Authors: Arina Oberoi
Abstract: Starting from the axiomatic formulation of scale-space theory, we develop a viscosity-solution framework for multiscale image representations arising from degenerate elliptic-parabolic partial differential equations. Rather than introducing a new semigroup theory, we work within the standard viscosity-solution setting, using comparison principles to obtain well-posedness, uniqueness, and contraction in the supremum norm. This perspective is used to motivate a hybrid reconstruction operator in which a learned inverse map is followed by a nonlinear diffusion evolution. At the continuous level, the diffusion operator satisfies non-expansiveness, which provides stability for the reconstruction process; this framework is then evaluated on a CT-based mesothelioma classification task, where it attains an AUC of 0.875 with negligible variation across epochs, while the baseline model acquires AUC values from 0.49 to 0.80 without a clear convergence pattern. These observations are consistent with the stabilizing role suggested by the discussed viscosity theory.
Authors: Esteban Pesnel (COMPACT), Julien Le Tanou (COMPACT), Michael Ropert (COMPACT), Aline Roumy (COMPACT), Thomas Maugey (COMPACT)
Abstract: Neural wrappers are learned pre-and postprocessing networks designed to enhance the performance of conventional video codecs. Although these approaches can significantly improve compression efficiency, training them remains challenging due to the non-differentiability of video codecs, which arises from the multiple discrete decisions involved in the encoding process. Surrogate gradients have recently emerged as an effective solution for enabling end-to-end learning with conventional codecs. They offer two main advantages: they avoid training an additional network to mimic the codec, and they can improve compression performance. In particular, the recently proposed SCALED method, which leverages the true compression error, has shown strong results for training neural pre-processors such as downscalers. However, this SCALED gradient was originally introduced as a reparameterization trick, which limits its interpretability. In this paper, we show that this surrogate gradient can be interpreted as a first-order local approximation of the video codec, providing insight into its effectiveness. We further demonstrate that it is effective not only for learning downscaling operations, but also for the more challenging task of full neural wrapping with pre-and post-processing networks. Finally, we show that the approach generalizes well across different video codecs, quality factors, and tasks, including multiple downscaling ratios, yielding BD-Rate (PSNR) reductions of up to -23.59% on x264 and -20.07% on VVenC relative to standard resampling baselines.
Authors: Daniel Lee, Harsh Sharma, Eunkyu Park, Pranav Narayanan Venkit, Jeonghwan Kim, Kah Mun Chia, Andreas Vlachos, Shafiq Joty
Abstract: MLLM-as-a-Judge is conventionally validated by agreement with human annotations, but this metric is undefined when the human pool is culturally heterogeneous. We introduce VOIR DIRE, a multimodal benchmark of 626 culturally paired image--prompt artifacts spanning U.S. and mainland Chinese contexts across food, fashion, and architecture, with annotator pools that are within-pool reliable (a = 0.86/0.74) but cross-pool divergent on evaluation (Q1 r = -0.12). Across six MLLMs, the bias decomposes into two failures: a positivity-floor calibration failure (compressed scale use) and an orientation failure (default to one cultural norm). On this corpus, where contested items are sampled to split the two pools, the floor mechanically validates the more-permissive Chinese reading; persona prompting partially recovers calibration, but the orientation residual survives, evidence the tilt is not reducible to scale compression. Reference-pool in-context demonstrations deepen the orientation residual and inflate the high end rather than restoring use of the low end. Model origin adds a small additive tilt (~0.10 MAE) that is approximately invariant under demonstration. We recommend reporting alignment against each reference pool separately and treating cross-pool divergence as a judge property.
