention-guided spatial token aggregation and a two-stream fusion strategy are used to integrate local identity cues and multi-order behavioral patterns into a discriminative identity representation. Our method achieves state-of-the-art (SOTA) average performance on the SCUT-DHGA benchmark dataset, demonstrating that combining CNNs with Mamba is an effective new solution for DHGA.
Video character replacement aims to replace actors while preserving facial expressions, motions, and scene dynamics. Existing methods typically rely on masked generation with pose guidance, limiting fine-grained expression and motion preservation in complex scenes. We propose ReXMo, an end-to-end framework that supports single-, multi-, and selective character replacement scenarios. ReXMo introduces paired triplet supervision, where synthesized driving videos and original videos share identical performances but different identities, enabling scalable training through synthetic data generation. An In-Context Diffusion Transformer learns identity transformation by jointly conditioning on driving videos, reference identities, and text prompts, while an Expression Enhancement Adapter improves facial expression preservation in multi-person scenes. Extensive experiments demonstrate that ReXMo outperforms existing methods in identity fidelity, motion consistency, expression preservation, and visual quality. Our dataset and code will be publicly released.
Facilitative Interpersonal Skills (FIS) is a performance-based assessment method that provides a structured framework for evaluating the interpersonal competencies of mental health professionals. However, existing FIS assessment relies heavily on human observer ratings, making the evaluation process labor-intensive, costly, and difficult to scale. Progress toward automated FIS assessment has also been constrained by the lack of publicly available professional data in psychotherapy settings. To address this limitation, we introduce Therapy-FIS, a dataset for automated FIS assessment in standardized psychotherapy tasks. To our knowledge, Therapy-FIS is the first publicly available dataset in this domain. It contains facial, acoustic, and textual signals derived from standardized therapist responses to standardized mock patient stimulus clips, based on 890 therapist video recordings and 8 patient videos, and is rated with eight FIS subscale ratings and an overall FIS score. Built on Therapy-FIS, we further establish a benchmark with two downstream tasks: Therapist Performance Rating and Joint Therapist--mock-Patient Performance Rating. We also introduce a competitive baseline, DyadicFIS, with gated fusion and routed readout under therapist-only and dyadic settings. DyadicFIS obtains the best macro CCC(Concordance Correlation Coefficient) scores on both tasks (0.2807 and 0.3299). Therapy-FIS offers a reproducible resource for data-driven automated assessment of therapeutic interpersonal skills in mental health.
We introduce BhopalMLS, a large-scale Mobile Laser Scanning (MLS) dataset from a dense, heterogeneous urban environment in Bhopal, India, with mixed traffic, informal structures, and narrow unplanned streets. It spans approximately 10 km of road corridors with over 1.2 billion points and 19,518 annotated instances across 62 fine-grained static categories, grouped into 12-class and 21-class benchmark taxonomies; 6 optional moving-class subclasses support dynamic-object analysis. Existing 3D datasets, collected in well-planned cities, are structurally more uniform than such unplanned settings, and lack their subtype diversity. On semantic and instance segmentation at both granularities, fine-tuned foundation models surpass supervised baselines: Utonia(L) reaches 71.28% mIoU (vs. PTv3's 68.04% from scratch) and 44.07% mAP50 on the 12-class benchmark. Cross-region experiments against four established datasets (Ke-MLS, Toronto-3D, Paris-Lille-3D, SemanticKITTI) reveal a consistent asymmetric transferability: models trained on BhopalMLS transfer better than the reverse on every pair, for both Utonia(L) and Concerto(L) (mean 21.5, up to 36 mIoU points), holding even when the target is denser. Factor-controlled retraining at a fixed label budget, repeated on both models, attributes this to the coverage of BhopalMLS's subtype inventory rather than to dataset size or corridor geometry: collapsing each class to a single subtype costs 13.0 and 13.3 mIoU points for Utonia(L) and Concerto(L). BhopalMLS therefore offers a testbed for 3D perception beyond well-planned cities. Data and an interactive viewer are at https://geoai4cities.github.io/bhopalmls.
Spatiotemporal scene reconstruction with Dynamic Gaussian Splatting (DGS) fundamentally depends on perfect temporal synchronization across all cameras, an assumption rarely achievable in practice. Industry-standard synchronization requires expensive specialized hardware and complex setup, while data-driven alternatives including audio-based alignment, geometry matching, and pose tracking remain limited by restrictive environmental or scene-specific assumptions. To overcome these limitations, we propose Phase-DGS, a framework that replaces conventional timestamps with a semantic phase representing each frame's inherent state within the underlying motion cycle. Frames capturing the same motion state share the same phase regardless of which camera records them or when, naturally establishing spatiotemporal correspondence across unsynchronized cameras. We validate Phase-DGS under temporal offsets, frame drops, and camera freezes, achieving up to +8.5 dB PSNR improvement over baselines while enabling seamless integration with existing DGS backbones including RealTime-4DGS and FreeTimeGS.
Oral photographs contain rich clinical information and hold significant potential for artificial intelligence applications; however, most models are trained for individual tasks and rely on costly expert annotations. We hypothesized that self-supervised training on unlabeled oral photographs could produce transferable visual representations for heterogeneous vision tasks. To test this hypothesis, we developed DOVE (Dental Optical Visual Encoder) by domain-adaptive self-supervised pretraining on approximately 530,000 unlabeled oral photographs collected from publicly accessible sources. DOVE was benchmarked against 3 established baselines across 5 classification datasets and 4 segmentation datasets, covering both frozen backbone evaluation and end-to-end finetuning. DOVE achieved the strongest overall performance, ranking best in few-shot transfer and label efficiency on most benchmarks. Under the 20-shot frozen-backbone protocol, DOVE outperformed the second best DINOv3 by 4.37 percentage points in mean macro-F1 across classification datasets and by 4.49 percentage points in mean macro-Dice across segmentation tasks. Under end-to-end finetuning, DOVE achieved at least 80% of the strongest full-data baseline's performance across most evaluation datasets using only 10% of the labeled training data. Qualitative retrieval and feature analyses further indicated better organization of image-level and spatial representations. These findings support DOVE as a generalizable and label-efficient backbone for oral vision research.
Multimodal perception is central to many computer vision applications, including robotics and autonomous driving, where different sensing modalities provide complementary cues. Self-supervised learning offers a scalable solution for exploiting large amounts of unlabeled multimodal data. However, existing methods either neglect modality-specific information by enforcing feature-space alignment between modalities or learn only global representations without preserving spatial structure. We propose DenseTwins, a multimodal self-supervised framework that learns dense representations by explicitly decoupling the dense feature space into shared and modality-specific components. The proposed approach combines dense cross-modal correspondences with redundancy-reduction objectives, enabling the model to capture both shared semantics and modality-specific cues within a structured dense embedding space. DenseTwins jointly optimizes an intra-modal objective across augmented views and a cross-modal objective that aligns shared features while decorrelating modality-specific information. We evaluate DenseTwins across multiple multimodal benchmarks and sensing setups, achieving state-of-the-art or competitive performance across multimodal self-supervised baselines. Code available at: https://github.com/CarloSgaravatti/DenseTwins.
Recent advances in video modeling have driven substantial progress in world action models (WAMs). Existing approaches exploit pretrained video priors by decoding actions from latent representations or inferring them from generated videos. The underlying link is causal: robot actions produce changes in the scene, and video observations of these changes provide evidence for inferring the actions that produced them. However, existing training formulations do not by themselves ensure that actions and their predicted visual consequences are consistent, potentially limiting the use of pretrained capabilities. We treat video and action as paired modalities linked by this causal relationship and learn their correspondence through a unified training framework designed to better exploit pretrained video priors. Cycle WAM first augments video-action co-training with bidirectional conversion to reinforce cross-modal correspondence and recover forward and inverse dynamics. It then introduces a differentiable cycle-reconstruction objective to further couple the two mappings. The resulting model supports both forward and inverse dynamics, with the potential to improve performance through more effective use of pretrained video priors. Cycle WAM achieves state-of-the-art performance among comparable methods on LIBERO-Pro and substantially improves DreamZero on DROID. Comparisons with UWM characterize its inverse-dynamics performance and show sharper visual detail in the displayed forward-dynamics predictions.
Recovering identity-faithful, physically based surface appearance for 3D human heads from sparse images remains challenging. Existing methods often rely on UV-based pipelines, introducing seam artefacts, or operate in image space, limiting surface consistency. We present VISAGE, Vertex-based Intrinsic Surface Appearance GEneration, a surface-based conditional diffusion framework that synthesises per-vertex albedo and roughness directly on arbitrary mesh topologies, without requiring consistent UV parameterisation at training time. VISAGE combines global spectral processing with local geodesic K-Nearest-Neighbour refinement, enforcing structural coherence while restoring detail beyond the truncated spectral basis. Multi-view RGB images condition the network via visibility-aware cross-attention, enabling occlusion-robust synthesis across the full head surface. Region-specific modules specialise in semantically demanding and distinct areas (eyes, mouth, skin and hair), while a tangent-space output projection recovers fine iris detail. We further introduce a scalable procedural augmentation pipeline that enriches raw geometry scans with physically plausible albedo, roughness and normal maps for training. The predicted attributes render directly as a single RGBA vertex-colour channel. VISAGE reduces FID by 42.7% on NPHM and 22.5% and 4.4% on zero-shot FaceVerse and i3DMM, respectively, relative to the strongest baseline, with a 7.2M-parameter core network.
Video Large Language Models (Video-LLMs) have achieved strong performance on many video understanding tasks, yet remain vulnerable to temporal hallucination in time-sensitive reasoning scenarios such as scene transition understanding and event ordering. Existing solutions either require costly retraining or introduce inefficient multi-pass inference and external supervision at test time. In this work, we show that temporal evidence is already encoded in Video-LLM hidden representations but is not fully exploited during standard inference. Motivated by this observation, we propose Single-Pass Orthogonal Decomposition (SPOD), a training-free framework that recovers suppressed temporal evidence through analytical hidden-state manipulation in a single forward pass. SPOD consists of two components: Frame Distinctiveness Analysis (FDA), which identifies salient frames from middle-layer hidden-state geometry, and Temporal Delta Subspace (TDS), which constructs orthogonal temporal and prior subspaces from weighted inter-frame hidden-state differences. By decomposing final hidden states into temporal, prior, and residual components and rescaling them independently, SPOD enhances dynamic information, suppresses static appearance bias, and preserves complementary information. Experiments on VidHalluc, EventHallusion, and VideoMMMU show that SPOD consistently outperforms strong inference-time baselines across temporal reasoning tasks and model architectures while retaining near-vanilla inference efficiency. These results suggest that improving temporal reasoning in Video-LLMs may depend not only on additional supervision, but also on recovering temporal evidence already present in their internal representations. Our code is available at https://github.com/VioAgnes/SPOD.
The reconstruction of fragmented historical textiles presents a significant challenge in computational archaeology. The Oseberg ship burial, dating to 834 CE, yielded hundreds of degraded textile fragments that have resisted systematic computational analysis. While deep learning has revolutionized image-based puzzle solving, progress on archaeological textiles has been limited by the lack of domain-specific datasets and systematic evaluation of modern architectures. To address this gap, we present TEXMET, a curated dataset of 18,644 historical textile images from the Metropolitan Museum of Art's Open Access collection, representing the first textile-specific benchmark for puzzle-solving research. Using TEXMET, we conduct a systematic evaluation of three state-of-the-art puzzle-solving models: JPDVT, FCViT, and DiffAssemble. Our experiments reveal that the transformer-based models pre-trained on standard datasets fail to generalize to textiles, but domain-specific fine-tuning proves highly effective. The graph-based DiffAssemble model, when fine-tuned on TEXMET, achieves 85.89% puzzle accuracy on textile data. Most significantly, applying this fine-tuned model to 45 highly degraded Oseberg fragments yields a performance increase from 26.67% to 64.44% puzzle accuracy. These results establish TEXMET as a new benchmark for textile reconstruction and demonstrate that domain adaptation is essential for applying puzzle-solving methods to imagery of real archaeological materials.