Authors: Ajan Ahmed, Masudul H. Imtiaz
Abstract: A biometric verifier is often deployed with a strict false match budget, so only a narrow, low false match rate (FMR) slice of the score range is used. A reporting standard for this setting already exists. ISO/IEC 19795-1 asks for error rates at stated operating points, for the detection error tradeoff (DET) curve as the view of the trade-off between FMR and the false non-match rate (FNMR), and for an interval of uncertainty on every value. In practice, a single area under the receiver operating characteristic curve (ROC-AUC), the equal error rate (EER), or a verification accuracy is still reported as the resolution, which is a threshold-independent summary that the standard does not endorse. The full ROC-AUC averages the true match rate (TMR) with equal weight over the whole FMR range from 0 to 1, so almost all of its weight is placed where the system is never operated; low-FMR behavior can then be hidden, and the order of two systems can even be reversed. The guideline is revisited in this paper and tested against seven pretrained matchers across four modalities, face, voice, iris, and fingerprint, each reported with bootstrap confidence intervals and paired bootstrap tests. A system that looks stronger on full ROC-AUC is shown to be significantly worse at FMR = 10^-3. For face, a higher full AUC was obtained by FaceNet, whereas a higher TMR at FMR = 10^-3 was obtained by ArcFace, and both gaps were significant with non-overlapping intervals. Hence, the DET curve and the FNMR at a fixed FMR are re-iterated in this paper as the primary report, with ROC-AUC and EER retained as supplementary context.
Authors: Jingfeng Zhang, Yi Li, Xianchong Liang, Huan Yang
Abstract: Slope hazards constitute a major safety threat to expressway infrastructure, and their evolution is typically manifested as slow surface deformation. Conventional manual inspection suffers from low efficiency and inadequate operational safety, especially on severely deteriorated slopes. Accordingly, there is an urgent need for an automated, high-precision solution capable of large-area slope observation and analysis. This study aims to develop a highly automated workflow for slope hazard detection using Unmanned Aerial Vehicle (UAV)-borne Light Detection and Ranging (LiDAR). The proposed workflow consists of a shared data-acquisition and ground-surface extraction stage, a single-observation hazard-screening branch based on RandLA-Net, and a multi-epoch deformation-monitoring branch based on grid-wise elevation differencing. To validate the effectiveness of the proposed system, we conducted multiple UAV-borne LiDAR data-acquisition flights in real expressway slope environments. The results show that the workflow can extract usable ground-surface point clouds under vegetation cover, identify potential hazard zones from single-observation point clouds, and quantify centimeter-level elevation changes using multi-epoch grid differencing. This study establishes an end-to-end UAV-borne LiDAR-based workflow for slope inspection and demonstrates its feasibility through controlled experiments, field tests, and simulation-based validation, thereby providing an implementable solution for automated slope-hazard monitoring and intelligent early warning.
Authors: Jaganadh Gopinadhan
Abstract: Automated cheque processing requires localising key fields (date, legal amount, IFSC code, account number, signature, and payee name) before any recognition step. The IDRBT Cheque Image Dataset is, to our knowledge, the only public collection of Indian bank cheques, but it ships without field annotations and with no stated licence, so its redistribution terms are unclear. We address both limitations. First, we release six-field bounding-box annotations for all 112 cheques in the dataset, distributed annotations-only and keyed to the original filenames so that the IDRBT redistribution terms are respected. Second, we release 295 fully redistributable synthetic cheque images produced by a cut-paste pipeline that composites annotated field regions from real cheques onto content-erased, bank-specific canvas templates; because patches are pasted at their source coordinates, annotations carry forward unchanged. Third, we provide a ResNet-50 direct-regression baseline that predicts all six fields in a single forward pass, and use it for a controlled test of the synthetic data. The test is sobering: because cheque layouts are rigid, a no-learning baseline that simply predicts each field's mean training box already reaches 0.691 mean IoU and 80% accuracy at IoU >= 0.5, and once seed variance and training compute are accounted for, the cut-paste synthetic data yields no measurable improvement over real data alone (an equal-compute real-only model matches or beats the synthetic-augmented model on every aggregate metric). We report this negative result in full, since it cautions against assuming appearance-only augmentation helps fixed-layout documents and points instead to layout-varying synthesis. The annotations and synthetic images are released as reusable resources on the Hugging Face Hub under permissive licences.
Authors: Boyang Li, Hezhao Xu
Abstract: Viewport-adaptive 360-degree imaging seeks to allocate a fixed sampling budget to the region a viewer is likely to observe. Existing view-biased projections increase viewport resolution through non-conformal warps, which can introduce anisotropic stretching and shear. We formulate spherical Mobius boosts as exact conformal maps for fixed-budget viewport magnification. The continuous spherical warp has quasiconformal dilatation K = 1, reallocating samples toward a target direction while preserving local angles. On a SUN360 saliency audit with 72 panoramas and 216 paired viewport targets, C1 Mobius boosting improves viewport PSNR over optimized offset cubemap on all paired cases, with case-level median gain +3.26 dB, image-level median gain +3.23 dB, and panorama-level bootstrap 95% CI [+3.15, +3.33] dB. Pareto analysis shows that this is not a free global-quality improvement: C1 trades full-sphere WS-PSNR for shear-free viewport fidelity. Prediction-error and filtering studies identify the operating envelope: strong boosts are useful for accurately targeted viewports, while large target uncertainty calls for weaker boosts or fallback. These results position Mobius boosting as a geometric primitive for prediction-conditioned foveated 360-degree resampling rather than a universal encode-once layout.
Authors: Hao Vo, Duc Nguyen, Ngan Le
Abstract: Multi-Camera Multi-Target (MCMT) tracking has emerged as a critical capability for applications ranging from autonomous driving to animal behavior monitoring. While recent advances have yielded sophisticated tracking algorithms, the availability of annotated multi-view data remains a significant bottleneck. Existing annotation tools predominantly support single-camera workflows or rely on LiDAR sensors, making cross-view labeling tedious and impractical for camera-only setups. We present ARGUS-TRACK, a multi-camera annotation system that addresses these limitations by enabling annotators to work directly on a bird's-eye-view (BEV) plane. Given calibrated camera parameters, a single ground-plane annotation is automatically projected into 2D bounding boxes across all relevant views, inherently ensuring identity consistency without manual cross-view alignment. To further accelerate the labeling process, ARGUSTRACK incorporates two complementary mechanisms: a Temporal Aware module that propagates annotations from preceding frames to initialize new ones, requiring only minor positional adjustments; and a Multi-camera Semi-annotation module that leverages off-the-shelf 2D detectors combined with foot-point estimation to automatically generate candidate BEV positions for annotator verification. We evaluate ARGUSTRACK through a pilot study on multi-camera broiler tracking and demonstrate that it substantially reduces annotation time compared to conventional single-camera labeling workflows.
Authors: Rahul Patel, Nirjala Jarpula
Abstract: Neonatal jaundice (hyperbilirubinemia) is one of the most common conditions affecting newborns worldwide, with India alone recording roughly 15 million cases per year. Early detection is critical, yet standard diagnosis requires blood tests that are often impractical in rural clinics where laboratory facilities are limited. This paper presents NeoJaundice-AI, a smartphone-based screening system that uses photographs of a baby's skin and sclera (eye white) to estimate jaundice severity and predict serum bilirubin levels in under three seconds without requiring internet connectivity. The proposed system is built on a dual-branch EfficientNet-B0 architecture that independently processes skin and sclera images. Deep features are fused with handcrafted YCbCr color statistics to jointly perform four-class severity classification and continuous bilirubin regression. A key contribution is a synthetic jaundice generation method that simulates bilirubin-induced yellowing through controlled YCbCr channel modifications on normal neonatal skin images. This approach addresses data scarcity, particularly for severe jaundice cases and darker Indian skin tones (Fitzpatrick Types IV to VI). In addition, a skin-tone normalization module improves prediction consistency across diverse neonatal complexions. Experimental results demonstrate an overall classification accuracy of 91.8 percent, a clinical sensitivity of 93.5 percent, and a bilirubin mean absolute error of 1.4 mg/dL. After INT8 quantization and ONNX conversion, the model size is reduced to 8.3 MB while maintaining inference times below three seconds on standard Android devices. To the best of our knowledge, this is the first India-focused neonatal jaundice AI system that combines multimodal image fusion, skin-tone adaptation, synthetic data augmentation, and fully offline mobile deployment within a single framework.