Recent literature widely used global metrics such as AUROC and AUPRO to quantify the detection performance. AUROC and AUPRO scores are approaching 100% in some public datasets such as MVTec AD dataset and VisA dataset, which misleadingly suggests that the pixel-level anomaly detection task has already been solved. Threshold-independent metrics represented by AUROC inherently ignore the threshold selection process, which is inevitable in practical applications. Although AUPRO restricts the False Positive rates (FPRs) to an acceptable range, extremely low FPRs can lead to increased false negative rates (FNRs). We argue that there is a lack of metrics capable of quantifying the separation between the anomaly score distributions of normal and anomalous samples, which hinders advancements in anomaly detection. In response, we propose the Bounded Area Under the Kolmogorov--Smirnov curve (Bounded AUKS), a partial integral metric that integrates the difference between TPR and FPR within a data-driven bounded range. Specifically, we introduce AUKS from KS integral as a direct measure of separability between the anomaly score distributions. The bounded range is determined only by score distributions of normal test samples. Lower bound excludes the uninformative high-FPR region. Upper bound avoids evaluation in extreme regions that aggressively push FPR towards zero, which result in a very low recall. Our experiments on 9 models across MVTec AD and VisA datasets show that Bounded AUKS can address the limitations of existing metrics and has a better performance in evaluating unsupervised anomaly detection models.
We introduce iMED, the first synchronized multi-endoscope dataset for robot-assisted minimally invasive surgery (RAMIS), designed to address a fundamental limitation in surgical vision benchmarking: the absence of independent held-out viewpoints. Existing surgical datasets capture single-trajectory sequences from a single endoscope, making it impossible to distinguish geometric generalization from photometric interpolation along a narrow forward-facing path. iMED provides 340 sequences ~170K synchronized timepoints with 4 views per timepoint) recorded simultaneously from two independent stereo endoscopes across ex vivo, postmortem, and live surgical settings, spanning 14 specimens with diverse anatomical regions and motion regimes. The dataset includes calibrated camera intrinsics, ArUco-based frame-wise pose estimates with uncertainty quantification, instrument segmentation masks, and rich clinical metadata. Using a train-on-one-endoscope, test-on-another evaluation protocol, we benchmark 23 state-of-the-art methods across rigid and deformable novel view synthesis, pose estimation, feature matching, and monocular depth estimation. Our experiments show that methods relying primarily on photometric supervision degrade substantially under this held-out-endoscope setting, while methods with explicit geometric regularization are more robust across views in our benchmark. Notably, large-scale foundation models transfer surprisingly well to surgical imagery, often outperforming domain-specific models, suggesting pitfalls in current fine-tuning protocols. iMED establishes a new evaluation protocol for geometric generalization in surgical vision.
Fine-grained cross-view localization aims to precisely localize a ground camera against geo-referenced aerial imagery, but current methods typically assume a narrow geographic prior, substantially limiting their applicability when upstream localization remains coarse. To bridge this gap, we study this task over much larger aerial regions. However, this seemingly simple extension fundamentally changes the localization problem: the growing disparity in spatial extent between ground and aerial views makes reliable cross-view matching difficult to establish directly, while the increasing number of look-alike locations in larger regions introduces substantial visual ambiguity. To address these challenges, we propose RingMatch, a search-and-verification framework for wide-area cross-view localization. RingMatch first leverages predictive uncertainty to uncover plausible locations and progressively zooms into their surroundings to obtain increasingly fine-grained evidence, yielding a compact set of promising candidates. We then introduce the depth ring, a novel geometric representation that reveals subtle variations in the spatial layout around a location and serves as a view-shared spatial signature for an LVLM verifier to resolve residual ambiguity. To benchmark this setting, we construct VIGOR-Pro by composing VIGOR aerial tiles into contiguous regions with spatial extents of up to 400 m. Experiments show that RingMatch maintains strong localization performance as the aerial region expands, consistently outperforming representative end-to-end and retrieval-based methods.
Latent diffusion and flow matching models are ubiquitous in state-of-the-art generative video models. While highly effective, relying on pretrained autoencoders to compress the data into a lower-dimensional latent space also comes with drawbacks. First, training proceeds in two stages: autoencoder pretraining, with compression and reconstruction objectives, followed by latent generative model training, precluding fully end-to-end training. Second, autoencoders also lead to an inherent loss of signal, and the trade-off between reconstruction quality and generative performance in the latent space is still an active area of research. In this paper we explore the viability of generative video models directly in pixel space. We analyze recent approaches in pixel-space generative modeling of images that rely on basic transformer designs, and identify several shortcomings that limit their effectiveness for the high-dimensional pixel-space video generation. To overcome these limitations, we propose a UNet-like transformer architecture along with improvements to the training recipe and sampling strategy. We conduct controlled experiments, training latent and pixel-space models from scratch on Kinetics-600. For the standard frames-to-video task at 128 resolution, our U-JiT model improves generative FVD by 27% over prior state-of-the-art results, and by 14% against the JiT pixel-space baseline. Scaling to higher 256 resolution, we find the improvement over pixel-space and latent-based models grows as we increase the spatiotemporal compression rate up to $64 \times 64 \times 8$. Finally, we find that U-JiT improves per-frame FID by 27% over latent models and 61% over pixel-space models on class-to-video generation, with respectively 9% and 56% reduction in FVD.
Nighttime images are inherently susceptible to complex, compound degradations, making accurate quality assessment exceptionally challenging. Score-based IQA methods condense quality into a single number, lacking the multi-dimensional, language-grounded reasoning required for nighttime evaluation. Multimodal Large Language Models (MLLMs) offer a more comprehensive alternative, yet remain constrained by a critical data gap: existing real-world IQA datasets are overwhelmingly daytime-centric and often built from outdated captures, while synthetic alternatives lack nighttime-specific degradation modeling, yielding artifacts far removed from authentic nighttime conditions. To bridge this gap, we present NightIQA, a dataset and benchmark suite purpose-built for MLLM-based nighttime IQA. It comprises three core components: NightIQA-Real, a real-world dataset of 1,769 high-resolution images that we captured ourselves with modern equipment, encompassing six canonical distortion types and structured multi-dimensional annotations; NightIQA-Bench, a benchmark of 1,078 visually grounded multiple-choice questions tailored to MLLM-based nighttime IQA, organized around a four-level evaluation hierarchy spanning Perception, Technical Assessment, Localization, and Reasoning; and NightIQA-Syn, an inherently scalable, scene-aware synthesis pipeline that jointly models global-level and instance-level degradations, with an initial release of 80k high-fidelity images alongside the full generation code. Fine-tuned on NightIQA with Supervised Fine-Tuning (SFT) and Group Relative Policy Optimization (GRPO), Qwen3-VL-8B outperforms open-source IQA methods and achieves higher overall accuracy than leading closed-source models, highlighting the value of domain-specific data and structured supervision.
We present minimal solvers for joint homography and radial distortion estimation using affine- or orientation-covariant features. The core contribution is a set of novel constraints that exploit local feature geometry inherent to affine descriptors, enabling solvers that require fewer correspondences than point-based methods. Using modern robust estimation frameworks, we demonstrate that the proposed solvers are advantageous to the current state-of-the-art with a significant speed-up in the presence of outliers while maintaining comparable or superior estimation accuracy. The proposed solvers are tested on both synthetic and real images containing challenging fisheye distortions.
Optical Character Recognition (OCR) is among the oldest and most widely deployed applications of artificial intelligence. This survey reviews its development, focusing on the Foundation Model Era. We define OCR through faithful transcription: within a specified visual scope, OCR should completely reconstruct the text, notation, and document structure observable in the source image, and every textual, notational, or structural element in the output must be verifiable from visual evidence in that image. We trace the development from specialist OCR models toward unified models, examining joint text detection and recognition, structured sequence generation, and the use of pretrained vision-language models (VLMs). We organize contemporary OCR systems into five coexisting families: modular toolkits and task-specific models, specialized document VLMs, hybrid workflows, general-purpose VLMs, and commercial products and managed services. We compare their architectures, data, and training, examining hallucination and omission, insufficient spatial grounding, and inference cost in generative OCR. We review evaluation from character and scene text recognition to parsing individual structural elements and full-page transcription, highlighting gaps in consistent output definitions, attribution of performance to individual components, and coverage of real capture conditions and visible content and structure. Finally, we summarize the challenges facing OCR and discuss directions for future research. We continuously track related work at https://github.com/zhihengli-casia/Awesome-OCR-in-the-Foundation-Model-Era.
Multimodal agents use web and image tools to answer questions beyond their internal knowledge. Some search tasks use images mainly to identify an initial entity, then rely on text retrieval. These tasks offer limited insight into how agents connect information across images, objects, and search steps. We therefore focus on visual context management. This involves organizing and using visual information and linking it to other findings during search. Visually intensive tasks require agents to combine object appearance, local details, or spatial relations with external information. We introduce VisSearch-Bench, with 204 human-written tasks across 7 main domains and 25 subdomains. It covers Set-wise Visual Search, Sequential Visual Search, Hybrid Wide-Deep Search, Competitive Visual Disambiguation, and Visual-Structure-Guided Search. Each task provides a reference answer, traceable evidence, and scoring rules. Accuracy measures complete task success, while Process Score measures the correctness and completeness of individual results and subquestion answers. Across 16 multimodal models, the best system fully solves only 26.47% of tasks, even with search tools. These results highlight the challenge of linking visual evidence with search results to produce complete answers.
Large vision-language models (LVLMs) can process interleaved text and multiple images in a single context, but how they internally identify the image relevant to a question remains poorly understood. We study this grounding step as in-context image retrieval and introduce ICIR-MCQ, a controlled probe for head-level analysis of image retrieval. Using each head's attention mass over image-token spans, we first identify sparse pointer heads that reliably point to the target image. These heads transfer beyond the probe: a single pointer head is competitive with external vision-language retrievers on a naturalistic multi-image retrieval benchmark, showing that LVLMs contain a strong internal image retrieval signal. Attention alone, however, shows where a head reads from, not what its output passes on to later layers, so we introduce a complementary output-side analysis. For each head, we train a lightweight image retriever on its value-weighted output and use it to identify writer heads, whose outputs contain enough information to identify the target image. Surprisingly, the pointer and writer criteria select substantially different head sets, with only 35 to 47 heads overlapping among the top-100 heads under each criterion. Targeted set-partition ablations show that the heads most important for standard multi-image inference are concentrated in this pointer-writer intersection, while heads selected by only one criterion show less consistent separation from random-head controls. The most consistent causal effects arise from heads selected by both the attention-based pointer and output-side writer criteria. Code and data: https://github.com/parkquasar/Image-Retrieval-Heads.
Reliable multi-sensor perception in autonomous vehicles requires accurate calibration between cameras and LiDAR. However, calibration drift is often unavoidable in long-term deployments: vibrations, thermal effects, and minor mechanical shocks may alter the relative pose between sensors, leading to systematic errors in downstream fusion tasks. We propose MiCaDe (Miscalibration Change Detection), an online solution detecting when the extrinsic LiDAR-camera calibration parameters are no longer accurate by means of sequential change detection. MiCaDe requires no calibration targets, or modification of the perception stack, providing low false-alarm rates with negligible computational overhead. Our key insight is that 3D and 2D bounding boxes produced by standard object detectors should remain geometrically consistent under correct calibration. By matching cross-modal detections, we derive geometric consistency metrics that serve as sensitive indicators of extrinsic drift. These metrics are aggregated into fixed-size batches and scored against a reference distribution, producing a likelihood stream that is monitored by a Change Point Model (CPM). Crucially, the CPM accumulates statistical evidence over time, enabling detection of subtle drifts that would otherwise go unnoticed. Experiments on multiple long-sequence datasets and on a real-world dataset with physically induced miscalibration confirm reliable detection under diverse conditions. Code available at: https://github.com/CarloSgaravatti/MiCaDe.
Long instructional videos are increasingly used in medical education, industrial training, and procedural knowledge transfer, yet their evidence is often incomplete or unreliable: subtitles may be missing, ASR noisy, OCR sparse, and decisive actions briefly shown without narration. Existing VideoQA systems typically return labels or free-form text, making answer support difficult to inspect. We study Long Video Moment Question Answering (LVMQA), where a system returns timestamped answer-supporting evidence. We propose EP-LVMQA, an evidence-preserving coarse-to-fine framework comprising an Uncertainty-Aware Multimodal Evidence Timeline, a Coarse Evidence Planner, and an Evidence-Conditioned Fine Localizer. An evidence card transfers planner scores, matched cues, source-confidence proxies, modality-specific evidence, neighboring context, and a temporal prior between the latter two modules. On MedVidQA, EP-LVMQA achieves 26.1 [email protected] and 31.8 mIoU, improving the strongest non-ours results by 6.3 and 5.1 points. It raises Suff.@2 and Ver.@2 to 25.4 and 22.6, gains of 9.5 and 8.8 points. Under matched low-quality perturbations, average relative degradation is reduced from the strongest non-ours value of 14.6% to 11.1%. On Ego4D-NLQ and QVHighlights, EP-LVMQA remains broadly comparable to established task-specific localization methods.