Authors: Maulik Srivastava, Esha Saha, Hao Wang
Abstract: Background: Wildfires in Canada present increasing threats to ecosystems, communities, and infrastructure, demanding accurate forecasting tools to aid mitigation efforts. Existing models often lack scalability or fail to capture temporal dynamics effectively. Aims: This study aims to develop a deep learning framework tailored to Canadian wildfire spread prediction that captures spatio-temporal patterns in environmental data. Methods: We propose a U-Net architecture integrating a Video Swin Transformer encoder with a convolutional decoder to model three-day sequences of meteorological and environmental variables. Data are exclusively sourced from public repositories via Google Earth Engine, ensuring transparency and scalability. The model is trained and tested on a curated dataset of major Canadian wildfire events from 2014 to 2023. Key results: Our approach achieves strong predictive performance by effectively leveraging spatio-temporal attention to forecast next-day fire incidence maps. Conclusions: The model successfully captures complex wildfire dynamics unique to Canada's landscape and temporal variability. Implications: This framework paves the way for advanced spatio-temporal wildfire forecasting research and operational applications using publicly accessible datasets.
Authors: Shuyang Hou, Ziqi Liu, Haoyue Jiao, Lutong Xie, Yaxian Qing, Xiaopu Zhang, Qingyang Xu, Zhangyan Xu, Xuefeng Guan, Huayi Wu
Abstract: AlphaEarth Foundations (AEF) unify global remote sensing foundation embeddings through multimodal self-supervised learning, but their pretraining focuses on physical land-surface signals, limiting plug-and-play use in socioeconomic tasks. We integrate seven heterogeneous data streams across 36 Chinese cities over eight years - AEF embeddings, population, nighttime lights, remote sensing indices, points of interest (POIs), urban morphology, and cross-lingual text - and construct CHN-Econ, a socioeconomic benchmark with 16 labels in three categories. We conduct 31 controlled experiments along five axes: fusion architecture, self-supervised objective, text integration, embedding dimensionality, and normalization. Used alone as a linear probe, AEF achieves R2 values of only 0.301 for cross-region and 0.160 for cross-tier evaluation. The five-axis ablated backbone improves these scores to 0.832 and 0.671, respectively, but reveals that low-dimensional semantic streams are consistently suppressed by high-dimensional streams under shared reconstruction. To address this bottleneck, we propose Capacity-Adaptive Reconstruction (CAR), replacing shared reconstruction with per-stream decoders and stream-level losses to mitigate inter-stream capacity competition. CAR further raises cross-region and cross-tier R2 to 0.848 and 0.693, and restores collapsed labels from negative R2 to a stable range. Using CAR, we infer 14.4 million pixels across 36 cities and eight years and release AEF-Econ, including 128d and 64d compressed versions. Self-diagnostics and case studies show that AEF-Econ captures cross-city hierarchies and intra-urban spatial organization under unsupervised settings, providing a socioeconomic remote sensing foundation embedding complementary to AEF physical embeddings.
Authors: Eirini Baltzi, Dionysis Christopoulos, Sotiris Spanos, Valsamis Ntouskos, Konstantinos Karantzalos
Abstract: Vision-language models (VLMs) have sparked growing interest in zero-shot Earth Observation (EO) downstream tasks, with further gains enabled by remote-sensing-adapted models. We examine this setting across 17 VLM variants and 12 remote sensing (RS) datasets under Meta-Prompting for Visual Recognition (MPVR), and show that zero-shot performance remains highly sensitive to textual design choices, from the meta-prompts used to guide the LLM in generating class descriptions to the descriptions themselves. We explore why semantically rich LLM-generated class descriptions do not translate into consistent gains over simple domain-adapted CLIP-style descriptions. While LLM descriptions are more semantically expressive, they can also introduce noise in the text embedding space, reducing robustness in downstream tasks. We support this observation through a text log-likelihood analysis in the whitened CLIP feature space, comparing LLM-generated and template-based descriptions. Building on this finding, we study query embedding calibration and show that lightweight calibration of the query space consistently yields strong improvements in zero-shot classification and retrieval. Overall, our results provide practical insight into the trade-off between semantic richness and robustness, and identify embedding calibration as a simple and effective tool for improving zero-shot remote sensing performance.