Video generation has progressed from isolated clips to coherent short-form audiovisual sequences, and the bottleneck is shifting from rendering to semantic control. This report summarizes the observations and insights on multimodal understanding gained from successive generations of Kling. We argue that generation quality is the projection of multimodal understanding through the entire data--conditioning--alignment--evaluation chain, and we examine this chain module by module. Kling-MLLM, a shared multimodal foundation model that unifies image, video, audio, synchronized audio--video, and interleaved inputs, is specialized for each downstream module. Because a DiT is trained on far fewer training samples than a language model, we treat captioning as a semantic contract that maximizes description density, and extend it to reference-grounded captioning that makes reference bindings explicit. Prompt enhancement translates user intent into this caption distribution: basic PE is derived from captions of compelling videos and refined with text-level and generator-in-the-loop reinforcement learning, while agentic PE refines the story and retrieves compelling examples. We show that a reliable text encoder comes from perceptual training rather than from stronger language ability, and that candidates can be screened from text alone before end-to-end training. Reward modeling pairs a general reward model for explainable, localized critiques with a decision reward model for fast multidimensional scoring, treating perceptual bandwidth as a first-class design parameter. Finally, we review task-specific automatic evaluation, focusing on protocols that expose scoring shortcuts and help trace failures to their upstream source. We hope these lessons offer practical guidance for building the understanding stack behind controllable video generation.
Clustering faces by identity in long, continuous video streams is a challenging task that serves as a building block for human-centric video analysis. The majority of existing face clustering models are offline, i.e., they assume the entire data to be available altogether. In many practical scenarios, however, the entire data is either unavailable or poses computational challenges to be processed in its entirety. A handful of online methods that exist rely on geometric visual features and simple thresholding techniques, which fail when the faces exhibit significant appearance variations in long, unconstrained videos. To this end, we present VISTA, the first vision language framework for online face clustering in long videos. VISTA leverages semantic reasoning in a controlled, uncertainty aware fashion to maintain both high cluster purity and long range identity continuity. This makes it robust to the variations in illumination, pose, and costume changes that the faces and characters exhibit in long real world videos. Extensive experiments on the VPCD benchmark dataset (with 15 full episodes from The Big Bang Theory [2007-2019], Buffy the Vampire Slayer [1997-2003], and Sherlock [2010-2017]) demonstrate that VISTA achieves a robust precision and recall balance, consistently improving over the strongest matched online unsupervised baseline (COFC) under identical detector, embeddings, and evaluation protocol. Code and supplementary material: https://github.com/SkyJiashu/VISTA.
Robustness verification is essential for ensuring the safety and security of neural networks, but current methods focus heavily on norm-ball attacks, which do not adequately model typical real-world threats that present physical perturbations, known as patch attacks. A naive approach requires computationally prohibitive enumeration of all possible patch positions. To address the challenge, we propose a novel neural network verification method specialized to the patch-attack threat. Instead of enumerating patch locations, we first model the patch attack with group-wise sparsity and formulate its verification methods as a mixed-integer semidefinite program (MISDP) by applying SDP relaxation to the neural network. We then propose three relaxations, including Group-Lasso relaxation, that remove the integer variables while preserving the sparse, group-wise structure of the original attack, enabling substantially efficient verification. Our empirical analysis demonstrates that the proposed relaxations require less than 3% of the computation time of the original MISDP, while the Group-Lasso relaxation incurs only a 0.34\% average increase in the objective value over the original formulation. Furthermore, Group-Lasso achieves a verified rate of 91%, compared with under 70% for prior methods.
High-order dependencies among views can be modeled by tensor singular value decomposition (t-SVD) in multi-view subspace clustering. However, the tensor nuclear norm often used with this framework assigns the same asymptotic marginal penalty to singular values of different magnitudes, which may excessively shrink dominant components that encode cluster structure. We propose HTNN-MSC, which replaces this norm with a bounded hyperbolic tangent tensor rank surrogate. The surrogate is strictly concave on the positive half-axis and has a Lipschitz continuous derivative. Its marginal penalty decreases as singular values grow. We develop an alternating direction method of multipliers solver in which the tensor subproblem decomposes into scalar frequency-domain shrinkage problems. Safeguarded multi-start Newton iterations and candidate-objective comparison implement the resulting hyperbolic tangent thresholding operator. The shape parameter is scaled by the input spectrum. We also establish o-minimal definability of the augmented objective. Under explicit boundedness, descent, relative-error, and exact-block conditions, the Kurdyka-Lojasiewicz framework guarantees convergence of the full sequence to a KKT point. On 23 datasets, HTNN-MSC achieves a mean clustering accuracy of 0.8404 and an average accuracy rank of 2.78 against nine representative methods. Friedman tests and Holm-adjusted Wilcoxon comparisons reveal significant overall differences, although several pairwise differences remain nonsignificant. HTNN-MSC records 19 wins, one tie, and three losses against the convex t-SVD-MSC skeleton. A same-skeleton ablation also shows that the proposed surrogate does not uniformly outperform alternative nonconvex penalties.
Complex visual question answering often requires vision-language models to think with images, i.e., actively acquire local visual evidence by zooming into informative regions of high-resolution images. Our error analysis shows that many failures in this setting originate from incorrect observation actions, where the model fails to localize key regions or obtain crops that contain sufficient evidence for answering. We further observe that bounding-box tokens exhibit substantially higher generation entropy than ordinary language tokens, indicating high uncertainty when the model decides where to look. However, existing reinforcement learning methods based on final-answer rewards provide only trajectory-level feedback, making it difficult to assign precise credit to the observation actions. We propose Observation Policy Optimization (OPO), an RL algorithm for optimizing observation actions in tool-augmented thinking with images. OPO consists of two core modules. First, Uncertainty-Guided Observation Branching (UOB) treats each image zoom-in tool call as an observation event and selectively branches at high-uncertainty, low-redundancy events during rollout, enabling efficient exploration of alternative cropping decisions and their resulting visual evidence. Second, Evidence-Localized Advantage Attribution (ELAA) compares sibling branches using local evidence-sufficiency rewards and assigns credit only to the corresponding observation-action tokens. By decoupling observation-action optimization from trajectory-level outcome supervision, OPO improves visual evidence acquisition and further enhances visual reasoning performance. Experiments show that OPO consistently improves Qwen3-VL models across scales and achieves competitive performance against larger models and tool-augmented baselines. Code is publicly available.
Webcam eye tracking can greatly accelerate data collection in basic and applied research by reaching large, diverse samples of participants online. However, its spatial performance is considered well below that of hardware-based systems, limiting its use. We evaluated the first-generation Chiasm webcam eye tracker in a large online study ($N = 505$) spanning diverse participants, devices, and recording conditions. Chiasm achieved a mean spatial accuracy of 2.39 cm ($\approx 2.28^\circ$ at 60 cm), spatial precision (SD) of 1.05 cm ($\approx 1.00^\circ$ at 60 cm), and sample-to-sample precision (RMS-S2S) of 1.29 cm ($\approx 1.23^\circ$ at 60 cm). For the 91% of participants who met a 3 cm calibration criterion, spatial accuracy was 2.15 cm ($\approx 2.05^\circ$ at 60 cm). After three minutes of a task that encouraged head movement, spatial accuracy declined by 0.59 cm, while the gaze center at each target shifted by a mean distance of only 0.37 cm. On the validation block, the offset was 0.30 cm larger for men than for women. Age, region of residence, face luminance, and Michelson contrast showed no reliable relationship with spatial accuracy. A higher eye aspect ratio, a more open eye, was associated with a smaller offset. Wearing glasses decreased spatial accuracy on every validation block. In a comparison between a random subsample ($N = 101$) and a separate sample tested with the open-source tracker WebGazer ($N = 101$) using an identical protocol, Chiasm showed better spatial accuracy (2.18 vs. 4.51 cm) and spatial precision (SD; 1.01 vs. 1.55 cm). WebGazer showed better sample-to-sample precision (RMS-S2S; 0.79 vs. 1.26 cm), which likely reflects conservative, over-smoothed estimates rather than superior stability. These results suggest that Chiasm is narrowing the gap between webcam and hardware-based eye tracking, making large-scale gaze research "in the wild" a reality.
Test-time scaling (TTS) improves generative models by allocating additional inference-time computation to sampling, search, and verification. Existing image generation approaches, however, typically rank completed images or image-centric intermediate states. We study TTS for parallel multimodal discrete diffusion language models, in which reasoning tokens and image tokens are decoded jointly within a single generation trajectory. We first diagnose a limitation of conventional final-image selection: on GenEval, a CLIP-style image-prompt score is weakly aligned with within-prompt compositional correctness, leaving substantial headroom between verifier selection and oracle selection. We then propose PATTS, a novel parallel-aware TTS framework that searches over intermediate thought-image states using cross-modal verifier signals. PATTS uses a state-dependent reliability weight, derived from model-internal trajectory diagnostics, to modulate the influence of external semantic verification during generation. In the fixed N=32 evaluation on MMaDA-Parallel, the PATTS reaches a GenEval score of 0.844, compared with 0.628 without TTS, 0.787 for Best-of-N, and 0.810 for FKD. These results show that reliability-aware trajectory verification can improve test-time selection for parallel thought-image co-generation under the evaluated search budget. Our code release is at https://github.com/Ringo-Star/PATTS.git
Gait biometrics aims at identity recognition by appearance or pose features captured during unconstrained human walking. Existing methods predominantly rely on binary silhouette images, inherently characterized by low information entropy, and fail to fully utilize the dynamic information in gait sequences, limiting their ability to handle cross-time variations effectively. Consequently, these methods encounter significant challenges in the wild. They are susceptible to variations in clothing, carried objects, and viewpoints, as well as dynamic environmental conditions, all of which lead to substantial degradation in recognition accuracy and robustness. To overcome these challenges, we propose a pose-knowledge-aware approach specifically designed for robust gait recognition in the wild. First, we propose a novel Dynamic Pose-Parsing enhanced Silhouette gait representation paradigm that substantially enhances the information entropy and effectively captures fine-grained behavioral cues by integrating pose-parsing cues with traditional silhouettes. Subsequently, we develop a dual-branch Dynamic Pose-Knowledge-Aware Gait network. The framework consists of two complementary branches: (1) a 2D dynamic pose-aware branch that extracts pose-enhanced features from our proposed DPPS representations, and (2) a 3D Skinned Multi-Person Linear branch that leverages the 3D SMPL model to capture rich and comprehensive 3D dynamic pose information. Finally, the features are integrated to facilitate accurate and robust gait recognition. Extensive experiments on four challenging in-the-wild gait datasets demonstrate the effectiveness and generalizability of the proposed DPPS representation. The complete framework is further evaluated on SUSTech1K, CCPG, and Gait3D, where SMPL information is available or can be consistently estimated, achieving competitive performance under diverse real-world conditions.
Radar is a core sensor modality for scene perception to achieve higher levels of autonomy in automotive driving. A common occurrence in automotive radars is clutter - detections of non-existent moving objects, that can adversely impact target detection and classification performance and subsequent driving actions. We propose lightweight tiny graph transformer network (TGTNet) models for classifying clutter from stationary and moving targets in the scene. Performance evaluation on the public RadarScenes show that our proposed TGTNet models achieve similar classification performance in precision and recall metrics in comparison to state of the art models, with one to two orders of magnitude lower model size and significantly faster inference.
Despite decades of progress, image codecs remain difficult to adapt to diverse real-world compression scenarios for two main reasons. First, most image codecs are optimized for a specific objective and require substantial redevelopment when the compression goal changes. Second, they typically assume clean inputs, whereas sensor-captured images often contain degradations that alter rate-quality behavior. To address these challenges, we propose Practical Image Coding Agents (PICA), a multi-agent framework that adapts existing codecs to diverse user requirements and potentially degraded inputs. PICA consists of four collaborative agents: a Perception agent that interprets user intent and analyzes image content, an Improvement agent that jointly considers bitrate and reconstruction quality to guide pre-coding restoration, a Coding agent that refines quality-control settings from global to regional levels, and an After-coding improvement agent that addresses residual degradations and compression-induced artifacts through restoration guided solely by image quality. To enable codec-agnostic regional adaptation, we introduce Agentic ROI Coding (AROIC), which treats the codec as a black box and allows the agent to automatically schedule, execute, evaluate, and reflect ROI coding plans without architectural modifications or codec-specific retraining. We integrate these four agents with a Scenario-Guided Quality-Rate (SGQR) evaluation strategy to enable more effective scenario-adaptive compression across heterogeneous codecs. Comprehensive experiments on clean, noisy, and blurred images across standard, perceptual, and machine-vision compression scenarios demonstrate that PICA consistently enhances the compression performance of both the conventional H.266/VVC codec and the neural Cheng2020 codec, outperforming competing compression methods on the Kodak, CLIC2020, and HEVC datasets.
Aerial-Ground Person Re-Identification (AG-ReID) aims to match pedestrian images captured by unmanned aerial vehicles (UAVs) and ground-based surveillance cameras. The task remains highly challenging due to severe viewpoint discrepancies, frequent occlusions, and substantial domain gaps between aerial and ground imagery. Beyond these observable factors, existing methods often overlook two fundamental structural issues: cumulative positional drift during hierarchical feature extraction and semantic inconsistency across cross-view feature distributions. To address these challenges, we propose ProAlign, a Progressive Positional and Prototype-Guided Alignment Network for AG-ReID. ProAlign comprises two key components: a Layer-wise Progressive Positional Embedding (LPPE) module and a View-Aware Prototype Contrastive Learning (PCL) module. LPPE performs adaptive positional calibration throughout transformer layers by employing conditional positional encoding in shallow layers to mitigate local spatial distortions, while introducing learnable static positional embeddings in deeper layers to reinforce global semantic priors. Meanwhile, PCL maintains view-specific aerial and ground prototypes for each identity and enforces cross-view semantic consistency via a dual-prototype contrastive objective. Extensive experiments on CARGO and two real-world AG-ReID benchmarks demonstrate the effectiveness of ProAlign, achieving state-of-the-art overall retrieval performance on CARGO with improvements of 1.60% in Rank-1 accuracy and 5.01% in mAP over the strongest competing methods.
Requested-value control is stricter than continuous steering: given $c$ on a human-rating scale, the generated image should attain that value from only limited ratings. We present ScoreDial, which fits a differentiable regressor $R$ to 100-479 human-rated images; once $R$ is fixed, a requested value $c$ is defined on its output scale, and learned target conditioning is paired with error-adaptive guidance that repeatedly reduces $|R(\mathbf{x})-c|$ during sampling. Across tire slip resistance, interior visual complexity, food desire-to-eat, and soap translucency, using one set of sampler settings shared across all four, ScoreDial reaches requested values and achieves, on all four attributes, $R$-MAE at most 0.013 over a range of width 0.8 and Spearman $\rho=0.980$, the maximum attainable under our evaluation protocol. Because $R$ also drives sampling, we evaluate agreement with $R$ separately from matched sweeps, an independent auditor fitted to the same ratings on a backbone none of the deployed regressors uses, and blinded human judgments. MPGD-flow also reaches the requested values under $R$, but ScoreDial has larger auditor displacement on every attribute, the largest among all compared methods, and a stronger MPGD-flow setting gives up target agreement without closing this gap. On every attribute, removing target conditioning leaves low $R$-MAE but more than halves auditor displacement, separating precise score correction from attribute movement. Blinded rating studies with 15 raters per attribute show that mean human ratings track $c$ on tire and soap, with linear $R^2=0.665$ and $R^2=0.786$, and in forced-choice comparisons of matched sweeps, raters chose ScoreDial's as the clearer progression in at least 84% of judgments against every baseline.
With the increasing importance of mobile camera quality in modern smartphones, growing attention has been directed toward computational photography and advanced image signal processing (ISP) algorithms aimed at enhancing various perceptual attributes of captured images. This creates a need for efficient deep learning models for this problem that are not only performant but can also be deployed on constrained mobile hardware. In this Mobile AI challenge, we address this problem and propose the participants to design fast solutions that can reconstruct RGB photos from RAW Bayer camera data while running on popular smartphone GPUs from Qualcomm and Arm. For this, the participants were provided with a large-scale Fujifilm UltraISP dataset consisting of RAW-RGB image pairs captured with the Sony IMX586 Quad Bayer mobile sensor and a professional 102MP medium format FujiFilm GFX100 camera. The runtime of all models was evaluated on the Snapdragon 8 Elite Gen 5 and Dimensity 9500 chipsets with the Adreno and Mali GPUs, respectively. Top solutions proposed in this challenge are able to reconstruct high-quality 5MP RGB image from raw data on both platforms under 100 milliseconds. A comprehensive description of the models developed in the challenge is provided in this paper.
Saliency maps are offered as a safeguard for medical image classifiers, but whether they reveal individual errors at a new hospital remains largely untested. We trained a convolutional network and a vision transformer on NIH ChestX-ray14 and evaluated 303,768 decisions per model at the training hospital and at two external sites, in the USA and Vietnam, with radiologist-consensus labels. We scored each explanation by its anatomical enrichment, the area-normalized concentration of attribution in a segmented thoracic region, and tested whether it detects errors beyond the model's confidence. Grad-CAM localized findings less often than radiologists (hit rate at most 0.575 versus 0.888). Adding enrichment to a confidence-based error detector calibrated at the training hospital never raised its area under the curve by more than 0.011, and for the convolutional network the relation between enrichment and correctness reversed between hospitals, degrading the transferred detector. Model confidence, not saliency, should anchor deployment monitoring.
On-device RGB photo enhancement is a popular task that is needed for quality improvement of photos captured with mobile devices as well as for retouching of images acquired through other sources. This creates a need for efficient deep learning models for this problem that are not only performant but can also be deployed on constrained mobile hardware. In this Mobile AI challenge, we address this problem and propose participants to design fast solutions that can perform comprehensive enhancement of RGB photos while running on popular smartphone GPUs from Qualcomm and Arm. For this, the participants were provided with a large-scale DPED dataset consisting of RGB image pairs captured with an old iPhone 3GS smartphone and a professional Canon 70D DSLR camera. The runtime of all models was evaluated on the Snapdragon 8 Elite Gen 5 and Dimensity 9500 chipsets with the Adreno and Mali GPUs, respectively. Top solutions proposed in this challenge are able to enhance Full HD resolution RGB images on both platforms under 300 milliseconds. A comprehensive description of the models developed in the challenge is provided in this paper.
Footstep patterns, captured using pressure or force-sensitive walkways during natural walking, offer a convenient and passive approach to biometric recognition. However, footwear variability poses a major challenge to practical deployment, as it impacts both the foot-sensor interface and the user's underlying gait mechanics. This study considers the particularly difficult scenario where users enroll under one fixed footwear condition but must later be recognized in arbitrary, unseen footwear. Using the StepUP-P150 dataset, we show that footwear-induced shift, while substantial and heterogeneous across individuals, contains shared structure that can be learned from a training population and transferred, zero-shot, to previously unseen users and footwear styles. We do this using BiStepNet, a novel architecture that decomposes spatial and temporal identity cues into independently trainable streams and outperforms compact 3D spatiotemporal baselines for cross-footwear recognition. We demonstrate that cross-footwear recognition performance scales systematically with the volume and diversity of footwear representation in the training set, with gains transferring to footwear styles not directly observed during training. Moreover, we show that auxiliary gait datasets with only partial modality overlap (incorporated through the architecture's decomposed design) can be leveraged to further improve robustness to unseen footwear conditions.
Pretrained video generation models distill internet-scale motion priors into robot policies, but full video is a redundant signal for action prediction. We argue that dense 3D motion is the medium through which video pretraining best transfers to robot actions, and that predicting motion rather than video affords better sample-efficiency for action prediction. FloMo is a 5B video-generation model fine-tuned to predict 3D scene-flow and action tokens. Rendering scene flow as RGB and encoding it into the same latent space as video enables a pretrained video generation backbone to efficiently adapt to predict 3D scene flow. Co-trained on action-free human video and action-labeled robot teleoperation data, our model benefits from human-video pretraining and generalizes to unseen objects, motion primitives, and tasks. Replacing motion prediction with a video prediction objective degrades out-of-distribution generalization, while adding a video prediction target alongside motion lowers policy success rather than improving it. When motion, video, and action are predicted jointly, action tokens attend far more to motion than to video, suggesting that predicting video wastes model capacity. Together, these results indicate that motion effectively mediates the transfer from video pretraining to action. More information can be found at flomo-wam.github.io.
Multimodal discrete diffusion language models (dLLMs) generate responses through iterative mask prediction and offer a promising alternative to autoregressive large vision-language models. However, they still suffer from hallucination, producing outputs that are plausible under language priors but insufficiently grounded in the image. We argue that hallucination in multimodal dLLMs is not only a token prediction problem, but also a premature commitment problem: during iterative denoising, some masked positions are unmasked too early because their confidence is driven more by language priors than by visual evidence, and these early commitments can bias later generation. To address this issue, we propose Visual Gain Ordering (VIGOR), a training-free and plug-and-play inference strategy that reorders masked positions according to counterfactual visual evidence. At each denoising step, VIGOR compares the confidence of each candidate token under the original image-conditioned pass and an additional visual-ablation pass, and prioritizes positions whose predictions are more strongly supported by the image. Experiments on LLaDA-V and Lumina-DiMOO show that VIGOR consistently reduces hallucination and improves multimodal reasoning performance across benchmarks. Code is available at https://github.com/THU-BPM/Vigor.
Estimating semantic correspondences between different object instances of similar categories in real-world images is a fundamental challenge in computer vision. While the recent progress in foundation models has significantly advanced solutions for such difficult image correspondence problems, respective methods are often insufficiently regularised. For example, common nearest-neighbour matching with foundation model features often results in noisy correspondences, which is particularly prominent when solving for dense correspondences. In this work, we tackle image matching via functional maps, which have been popularised for 3D shape matching due to their powerful spectral formalism utilising an efficient low-dimensional linear representation. However, functional maps require that domains (in our cases the rectangular image grids) are equipped with an informative and non-trivial geometry. To define a meaningful manifold structure for images, we use Galerkin's method from finite elements to derive a discrete Laplace-Beltrami operator (LBO) based on a manifold embedding of deep image features. Further, we leverage a neural adjoint map that allows to represent non-linear mappings. We demonstrate that our method sets the new state of the art among zero-shot image correspondence methods on multiple dense correspondence benchmarks of real-world images. Our code is publicly available: https://github.com/NafieAmrani/NAMI
Repeated robotic monitoring requires localization across visits to the same environment, even if the environment changes. Such changes can substantially reduce persistent visual content, and repetitive structures can lead to incorrect cross-session correspondences. In this paper, we address visual multi-session registration of a new data recording (the query session) to a previously reconstructed reference map. Under substantial visual and structural changes, cross-session localization may be possible only for parts of the trajectory. In our approach, we therefore rely on a sparse set of reliable absolute pose constraints and combine them with within-session relative-pose information to register the complete trajectory to the reference map. We first estimate absolute alignment hypotheses through visual place recognition, local feature matching, and geometric verification. We then use sequence consensus to reject hypotheses that are inconsistent with a common query-to-reference alignment and retain the remaining poses as absolute anchors. These anchors are refined through featuremetric alignment against a Gaussian feature field and combined with within-session relative-pose constraints in a robust pose-graph optimization. We evaluate our approach on 15 cross-session experiments from the challenging HILTI26 construction-site dataset, covering substantial scene changes and difficult-to-match environments. Our method achieves 94.4% recall within 1m and 100.0% within 5m, outperforming independent image localization, which peaks at 65.3% and 70.7%, respectively, as well as direct registration of independently reconstructed Structure-from-Motion geometry. Our results show that sparse, reliable absolute anchors can provide accurate and complete trajectory registration even when reliable cross-session correspondences are available only for part of the query session.
Vertical forest structure influences fire behavior by regulating understory-to-canopy fuel connectivity, yet operational fuel-type models represent this complexity through discrete classes that only indirectly capture vertical continuity. High-density point clouds offer an opportunity to characterize vertical fuel connectivity in a more explicit and continuous manner, but specific methodological approaches are still required. We applied Gaussian decomposition to vertical height profiles derived from terrestrial laser scanning (TLS) point clouds across 25 permanent forest plots to characterize geometric vertical fuel continuity. A multiscale analysis spanning from the plot scale to ~0.5 $m^2$ units was used to evaluate geometric, probabilistic, and overlap metrics for characterizing fuel strata. The method reproduced the vertical transition between shrub and tree strata, with median Pearson correlations ranging from 0.83 to 0.96 across analysis levels. Probability density overlap metrics and separability indicators, such as the Jeffries-Matusita distance, provided complementary descriptors of vertical continuity. Intermediate spatial scales (3-6 m cells) provided a useful compromise between spatial detail and the consistent representation of shrub-canopy interaction patterns. Finer scales increased variability due to point density reduction and profile irregularity, and low mean squared error values were found insufficient as sole performance indicators. Gaussian decomposition applied to TLS point clouds enables explicit quantification of vertical fuel continuity, a limitation of current discrete classification systems. Continuous vertical connectivity metrics derived from this approach offer a pathway for improving ladder fuel characterization and strengthening decision-making support in wildfire risk assessment.