Authors: Hong-Fei Li, Xi-Lin Gao, Yi-Juan Xiang, Shu-Song Huang, Yi-lin Wang, Chun-Dong Xue, Zhuo Yang, Yong-Jiang Li, Xu-Qu Hu
Abstract: Label-free, image-based cellular mechanophenotyping in microfluidic devices provides a high-throughput method for single-cell profiling. However, while complex microchannels (e.g., hyperbolic geometries) reveal transient deformation dynamics under continuous extensional stress, the resulting high-dimensional feature spaces are highly susceptible to hydrodynamic artifacts. Flow rate variations often distort discriminative boundaries, linking feature distributions to fluid conditions rather than intrinsic biology. To overcome this, we introduce a stability-guided analytical framework that decouples flow-induced noise from authentic mechanobiological signatures. We tracked the morphodynamic, kinematic, and intracellular optical-density trajectories of healthy and malignant ovarian cells to build a 93-dimensional feature space. Using a cross-flow screening strategy based on structural consistency and statistical persistence, we isolated robust descriptors, creating task-adapted subsets (20 features for binary classification; 25 for cancer subtyping). Variance-attribution analysis confirmed the neutralization of flow-conditioned artifacts; notably, flow-associated variance in the primary principal component fell from 69.9% to 9.3% in the subtyping task. We also found that macroscopic binary discrimination depends on bulk kinematic transitions, while clonal subtyping requires localized intracellular optical heterogeneity. These optimized subsets maintained diagnostic fidelity across multiple machine learning architectures and restricted sampling conditions. This framework establishes a robust, flow-independent foundation for continuous dynamic phenotyping.
Authors: Gao Zhu, Zaishuo Xia, Yubei Chen
Abstract: We ask whether the representational hierarchy seen in perception, from local primitives such as edges to higher level structures such as parts and objects, can be established for motion. In humanoid control, low level actions specify immediate motor commands, while meaningful behavior is organized over longer temporal scales, including contacts, gait fragments, balance recovery, reaching, and whole body skills. We introduce MotionPyramid, a hierarchical action representation that learns such structure from motion data. Starting from a motion tracking teacher, it trains a recursive stack of latent decoders: low level latents decode to immediate full body motor commands, while higher level latents unfold through lower levels into temporally extended motion programs. After pretraining, the hierarchy is frozen and reused by downstream reinforcement learning policies as a family of action interfaces at different control resolutions. Experiments show the learned levels form a motion hierarchy: coarser interfaces improve early learning and motion regularity by constraining exploration to structured segments, while finer interfaces preserve feedback control and final task precision. Representation probes show the hierarchy supports traversal, interpolation, transition, and qualitative composition, exposing editable control handles across temporal scales. Finally, we introduce Residual Interfaces, letting a downstream policy maintain coarse, segment level, and frame level residual commands through the frozen hierarchy. Analogous to residual or skip connections in deep networks, this allows coarse motion programs and fine residual corrections to coexist within one controller. MotionPyramid shows that motion, like perception, can be organized into a reusable multi level representation, providing structured abstraction without sacrificing controllability.
Authors: Christian Intern\`o, Alexander Pondaven, Habon Issa, Fabio Pizzati, Francesco Pinto, Markus Olhofer, Ivan Laptev, Philip Torr, Eero P. Simoncelli, Barbara Hammer, David Klindt
Abstract: While humans can identify physically implausible events within milliseconds, machine learning approaches addressing the same problem are extremely slow and expensive. They either rely on external multimodal-LLM judges or require ad-hoc modifications to the training procedure. In this work, we argue that indicators of physical plausibility are implicitly captured by five geometric properties of the per-frame embeddings produced by frozen image encoders. In aggregate, we call them GEOPHYS. First, we show that these signals correlate with human EEG responses to two forms of object-permanence violations. Second, GEOPHYS robustly discriminates physically implausible videos from realistic ones, achieving state-of-the-art physics-violation detection: 98.3% on LikePhys and 93.3% on IntPhys2, whereas V-JEPA 2, GPT-4o, Gemini, and twelve modern video diffusion models perform near chance. Third, used as a best-of-N verifier for physical alignment during video generation, GEOPHYS lifts MAGI-1 24B from 50.01% to 64.50% on PhysicsIQ at 1.5x lower wall-clock and 4.65x lower memory than the V-JEPA 2 world-model verifier. Ultimately, GEOPHYS demonstrates that physical plausibility in videos can be assessed by leveraging the emergent geometric properties of temporal features extracted from image encoders.