High-fidelity photovoltaic (PV) module mapping requires complete instance recovery and accurate delineation. Vision foundation models offer zero-shot segmentation, but converting incomplete and inconsistent predictions across views into a complete, geometrically accurate map of individual modules remains challenging. We propose the Multi-View PV Module Mapper (MV-PVMapper), a training-free framework coupling vision foundation models with unmanned aerial vehicle (UAV) photogrammetry. First, Segment Anything Model 3 (SAM 3) generates candidates from original images using text prompts. Their contours are then transferred into object space through per-module slope correction to limit distortion from surface-model noise, and verified against representative module dimensions to guide cross-view instance selection. Finally, accepted instances return to all covering images as box prompts for SAM~3, supplementing text prompts with spatial cues for iterative segmentation, verification and fusion. On five-direction surveys of three operational rooftop PV plants at approximately 1 cm nadir ground sampling distance, two feedback iterations recover 7,710 of 7,711 reference modules with no false positives at an intersection-over-union (IoU) matching threshold of 0.5. Macro-averaged area precision and recall reach 99.00 % and 98.52 %, respectively. Averaged across sites, the aggregated Jaccard index reaches 97.55 %, compared with 60.73 % and 41.24 % for orthomosaic segmentation and multi-view pixel-voting baselines, respectively; average precision at the stricter IoU threshold of 0.95 reaches 95.67 %. Ablation studies show that module-size constraints are critical for instance separation, while slope correction and feedback to all covering views improve boundary accuracy. These results are achieved without task-specific image annotation or segmentation-model weight updates.
Public cervical cytology benchmarks release many cell crops cut from far fewer microscope fields or slides and are often split at the crop level, so test cells share acquisition parents with training cells. In a preregistered study, crop-level splitting raised SIPaKMeD accuracy by 0.97 percentage points across twelve architectures and twenty seeds (95% CI 0.59-1.39), and CRIC accuracy by 12.08 points (11.16-12.99). On SIPaKMeD, a factorial that fixes training crop and parent counts attributes the gain to sibling exposure (1.73 points, 0.95-2.51), not to the extra parent diversity of crop-level splits (0.00). Parent identity is decodable at about 100 times chance, yet erasing 82% of its above-floor linear recoverability left the gap unchanged, and Grad-CAM did not distinguish leaking from clean models; matching test cells' color statistics to an unseen same-class field removed most of the advantage. Decodability and saliency cannot substitute for a parent-disjoint split.
Vision-language verifiers judge whether an image faithfully matches a textual description, yet existing training pipelines typically rely on static supervision from stronger external judges or curated hard-negative data. Such supervision requires external generation or annotation, is teacher-bounded, and is difficult to adapt as model failures evolve. We introduce PROVE (Perturb-and-Repair Optimization for Vision-Language Evaluation), a self-play framework that trains verifiers through a closed perturb-verify-repair-verify loop. Starting from a known-correct image-caption pair, a Mutator introduces a typed perturbation over objects, attributes, counts, or relations. The verifier then judges the perturbed caption and provides textual feedback, which a Repairer uses to recover a faithful caption for re-verification. These two verification rounds produce structured rewards for informative mismatches and visually grounded repairs. Since perturbation, verification, and repair are role-conditioned behaviors of the same evolving multimodal backbone, updating the shared parameters also improves the verifier itself. Experiments show that PROVE improves fine-grained compositional verification across model scales and families and strengthens visual-detail robustness on the reference backbone, with limited, benchmark-dependent changes on broader multimodal tasks.
We propose PadLoc, a training-free localization back-end that places a moving sensor within a known floor plan. Floor plans are cheap, persistent, and robust to appearance change, but recent learned-depth methods localize against them by filtering per-frame depth through dense $(x,y,\theta)$ pose grids. PadLoc keeps the swappable depth front-end and replaces the dense grid back-end with sparse geometric matching: dominant wall orientations define a small pose-candidate set, masked normalized cross-correlation scores observed free space against the plan, and a moving-pose Gaussian-mixture Bayes filter plus consensus readout decodes the trajectory. Holding each competitor's depth fixed, PadLoc matches or beats UnLoc's forward filter and the F3Loc filter at every Gibson trajectory length, and UnLoc's offline refinement from $T=35$ on; it exceeds Z-FLoc's published results with a shared MapAnything front-end. On Bonn LiLocBench, PadLoc improves pooled SR@1m over UnLoc by 23-32 pp under wheel odometry and 35-43 pp with ground-truth motion; with full-FOV LiDAR plus wheel odometry the same readout reaches 100% SR@1m at 9-10 cm median error on the static sequence. On the Hilti-Trimble Localization Challenge PadLoc localizes a camera-only fisheye rig on construction floors hundreds of metres across at 0.90-0.98 online SR@2m on three of five sessions; adding learned wall isolation, applied to every session, covers all five at 0.67-0.92 with the localizer unchanged throughout. PadLoc thus matches or outperforms dense grid back-ends while preserving sensor modularity and a compact state that does not grow with trajectory length.
Multimodal large language models (MLLMs) allow social scientists to analyze video at scale, but researchers must decide which parts of a video to provide as input. We use the term representation validity to examine how text, audio, video, and combined inputs affect measurement and subsequent analysis. We compare input representations across six open-weight MLLMs and three human-annotated video datasets. No representation consistently performs best. On seven news-related constructs, native-video performance varies little across models (macro-F1 = .70-.77), while extracted-text performance ranges from .52 to .80. Three models perform better with text and three with video. Combining inputs rarely improves performance. Higher classification accuracy also does not reliably produce estimates closer to those based on human codes. The highest-F1 representation best reproduces human-coded regression coefficients in 17 of 42 comparisons. Even when each model uses its highest-F1 deployable representation, 45% of sample-prevalence estimates differ from the human-coded benchmark by more than ten percentage points. Input representation therefore requires validation for both the construct being measured and the quantity estimated from the resulting labels.
Transfer learning from natural images is standard in supervised and increasingly adopted in self-supervised medical image analysis, but its role in generative modelling, and in particular diffusion denoisers, remains underexplored. Medical diffusion models typically train the denoiser from scratch, with no systematic evaluation of natural-image transfer. We analyse this across latent and pixel paradigms, model sizes (131M-952M) and two radiology datasets (RadImageNet, BraTS), and ask which aspects of transfer support generation. We find that: i) Natural-image initialisation consistently improves generation, by 21-34% relative gFID in pixel space against 14% in latent space, where the tokeniser supplies much of the prior. gFID gains mirror downstream pathology classification and radiomic-feature FD, both proxies for clinical fidelity. ii) Benefits reflect spatial structure, not semantics: semantic probing does not predict generation quality, whereas a spatial-structure metric adapted to internal denoiser representations tracks gFID at $|r|=0.85$, positioning spatial organisation as a channel through which pretraining manifests. iii) Mixed-domain denoiser training shows that natural and medical images share similar layer-wise representations up to the late blocks, and mixing natural images into medical training improves fidelity. iv) Transfer benefit is tied to natural image initialisation, outperforming in-domain medical pretraining and several reinitialisation schemes. Overall, natural image denoisers transfer positively to medical ones in our setup. Code is available at https://github.com/CAIROLab-Bern/rad-dit
Composed Image Retrieval (CIR) aims to retrieve a target image given a reference image and a modification text. Although recent approaches leveraging Multimodal Large Language Models (MLLMs) have shown significant progress, we argue that the MLLM's compositional understanding remains underutilized. This stems from directly mapping composed queries into a retrieval embedding via contrastive supervision alone, without explicitly resolving the intended visual modifications. In this work, we introduce Factorized MLLM Embeddings (FactEmbed), which decouples compositional query comprehension from building discriminative embeddings. Rather than directly projecting the composed query into a single embedding without internal reasoning, FactEmbed employs a set of factorized latents that simulate the intended visual modifications via an intermediate target imagination objective. This process encourages the latents to ground into target semantics before forming discriminative representations for retrieval. Subsequently, to propagate these factorized representations throughout the model for retrieval, we optimize a factor-level contrastive loss while distilling the decomposed representations into a deeper attention layer of the MLLM. Finally, for efficient inference, we retain the [EOS] token to establish a global-level embedding on top of these factorized latents, while we exploit the mean-pooled factorized latents to rerank a short candidate list at negligible cost, as both are produced by the same forward pass. Extensive evaluations demonstrate that FactEmbed outperforms prior works across CIR benchmarks.
Accurate vegetation-encroachment assessment and risk mitigation require electric utilities to accurately locate and characterize distribution-network assets, including poles and power lines, and distinguish among medium-voltage, low-voltage, neutral, and telecommunication lines. Mobile and aerial Light Detection and Ranging (LiDAR) point clouds provide detailed 3D representations of these assets and their surroundings. However, power-line detection and reconstruction remain challenging because conductor returns are often sparse, incomplete, noisy, or occluded by vegetation. These challenges are especially significant in distribution networks, where lower pole heights and complex line configurations place conductors close to trees. In addition, mobile and aerial LiDAR datasets differ substantially in point density, viewing geometry, spatial coverage, and occlusion patterns. We propose a robust and automated reconstruction method combining scaled density-based clustering, robust polynomial fitting, and iterative fragment merging to recover individual conductors under severe data incompleteness and occlusion. Following semantic classification, the same reconstruction pipeline processes both mobile and aerial LiDAR data without modality-specific code or parameter tuning. The method is evaluated through degradation experiments, benchmarking, parameter sensitivity analysis, and large-scale validation. On the aerial dataset, it achieves 96.87% precision, 96.66% recall, a 96.76% F$_1$-score, and a geometric RMSE of 0.127 m. On the mobile dataset, where conductor-level reference annotations were unavailable, it achieves a point-to-model RMSE of 0.045 m and a reconstruction coverage of 95.27%. Source code, documentation, and evaluation data are publicly available at https://github.com/varen-project.
Tracking-by-propagation (TBP) methods perform end-to-end multi-object tracking by propagating track queries across frames, jointly handling detection and identity association without heuristic post-processing while naturally modeling temporal information. However, as detection and association are tightly coupled, detection queries in TBP are expected to discover currently untracked objects and provide complementary current-frame evidence for challenging tracks whose queries and identities are retained. Existing methods largely inherit detection-query formation from single-frame detection and construct such queries before the decoder with little awareness of trajectory states. Consequently, currently untracked objects may be missed, while challenging tracked objects with reduced visibility under occlusion may lack complementary evidence, causing association failures or duplicate responses. To address these issues, we propose TAQ-MOTR, a tracking-aware detection query formation framework that employs a pre-decoder Hybrid Query Generator (HQG) to fuse current-frame image features, track memory, and learnable memory. By conditioning detection queries on trajectory states, TAQ-MOTR adapts them to \rev{the discovery of currently untracked objects and tracked-object complementation We further introduce a training-only auxiliary detection branch whose one-to-one label assignment is decoupled from that of the main tracking branch, providing additional detection supervision to strengthen the shared HQG and decoder for the discovery of currently untracked objects. TAQ-MOTR improves performance on DanceTrack, SportsMOT, and BFT, achieving 72.0 HOTA, 63.1 AssA, and 76.6 IDF1 on the DanceTrack test set. Code is available at https://github.com/Magicmiya/TAQ-MOTR
\textit{Objective:} Ultrasound videos are limited by hardware-constrained spatial resolution and signal-dependent speckle, while paired low- and high-resolution acquisitions for supervised restoration are rarely available. We aim to jointly super-resolve and despeckle ultrasound videos without paired training data or network retraining. \textit{Methods:} We propose UltraDiff, which uses a frozen pre-trained diffusion model (DM) as a plug-in prior and restores each frame by optimizing the latent seed of the DM sampler under a range-constrained maximum a posteriori formulation. We derive a speckle-aware data-fidelity term from a Rayleigh scale-family model and characterize its relative-residual and variance-adaptive weighting properties. We further introduce a stabilized fidelity that is bounded below and strictly convex in log intensity for positive observations in its unclamped form. A total-variation regularizer complements the DM prior, and a temporal seed update warm-starts each frame from the optimized seed of its predecessor. \textit{Results:} On EchoNet-LVH videos with simulated speckle and additive noise, UltraDiff with a natural-image prior improves PSNR by 1.24\,dB over the strongest baseline, and ultrasound-related priors improve it further. On real clinical echocardiography videos, UltraDiff reduces the mean absolute error of zero-shot ejection fraction (EF) prediction from 7.31 to 6.37 EF points relative to DUP, the strongest baseline. \textit{Conclusion:} Combining a speckle-aware fidelity with frozen diffusion priors enables ground-truth-free ultrasound video restoration that benefits downstream measurement. \textit{Significance:} UltraDiff needs neither paired data nor retraining and is not tied to a specific diffusion checkpoint. Code associated with this work will be made publicly available upon acceptance.
We introduce PLANTEUR, a benchmark for crop-type mapping from satellite images in the French overseas territories. Building on the PASTIS design, PLANTEUR provides georeferenced and aligned Sentinel-2, Sentinel-1, and Landsat-8 sequences with parcel-derived labels spanning six tropical regions and an 8-class label space. We define both a standard test split and a leave-one-island-out protocol to measure cross-territory generalization, and evaluate fully supervised models, linear probes, and fine-tuned foundation models. The benchmark code and data are open source and available on GitHub and Hugging Face.
Deep models for radiological diagnosis are typically trained to predict disease labels directly from images, which limits them to diseases seen during training and makes their decisions hard to interpret in radiologists' terms. Radiology, however, proceeds from visual findings to disease through published guidelines that make this decision rule explicit, interpretable, and reproducible. We introduce diagnosis by composition (DbC), a representation learning framework that encodes this findings-first logic. DbC learns a vocabulary of radiological findings by aligning image features with the text embeddings of the findings, each finding represented as a dense map over the scan. A disease is defined by a set of required findings derived from its guidelines, and its diagnosis map is a fixed, parameter-free composition of the corresponding finding maps. Because the finding-to-disease mapping is derived from guidelines rather than learned, DbC is interpretable and auditable by design, can extend to new diseases by specifying their findings without retraining, and can diagnose unseen diseases by composing their findings. On multi-phase liver CT, DbC detects and localizes unseen diseases, rare diseases from a different institution, and an external cohort significantly better than all comparators, including models that align images with disease names. DbC also improves detection and localization in the fully supervised setting and remains superior across training-set sizes. Although demonstrated on liver CT, DbC applies wherever radiological guidelines define diseases through findings.
Artificial general intelligence (AGI) requires a method that can understand, generate, reason, and act across diverse domains and modalities. Rather than relying on a single model to master every capability, a promising path toward AGI now is to orchestrate a heterogeneous ecosystem of specialized models, tools, and policies (candidates) into a unified AI system. At the heart of this vision lies a fundamental question: how can an AI system dynamically select and coordinate the most capable candidate for each task while balancing performance and computational cost? In this work, we present Route Anything, a unified framework for studying model and policy routing across general-purpose AI systems. We develop a unified theoretical foundation that characterizes optimal routing under quality--cost trade-offs and establishes how the information available to a router determines its attainable performance. To systematically investigate routing across diverse capabilities, we first construct an omni-modal trajectory matrix spanning 25 benchmarks across language understanding, image, video, and speech generation, coding and workplace agents, and robotic manipulation, comprising 374,401 scored runs from 452 candidate configurations. Building on this framework, we train and test different routers to investigate the potential of omni-modal model routing, the capabilities of learned routers, and the conditions under which routing improves efficiency. Our results reveal substantial opportunities for capability orchestration: per-input oracle routing outperforms the best fixed candidate by 5.4 points, and learned routers outperform it by 0.3 points across 16 benchmarks, by 2.1 points on video generation, and by 1.1 points on robot manipulation while using 24% less policy time. More importantly, routing raises efficiency by 8.82x on average compared with the reference model.
We aim to build a truly unified motion model that can understand, generate, and edit human motion within a single framework. Existing motion UMMs remain only partially unified: motion understanding is handled by a language model, while generation is often delegated to a separate diffusion module operating over learned motion latents. We introduce M\"obius, which brings the entire diffusion process into the same multimodal representation space used for motion understanding. Clean motion, noisy motion, and text jointly participate in shared attention, while role-specific parameters process understanding and generation streams. Importantly, M\"obius operates directly on continuous frame-level raw motion, requiring neither discrete tokenization nor a pretrained motion VAE. This simple formulation naturally supports motion captioning, text-to-motion generation, temporal completion, and instruction-guided editing within a single model. On HumanML3D, M\"obius achieves state-of-the-art performance among unified motion models. Scaling to 1.7B parameters and 1,700 hours of motion data further demonstrates that our framework is both effective and scalable.
Unified Multimodal Models (UMMs) integrate visual understanding, generation, and editing within a single unified framework. However, existing unified multimodal datasets and benchmarks remain dominated by single-turn tasks. Even in recent multi-turn datasets, many turns can be solved independently without tracking information across turns. Consequently, they provide limited supervision and evaluation for multimodal stateful interaction, which requires models to understand, maintain, update, and faithfully realize evolving dialogue states across turns. To address this gap, we introduce YANAMI, the first large-scale multimodal dialogue dataset and benchmark for stateful interaction, comprising YANAMI-400K and YANAMI-Bench. YANAMI-400K contains 400K multi-turn multimodal dialogues, with more than 2M images and 2.6M dialogue turns. The dialogues span four representative scenarios: Multi-Image Fusion, Image Editing, World Modeling, and Visual Reasoning, and require models to continuously track, preserve, and revise evolving multimodal dialogue states across turns. YANAMI-Bench comprises 400 multi-turn dialogues for systematically evaluating multimodal stateful interaction. It jointly evaluates Dialogue State Understanding and Visual Realization, characterizing the gap between models' ability to understand evolving dialogue states and their ability to faithfully realize them in visual outputs. Experiments show that fine-tuning BAGEL on YANAMI-400K improves image editing, generation, and multimodal stateful interaction by 10.3%, 2.0%, and 13.23%, respectively, while preserving its general visual understanding capabilities. Evaluations on YANAMI-Bench further reveal that existing UMMs still struggle to maintain, update, and visually realize evolving multimodal dialogue states.
Visual place recognition (VPR) localises a camera by retrieving similar geo-tagged images, and current foundation-model VPR models are accurate across cities, seasons and illumination, but not robust to adversarial perturbations: under a white-box attack on the ranking at an imperceptible budget of 1/255, SuperVLAD and BoQ keep at most 0.2% top-1 recall (R@1) on four benchmarks. We propose anchored rank-adversarial fine-tuning (ARAFT), which fine-tunes a released model with a listwise rank loss on each adversarial query's hardest positive and an anchor to the clean descriptor of the frozen pretrained model. Checkpoints are selected under a clean-accuracy budget fixed in advance, and the full trade-off is reported. Within five validation R@1 points of clean cost, plain adversarial training has no admissible checkpoint, whereas ARAFT raises robust R@1 from zero to 47.3 on SuperVLAD and 55.3 on BoQ; plain adversarial training exceeds this only at about three times the clean cost. Against unbudgeted plain adversarial training on the test sets, ARAFT matches its robust R@1 at 2/255 with about ten more clean R@1 points. At 4/255, plain adversarial training is 6-9 robust R@1 points ahead, while ARAFT still keeps its ten-point clean advantage. Developed on SuperVLAD, ARAFT transfers to BoQ without re-tuning, and its robustness holds against stronger optimisers, with no sign of gradient masking.
3D point cloud classification, a task in computer vision, has recently gained substantial interest due to its extensive applications across various domains such as augmented and virtual reality, robotics, and autonomous driving. However, classifying 3D point clouds becomes challenging in real-world scenarios where the density levels vary. These variations are due to limitations inherent to current sensing technologies and variable environmental conditions, which often prevent the capture of detailed and comprehensive geometric representations. Existing classification methods, which have demonstrated impressive results on dense point clouds, may be affected and could experience reduced performance when dealing with low-density point clouds. Addressing this challenge, this paper introduces LD-PointNet++, an architecture optimized for the classification of low-density point clouds. To pave the way for LD-PointNet++, we conduct the first benchmarking study that systematically evaluates state-of-the-art point cloud classification methods across varying densities, revealing significant performance declines in low-density environments. Experimental results on the ModelNet benchmark dataset demonstrate that LD-PointNet++ not only outperforms these methods in low-density scenarios but also demonstrates consistent accuracy above 90% across different density levels.
A real photograph is often blurry, grainy, compressed, scratched, and low-resolution at the same time. Each defect has its own severity and its own place in the image. The corrections for these defects conflict with each other. Exist- ing models describe the whole image with one description, so they cannot say where each correction belongs. To solve this problem, we present Wonder 4, a mixture-of-experts (MoE) model for image quality enhancement. It corrects several defects of a real photograph at the same time, each in the region where it occurs. Every block of the model holds a mixture of N = 13 experts. A router, trained with the model, sends every image patch to k = 5 of them. No degradation classifier, mask, prompt, detector, or task label is used. Another issue is that standard MoE training, taken from language models, pushes every expert toward equal use. Equal use applies every correction everywhere, even where it is not needed. We replace this rule with a bias that only sets a minimum share of use. Across all patches, an expert used less than this minimum gets higher router scores until it is selected again. An expert above the minimum is not changed, so no expert is forced to be used as often as the others. The bias needs no extra loss. The method adds no extra module and no extra processing step. We evaluate Wonder 4 on DIV2K and Flickr2K, against five published methods and three open-weight pipelines. It reaches the best LPIPS, DISTS, and NIQE on all three test settings (DIV2K x4, DIV2K x8, and Flickr2K x4).
Automatic tools can now generate whole-brain MRI parcellations at cohort scale, but generated-label releases often provide little evidence about which cases are reliable enough to reuse. We introduce OpenBrain, a confidence-aware release of 35,838 provenance-verified OpenNeuro T1w cases from 607 source datasets. OpenBrain is organized as an auditable case-record release rather than a directory of standalone segmentation files: each record links a primary parcellation, two committee parcellations, source/license provenance, raw QC-7 measurements, percentile risks, a combined risk score R, and a confidence tier. QC-7 is a reference-free reliability panel over label geometry, image-label consistency, and committee disagreement, so users can filter, weight, audit, or re-threshold generated labels without rerunning inference. We evaluate this released evidence under a frozen protocol. Across external cohorts, lower QC-7 risk corresponds to higher generated-label quality; in fixed-budget training, lower-risk selections improve paired macro Dice over random selection by +3.2 to +3.7 percentage points. OpenBrain also exposes raw axes, committee outputs, provenance, and datasheet documentation, so confidence claims remain inspectable after download. It does not turn generated labels into manual annotations or clinical-grade segmentations. Its contribution is a large open generated-parcellation substrate, a reusable case-level risk-evidence layer, and an external validation protocol for release-time QC. Dataset: https://huggingface.co/datasets/lanqz7766/OpenBrain. Code: https://github.com/lanqz7766/openbrain.
This paper presents GSCV++, a lightweight pipeline for 3D {G}aussian {S}platting (GS) sequences {C}ompression with standard {V}ideo codecs. To meet the requirements of low-complexity and hardware compatibility from the industry, GSCV++ jointly improves preprocessing, 3D-to-2D mapping, and practical video compression configuration of GS compression. First, for preprocessing, energy-adaptive inter-frame spherical harmonic (SH) alternative current (AC) dimensionality reduction (EA-SHDR) is proposed to produces a compact and stable temporal SH AC feature space. It can reduce the data volume of following mapping and practical compression, as well as less complexity while eliminating redundant information. Second, for 3D-to-2D mapping, prior-based Inter-MiniPLAS (P-MiniPLAS) is designed to generate smooth 2D feature maps through prior-based weighting factor inference and small scale remapping. Compared with vanilla Parallel Linear Assignment Sorting (PLAS) and Morton scan, P-MiniPLAS ensures the generated 2D maps are more suitable for the video codec while maintaining a low level of computational complexity. Third, for practical compression, content-aware generalized compression (CA-GC) is developed to use a non-uniform bit-depth split for coordinate map generation, and a coding unit size selection is introduced for efficient compression complexity control, which fully exploits the performance of video codecs without involving normative changes. Experiments demonstrate that GSCV++ reports over 20\% in intra- and 60\% in inter-prediction rate-distortion gains compared with state-of-the-art (SOTA) methods. GSCV++ also achieves faster 2D map generation, encoding, and decoding than other SOTA methods using the same type of video codecs. Ablation studies verify the effectiveness and robustness of the proposed modules and provide insights for subsequent research.