Authors: Shiwen Zhang, Yifan Xu, Haibin Huang, Chi Zhang, Xuelong Li
Abstract: Given a content reference and a style reference, content-preserving style transfer requires the model to generate stylized outputs with content and style consistency. We introduced TeleStyle V1 to tackle this problem. However, TeleStyle V1 is trained with photorealistic content reference and artistic style reference, which makes it incapable to cope with artistic content reference and realistic style reference in most cases. In this paper, we designed a Self-Distillation data synthesis strategy to construct such triplets from TeleStyle V1. Trained with such self-distilled triplets, our TeleStyle V2 supports Content-Style references in the forms of Realistic-and-Realistic (RnR), Realistic-and-Stylized (RnS), Stylized-and-Realistic (SnR), Stylized-and-Stylized (SnS). In addition, we found Distribution Matching Distillation could preserve the general text-guided image editing capability of the foundation model and fix the content consistency degradation caused by SFT process. Through quantitative evaluations, our TeleStyleV2-QIE-2509-DMD performs at least on par with Qwen-Image-Edit-2509-DMD, demonstrating strong general image editing skills beyond content-preserving style transfer. We observed the content/style reference order confusion problem in TeleStyle V1 and further introduced prompt enhancer to solve it. TeleStyle V2 uses Qwen-Image-Edit's VLM encoder, Qwen2.5-VL-7B, to generate content prompt and style prompt for free. TeleStyle V2 could achieve comparable style transfer performance with state-of-the-art commercial model, gemini-3-pro-image-preview.
Authors: Mingde Xu, Zhen Yang, Yan Wang, Yu Wang, Xijun Liu, Zijun Dou, Wenyi Hong, Xiaotao Gu, Bin Xu, Jie Tang
Abstract: UI videos provide a natural input for generating interactive webpages, as they capture both webpage appearance and action-triggered state transitions. However, directly applying video-capable vision-language models to this task remains insufficient. Existing models typically rely on sparse sampling or compressed temporal representations, which may miss short action boundaries and break the state-action-state transitions needed to implement webpage behavior. We formulate UI video-to-code generation as executable state-transition recovery from interaction videos, and identify this failure mode as state-transition misalignment. We introduce Video2Code, an action-aware video-to-code approach for recovering executable UI state transitions. Rather than allocating the visual budget uniformly across the video, Video2Code first performs coarse video understanding to locate action-critical regions, then invokes a temporal clipping tool to revisit these regions at higher temporal resolution before generating HTML/CSS/JavaScript code. We instantiate Video2Code with action-aligned video-code supervision and evaluate it under both visual and functional criteria. Experiments show that Video2Code substantially strengthens the underlying open-source model for UI video-to-code generation, improving functional correctness over direct video observation, especially on dense multi-step interactions.
Authors: Jingting Li, Hui Sha, Su-Jing Wang
Abstract: Micro-expression recognition (MER) in realistic scenarios demands high temporal sensitivity and ecological validity, yet existing benchmarks are largely constrained to laboratory-controlled settings and rigid hardware-coupled sensing. We introduce CDER-SME, a cross-device Event-RGB dataset collected under a multi-level stress induction framework (cognitive and social) to elicit spontaneous emotional leakage. To enable reproducible acquisition with independent, decoupled sensors, we provide a hardware-agnostic alignment pipeline for temporal synchronization and landmark-guided spatial registration. CDER-SME adopts a three-tier structure with 92 subjects and 1,963 expert-annotated samples (Action Units and emotions), including 790 Event-RGB pairs and 210 high-fidelity aligned pairs. We further report a reproducible multimodal baseline, where cross-modal fusion improves performance over single-modality counterparts, supporting the complementarity of event dynamics and RGB cues. By removing the need for coaxial calibration, CDER-SME offers a practical benchmark for cross-device alignment and deployable Event-RGB MER in real-world affective intelligence.