Reliable evaluation of visual 3D reconstruction and depth estimation in vegetation-rich outdoor environments is limited by the scarcity of geometric ground-truth data and the cost of complete scanner surveys. We present a LiDARbased reference-generation pipeline for evaluating the zero-shot performance of feed-forward visual-geometry models alongside conventional structure-from-motion (SfM) methods. The pipeline reuses camera images, LiDAR scans, and reference poses from existing multi-sensor localization datasets to generate per-view depth maps and visible reference point clouds. To address visibility errors in accumulated LiDAR scans, we introduce the LargeDepth-Gap Visibility Score (LDGVS) for point-wise visibility filtering and automatic scale selection in Hidden Point Removal(HPR). Experiments on TartanAirV2 and TartanGround show that, compared with Poisson surface reconstruction, which is an approach suited to completed scan surveys, the combined HPR and LDGVS filtering retains approximately three times the point density at comparable absolute relative error. We also apply the pipeline to the BotanicGarden dataset to systematically compare depth estimation and 3D reconstruction methods. Feedforward methods produce dense depth predictions efficiently, but their 3D reconstructions can contain duplicated structures. Conventional SfM generally produces more coherent geometry, but its reconstructions remain sparse and more prone to failure in challenging vegetated scenes. The benchmark toolkit and datasets will be released.
Learning a universal action representation from video requires modeling dynamics that are consistent across different executions of the same action yet invariant to changes in embodiment and appearance. Existing latent action models infer actions from visual transitions, but their representations often entangle the underlying action with irrelevant visual variations, limiting transfer across embodiments. We introduce DreamX, which repurposes a pretrained video diffusion model as a universal latent action learner. Our approach extracts compact latent actions from the video model's rich spatiotemporal features, compressing each latent video frame by $\boldsymbol{300\times}$ ($\boldsymbol{1{,}200 \rightarrow 4}$ tokens). In addition, by leveraging the video model's generative prior, these latent actions capture action-relevant dynamics disentangled from visual appearance. The resulting latent space serves as a shared action interface across embodiments (human and robot), environments, and action parameterizations. On LARY-Bench, DreamX achieves state-of-the-art performance among latent action models. Moreover, actions encoded in one setting remain effective in another: the latent space supports any-to-any video transfer and zero-shot action transfer across diverse embodiments and environments. Furthermore, this shared interface also enables policy learning in a compact latent action space, reducing the computational cost of video-diffusion-based policies.
Visual agents need to coordinate reasoning and action while their environment evolves during inference. We introduce LOLPlay, a benchmark in native \emph{League of Legends} with 36 champion-specific tasks spanning resource management, combat, cooperation, and objectives. Agents interact through screenshots and mouse--keyboard actions; automated initialization and 82 executable subgoal checks distinguish partial progress from completion. Across 324 task evaluations of three models at three reasoning-effort settings, GPT-6 Astra achieves the highest task success rate of 25.0\% at low and medium effort, and the highest subgoal success rate of 40.3\% at medium effort. However, high effort improves neither metric over low effort for any model. For Astra, longer requests leave fewer interaction rounds, suggesting a cost to additional reasoning in real-time control. Trajectories reveal incomplete subgoal composition and actions executing after the observed scene changes, motivating agents that combine visual reasoning with timely action.
Embodied agents are increasingly deployed in open-world environments, yet current robustness evaluations remain biased toward hazardous instructions and jailbreak vulnerabilities. A more fundamental issue is largely overlooked: agents are rarely tested under semantically sufficient but contextually minimal instructions (i.e., common in real-world human communication), where auxiliary contextual cues are absent. For the first, we identify a novel phenomenon termed Ambient Context Illusion, where agents fail to execute tasks correctly when non-essential contextual details are omitted, despite unchanged task semantics. To systematically study this, we establish VagueBench, a benchmark built upon the AI2-THOR interactive simulation environment for the evaluation of context dependency in embodied agents. We systematically consider key semantic components of instructions (entities, procedures, constraints, and prior knowledge) and derive a unified taxonomy with four categories and nine subtypes to reduce auxiliary information. VagueBench contains 1,303 instruction pairs across diverse indoor environments, constructed via a human-agent co-generation framework that integrates semantic redundancy estimation, taxonomy-guided transformation, and rigorous semantic-invariance verification. Through extensive evaluation on 6 state-of-the-art embodied agents, we observe significant degradation on VagueBench in both task performance and executability (relatively -19.65% in task success rate and relatively +54.10% in empty plan rate) revealing a strong reliance on auxiliary linguistic signals rather than core task semantics. Furthermore, we demonstrate that this phenomenon persists in real-world robotic systems, where it can lead to incorrect decisions and potential safety risks.
Feature matching underpins many robotic perception tasks, including visual localization, mapping, SLAM, and autonomous navigation. Existing semi-dense matchers predict confidence on fixed grids, limiting correspondences to predefined locations and requiring costly high-resolution grids for precise localization. We present CoReMatch (Coordinate Refinement Match), a recurrent framework that refines correspondences directly in continuous coordinate space rather than predicting discrete confidence maps. CoReMatch progressively improves correspondence estimates by propagating information across iterations. At the coarse stage, a Deep Aggregated Transformer captures global context and iteratively updates correspondence coordinates, while a lightweight regression head further sharpens their localization. Experiments on indoor and outdoor benchmarks show that CoReMatch strikes a strong balance between accuracy and efficiency, outperforming Efficient LoFTR in accuracy while running more than 10x faster on embedded edge hardware. These results demonstrate that recurrent coordinate refinement offers an efficient and scalable approach to real-time feature matching for robotic perception.
Diabetic macular edema (DME) is a leading cause of severe vision loss among working-age adults. Although intravitreal anti-vascular endothelial growth factor (anti-VEGF) injections currently serve as the first-line therapy for DME, a notable subset of patients fails to respond despite the substantial cost and clinical burden, suggesting they may benefit more from alternative interventions. Automated, noninvasive pre-treatment response assessment could therefore spare non-responders from the current trial-and-error treatment paradigm. In this study, we propose a novel conditional adversarial diffusion framework that synthesizes post-treatment optical coherence tomography (OCT) images from baseline scans, enabling the derivation of each patient's initial response to anti-VEGF therapy. The model was developed with subject-level 5-fold cross-validation on a US cohort (n = 127) and externally validated on an independent Iranian cohort (n = 44). Benchmarked against fourteen baseline and state-of-the-art translation models, the proposed model achieved the best treatment-response prediction performance among the methods evaluated for that task on both cohorts, with balanced accuracies of 85.7% and 93.0% on the US cohort and 85.2% and 95.3% on the external Iranian cohort at the 10% and 20% central subfield thickness reduction thresholds, respectively. Ultimately, this framework offers a decision-support tool to help ophthalmologists anticipate initial anti-VEGF outcomes in DME prior to treatment initiation, toward personalized therapy selection. The source code will be made publicly available upon acceptance.
Longitudinal rodent positron emission tomography (PET) studies of stroke and neuromodulation rely on accurate registration to a common atlas space to detect group-level effects. Prior work applying ultra-high frequency low-intensity magnetic stimulation (UHF-LiMS) to a rat model of chronic capsule infarct used affine normalization to a Sprague Dawley MRI template without evaluating that choice. We compare a two-stage (affine and nonlinear) pipeline against an affine- only one for rat PET-to-atlas alignment on the same dataset. Across 32 longitudinal [18F]-FDG PET scans (8 rats, 4 timepoints), the nonlinear stage gave a higher Dice similarity coefficient on every scan, and the gain was significant at the rat level. Jacobian determinants showed no folding on the sampling grid. Group-level linear mixed-effects maps of change from baseline (AFNI 3dLME), computed identically under both pipelines, differ in the size, number and location of their suprathreshold clusters. In this dataset, the registration pipeline is therefore a variable that can change the interpretation of downstream group-level analyses.
State-of-the-art bronchoscopy guidance systems and computer-aided diagnosis methods have emerged as important tools for early lung cancer detection. Effective use of these tools depends on being able to accurately link a patient's bronchoscopic airway exam video to their pre-operative 3D chest CT scan. Unfortunately, the derivation of such links, which include bronchoscope depth and camera motion, from the exam video remains an open problem. Building on recently proposed 3D-vision foundation models, we propose DUNEDepth, a hybrid architecture that combines a shared DUNE ViT encoder, a twin MASt3R cross-attention decoder structure, and a prediction head that includes elements of the MASt3R and Reloc3r models. To fine-tune the architecture to our application, we utilize an integrated hybrid synthetic-supervised/self-supervised training strategy that draws on both bronchoscopic video and CT-derived virtual bronchoscopic views. Experiments drawing on bronchoscopic video sequences demonstrate that DUNEDepth more accurately derives depth information and camera motion trajectories than previously proposed self-supervised methods.
The corotation radius R_CR of a spiral galaxy marks the radius where the angular speed of the spiral pattern matches the orbital speed of the disk material. Despite its importance for understanding spiral structure and galaxy evolution, very few galaxies have corotation measurements, often derived using heterogeneous techniques. We present an automated photometric pipeline that identifies corotation radii by tracking the azimuthal phase offset between young and old stellar populations. Building on the color-gradient framework of \citet{Puerari1997}, we extract azimuthal brightness profiles from deprojected dual-band images, fit periodic models to the profiles, and identify corotation candidates at radii where the phase difference between the two stellar tracers changes sign. Each candidate is assigned an adaptive uncertainty interval and reported with a goodness-of-fit metric. We benchmark the method against a cross-method literature compilation, scoring every technique -- including our own -- against a reference built from the published measurements alone and evaluated leave-one-out. Over the $90$ galaxies for which such a reference exists, the pipeline places a correct corotation radius in $80.0\%$ of them, recovers $63.6\%$ of their known corotation radii, and reaches a harmonic mean of recall and purity of $0.58$, the highest values of any method in the comparison. Unlike the published methods, each of which was applied to a small, curated set of galaxies, our pipeline is run on the entire reference sample without any pre-selection, a sample two to six times larger than existing methods. The pipeline is scalable to large surveys, flexible with respect to spiral mode, and naturally recovers multiple corotation radii in galaxies with complex spiral structure, providing a uniform framework for studying disk resonances across diverse galaxy populations.
Large-scale astronomical surveys define a heterogeneous, partially observed multi-survey learning setting: each object is observed by only a subset of surveys, while survey observations differ in resolutions, wavelength coverage, noise characteristics, and footprints. This setting gives rise to a natural machine learning problem: given observations of an object in some surveys, how to infer its appearance in other surveys. We formalize this as the problem of cross-survey modality imputation and introduce COSMIO, a multi-survey benchmark of aligned observations obtained by forward-rendered shared astrophysical scenes across LSST, Euclid, and Roman under survey-specific instrument characteristics. The benchmark enables systematic evaluation of imputation across source-target survey combinations and missing-survey patterns. We evaluate a broad range of machine learning methods for imputation, which reveal a clear domain gap: methods developed for existing imputation settings transfer poorly to the survey setting. We identify rare-event imputation as a central challenge. This regime arises in the early stages of new surveys, when rare but scientifically valuable phenomena may be available only from prior surveys. We use strong gravitational lensing, where light from a background galaxy is gravitationally deflected by a foreground galaxy, as a representative rare-event setting. We evaluate model performance on zero-shot imputation of gravitational lenses and on downstream scientific tasks using the imputed lens observations. On our constructed evaluation set of galaxy-galaxy strong lenses, performance degrades under rare-event distribution shift, and this degradation further propagates to the downstream lens-detection task. Code: https://github.com/fw-ic/COSMIO.
Reasoning vision-language-action (VLA) models pair physical control with natural-language rationales that supervisors can read to monitor embodied safety. Prior attacks on VLA reasoning corrupt the rationale itself and leave visible evidence in the text. We show that visual perturbations can instead alter the physical action while keeping the generated rationale word-for-word identical. At the shared text/action interface of Alpamayo for driving and InstructVLA for manipulation, our text-neutral action-subspace (TNAS) diagnostic shows that the locally most action-sensitive direction is nearly orthogonal to the active text-loss gradients, with 1.87% and 5.28% norm overlap. At equal hidden-state perturbation norms across both models, interventions along this text-neutral residual shift actions 4.64x to 47.8x more than text-gradient perturbations, whereas text-gradient perturbations induce 21.2x to 277x more text drift. Steering visual perturbations along this direction reaches the same decoupling from the image. Across 154 obstacle-annotated driving scenes in Alpamayo, TNAS-guided attacks induce a new collision under a word-for-word identical rationale in 52.6% of scenes under full-image perturbations and 35.1% under a localized forward-camera patch, compared with 4.55% for unguided action attacks. Relative to a text-preserving baseline, TNAS guidance raises exact rationale preservation from 83.0% to 89.5% and cuts teacher-forced text drift by 68.4% at a comparable collision rate. In InstructVLA, TNAS guidance cuts text drift by 40.5% and preserves the exact response on 85.0% of examples alongside a 1.73-unit action-chunk shift. An unchanged rationale therefore cannot certify a safe action, so monitors for reasoning VLAs must verify the predicted action channel directly.
Adapting a generalist vision-language-action (VLA) policy to a target task with limited demonstrations can improve nominal task success while reducing robustness to variations in appearance, objects, and instructions. We introduce reasoning-aligned fine-tuning (RAFT), a two-stage post-training procedure: RAFT first trains low-rank adapters on task-relevant reasoning annotations, then freezes them while fine-tuning the policy on action demonstrations. On a physical DROID robot, RAFT achieves $75.0\%$ out-of-distribution success, compared with $27.9\%$ for plain fine-tuning; on a multi-stage bimanual YAM task, it reaches $70.0\%$ mean success, compared with $36.0\%$ for the strongest baseline. RAFT also improves success under visual, object, and instruction shifts in simulated pick-and-place and open-drawer tasks. Compared with plain fine-tuning, RAFT policies place more attention on annotated task regions and yield higher linear-probe accuracy for object identity in later layers. A broader reasoning-data mixture further improves downstream success across demonstration budgets.
We introduce the Pauli-Correlator Autoencoder (PCAE), a hybrid quantum--classical architecture for image reconstruction. PCAE splits an image into patches and compresses each patch as a matrix product state (MPS). A small quantum circuit turns each compressed patch into a few measured numbers, and a classical neural network rebuilds the patch from these numbers and the patch position. A learnable energy term, taken from physics, is added to training and tracked as training proceeds. Two versions place the six qubits on a line (PCAE1D) or on a grid (PCAE2D). An averaging step makes the PCAE2D features follow rotations and reflections of the image exactly. Trained on one image at a time, PCAE2D rebuilds images from six public datasets with a peak signal-to-noise ratio of 25.8 to 41.6 decibels. On CIFAR-10 images not used in training, a formula-based stand-in for the PCAE2D features performs within 1 decibel of several simpler classical methods. Five trained models also run on real IBM quantum computers without retraining, and rebuild images at 25.90 to 31.52 decibels. A short argument and a synthetic test show that, with a linear final layer, measuring qubits in pairs is needed for targets built from products of inputs. These results show that PCAE works as a hybrid model that rebuilds varied images and runs on today's quantum hardware at the six-qubit scale.
Predicting how the world evolves in response to robot actions is central to policy learning, evaluation, and planning. However, many action-conditioned world models predict future observations in 2D image or video space without explicitly modeling the underlying 3D scene, making spatial consistency across viewpoints and over long-horizon interactions challenging. We introduce 3D World Simulator, an action-conditioned multimodal world modeling framework that jointly predicts appearance, geometry, and tactile observations from a unified 3D representation. Our approach combines a hybrid particle-voxel autoencoder that compresses point clouds into compact 3D voxel latents with an action-conditioned latent dynamics model that predicts their evolution. The shared 3D representation supports geometrically consistent rendering from arbitrary viewpoints and flexible integration of spatially aligned tactile signals. Our experiments demonstrate interactive, long-horizon, multimodal prediction at 50 Hz. We then show how our model enables scalable data generation for policy training and evaluation using tactile and multi-view visual observations, including wrist-mounted and novel camera views. Furthermore, we scale our method to large datasets containing diverse objects and demonstrate model-based planning with unseen objects and robot configurations. Together, these results highlight the potential of hybrid particle-voxel dynamics as a foundation for multimodal 3D world simulation.
Reconstructing three-dimensional (3D) coronary anatomy from sparse angiographic views could support percutaneous coronary intervention, but limited angular coverage and imperfect vessel segmentations introduce substantial geometric ambiguity. We propose a vessel-specific reconstruction framework combining a learned 3D diffusion prior, visual-hull initialization, and projection-based data consistency. The unconditional diffusion model is trained on coronary vessel masks without paired 2D--3D data and reused across different view counts without retraining. During inference, a scaled visual hull initializes reconstruction, while projection-based updates constrain diffusion refinement using patient-specific vessel observations. We evaluated the framework on simulated angiograms derived from ImageCAS computed tomography angiography volumes using two, four, and eight views at two contrast levels. Across 50 evaluation coronary-tree cases, the proposed method achieved higher mean Dice and clDice than visual hull, deep image prior (DIP), and hash-grid implicit neural representation (INR) at all view counts under reduced contrast. With eight views, improvements over DIP, the best-performing baseline at lower contrast, were approximately 0.13 in Dice and 0.22 in clDice. At higher contrast, performance remained competitive with hash-grid INR, the best-performing eight-view baseline. The preferred diffusion starting timestep depended on observation quality and view count, with excessive refinement reducing accuracy at higher contrast. Projection guidance improved both metrics across all conditions. Averaging stochastic reconstructions further improved accuracy, while sample disagreement localized errors with average-precision gains of 0.14--0.21 over error prevalence. These findings support diffusion-prior reconstruction from sparse vessel observations, although clinical validation remains necessary.
In single-pixel (ghost) imaging, known illumination patterns probe an object and a detector with no spatial resolution returns one number per pattern. Each measurement costs acquisition time and photons and, for ionizing probes, contributes to delivered dose. Motivated by automated radiographic defect screening, where a class label suffices, we introduce Learning Illumination Patterns for Single-Pixel Classification (LIPS-PC). The patterns are learned end-to-end while the measurement operator remains one fixed linear matrix, identical for every input. We parameterize it as a residual correction to a two-dimensional discrete cosine transform (2D-DCT), $D=D_{\mathrm{base}}+\Delta$, and jointly train the correction and a compact classifier using cross-entropy, without a reconstruction objective. This yields a task-driven linear embedding through optimization. We evaluate LIPS-PC numerically on MNIST and Fashion-MNIST under a controlled protocol, then on RIAWELC, a real industrial X-ray weld-radiograph dataset. Across five budgets, $M\in{8,16,32,64,128}$, corresponding to sampling ratios from below 1% to 12.5%, the learned operator outperforms the best tested fixed transform by 9-15 percentage points at $M=8$ on all three datasets. Its eight-measurement accuracy requires roughly 16-32 measurements with the best fixed transform, indicating a $2\times$ to $4\times$ saving at comparable accuracy. The advantage generally shrinks as $M$ increases, with a small reversal on RIAWELC at higher budgets. These results show that learning what to measure is especially valuable when measurements are scarce.
Video world models enable candidate actions to be evaluated through imagined outcomes, but high predicted rewards can favor trajectories with poor execution quality. We introduce Trusting Imagined Futures (TIF), an offline supervision selection method for vision-language-action (VLA) post-training that audits predicted rewards using execution feedback. A multidimensional reward model predicts a utility score for candidate ranking and five dimensions of execution quality. An auditor uses reward predictions and uncertainty to identify overestimation patterns learned from paired imagined videos and real executions. TIF accepts the candidate with the highest predicted utility when its advantage over the existing trajectory exceeds a margin and its audit risk passes a threshold; otherwise, it retains the existing supervision. The retained real trajectories then supervise behavior cloning. Across four LIBERO suites and three training seeds, TIF achieves a mean success rate of 76.25%, improving over training on the existing trajectories by 3.00 percentage points with the same trajectory count and training budget. Adding audit gating yields 1.47 percentage points with the reward model and advantage margin held fixed. The gains persist against advantage ranking and logistic regression risk selection at matched replacement counts. On recorded videos from three real robot tasks, TIF increases clean completion among selected trajectories from 58.33% to 70.00% across 60 candidate pools.
Deep learning in medical imaging is constrained by data scarcity and by privacy regulations that make centralizing patient data across institutions impractical. Federated Learning (FL) addresses these constraints by keeping data local, but its distributed nature exposes training to strong statistical heterogeneity. Multicentric medical data is particularly affected, exhibiting a mixed skew that combines feature, label, concept, and quantity shifts across centers. Personalized FL mitigates heterogeneity by tailoring a model to each client, yet most methods assume training from scratch, which is unrealistic given the high dimensionality of medical features relative to the limited data available. We propose the Personalized Aligner Federated Pretrained (PAFP) framework, a personalized FL approach built on a pre-trained backbone. PAFP inserts client-specific Feature Alignment modules before the fine-tuned blocks to realign hidden feature distributions toward a server-aggregated target. On the FedISIC benchmark, PAFP attains the highest unweighted balanced accuracy while reducing inter-client performance variance roughly six-fold relative to the strongest baseline, yielding accuracy and cross-client equity jointly. Our code is publicly available at https://github.com/Alexandre-Leclercq/PAFP.
Recent multimodal language models can reason directly about robot scenes, but it is unclear whether they need to repeatedly reinterpret raw visual observations at every step of an interaction. We propose shifting routine spatial reasoning from images to text and symbols through a 3D geometric abstraction that is refreshed locally from observations and read directly by the language models. Specifically, our interface represents scene geometry via typed, evidence-aware symbolic references to object parts, grounds them from calibrated RGB-D, and returns compact textual checkpoints with metric residuals after each action. Symbolic task structure can thus be reused across decisions while metric values are rebound to the current scene, with direct visual reasoning invoked only on demand. Across offline policy synthesis and continuous online execution, reasoning over grounded text and symbols improves multi-step manipulation completion while substantially reducing repeated multimodal queries, positioning explicit geometric state as an effective substrate for agentic robot policies.
Although existing candidate trajectory evaluators have substantially improved end-to-end planning accuracy, their underlying mechanism remains suboptimal. Model-based evaluators typically make scoring future-aware by explicitly predicting candidate-conditioned future states over the planning horizon, which we term rollout. However, rollout incurs high inference cost and accumulates prediction errors. We argue that planning does not require reconstructing a full future scene for each candidate, but only future-relevant information for reliable comparison. We therefore propose RFWorld, a Rollout-Free World model for end-to-end trajectory evaluation. RFWorld constructs a shared scene memory and shapes it into a future-readable representation via lightweight training-time temporal readout with semantic supervision, keeping training overhead low. At inference time, candidate trajectories directly query the shared memory via sparse spatial readout for scoring, reducing computation by roughly the planning horizon times the number of candidate trajectories, while avoiding recursive rollout errors. Experiments on NAVSIM and Bench2Drive show that RFWorld learns a more planning-aligned world representation and achieves state-of-the-art performance.
Accurate segmentation of the mitral valve from three-dimensional transesophageal echocardiography (3D TEE) is severely restricted by the scarcity of publicly available expert- annotated volumetric datasets. To address this critical limitation, we investigated Fourier Domain Adaptation (FDA), utilizing general-purpose generative-AI images (from platforms like Chat- GPT, Google Gemini, and Microsoft MAI) as annotation-free style donors for 3D mitral valve segmentation. We employed a DeepMitral residual U-Net model on the public MVSeg2023 dataset, comparing six conditions over three runs: real-only training, traditional augmentation, FDA with each generative source, and a non-AI FDA control using real-image style donors, plus an optimization-matched real-only control and a \b{eta} sensitivity analysis. Case-level paired testing showed that FDA with these generative sources led to significant reductions in boundary- and surface-related errors across all three donor conditions relative to the primary real-only baseline. However, the impact on the core segmentation metric, Generalized Dice Score (GDS), proved generator-dependent. ChatGPT-FDA showed a significant GDS advantage over the optimization-matched control but not over the primary baseline, and Gemini-FDA showed no significant GDS difference. Notably, only MAI-FDA provided a statistically robust and significant increase in GDS compared to the primary baseline. The \b{eta} sensitivity was not robust across training runs. These findings confirm that FDA remains an important augmentation mechanism. While generative-AI images offer a practical means of acquiring style diversity without new annotations, the non-AI control performed comparably to ChatGPT-FDA, so we do not conclude that this approach is superior to training with real-image donors.