Authors: Xuelong Dai, Jianyu Ma, Boyang Ma, Biwei Yan, Yijun Yang, Yue Zhang
Abstract: Multimodal Large Language Model (MLLM)-based web agents provide practical, high-precision solutions for visual browser automation; however, they inherently expand the attack surface, introducing novel vision-based vulnerabilities. Existing adversarial evaluations targeting these agents frequently rely on permissive threat models and visually conspicuous artifacts. In this paper, we investigate a constrained vulnerability detection setting: a trusted web platform where the evaluator acts solely as an unprivileged third party, such as a merchant or advertiser, controlling only a semantically legitimate, spatially constrained region, such as an ad slot, a sponsored card, or a localized widget. Operating under these realistic constraints, we propose MIRAGE, a novel visual indirect prompt injection framework for targeted next-action hijacking. Our approach leverages diffusion models to generate perceptually benign adversarial images strictly confined to the attacker-controlled boundaries permitted by the trusted service provider. To maximize attack efficacy within such a restrictive setting, we introduce a robust optimization technique combining curvature-aware adversarial diffusion guidance with sparse, dark-pixel residual perturbations. Comprehensive evaluations against prominent MLLM web agent frameworks, specifically SeeAct and OpenClaw, empirically demonstrate the potency, realism, and stealth of our proposed MIRAGE.
Authors: Yunzhe Xue, Mohammed Saim Ahmed Quadri, Neal Panse, Justin W. Ady, Usman Roshan
Abstract: Chronic wound assessment remains a clinically challenging task that requires accurate interpretation of wound morphology, tissue composition, vascular characteristics, and infection risk. Recent advances in Vision-Language Models (VLMs) have introduced the possibility of automated multimodal wound analysis through image understanding combined with clinical reasoning. This study evaluates the performance of several general-purpose and medically specialized open-source and proprietary VLMs for clinical wound assessment using an expanded, curated dataset of 20 clinically diverse wounds spanning vascular, surgical, ischemic, venous, lymphedema, and amputation-related etiologies. Six VLMs were evaluated using a structured twelve-question clinical framework covering wound classification, infection risk, vascular intervention recommendations, debridement urgency, wound therapy selection, and advanced management planning. Across 20 wound cases and 240 clinician-graded wound-analysis decisions, ChatGPT achieved the highest overall performance with 174/240 correct responses (72.50%), followed by Claude with 149/240 (62.08%). Among the open-source and medically specialized models, HuluMed achieved the strongest performance with 96/240 correct responses (40.00%), followed by Gemma 3 (81/240, 33.75%), MedGemma 4B (62/240, 25.83%), and MedGemma 27B (42/240, 17.50%). The findings suggest that frontier general-purpose multimodal systems currently demonstrate substantially stronger wound-analysis performance than medically specialized alternatives, highlighting the continued importance of broad multimodal reasoning capabilities alongside domain-specific medical knowledge. Although current VLMs demonstrate promising potential for clinical decision support, substantial limitations remain in advanced wound-management reasoning, procedural planning, and autonomous clinical reliability.
Authors: Seojun Shon, Chikao Tsuchiya, Dhaval Bhanderi, David Ilstrup, Hsinmin Cheng, Christopher Ostafew
Abstract: Accurate, up-to-date representations of road structures are critical for the safe operation of autonomous vehicles. Existing systems rely either on costly, maintenance-heavy high-definition (HD) maps which compromise safety when outdated, or purely sensor-based online mapping which struggles with long-range reliability and occlusion. Systems incorporating map prior information into online mapping seek to overcome drawbacks of both approaches by combining them in some way. We propose 'Driveline To HD Map' (D2HDMap), an online mapping system that injects a lightweight, non-visible driveline prior to guide the estimation of visible road structures such as lane dividers, road boundaries and crosswalks. This prior incurs less effort to create and update compared to full HD map priors used in other approaches. We also show that training with such a prior can improve generalization at inference time when no prior is available. Ablation studies conducted on the nuScenes and Argoverse 2 dataset demonstrate that models trained using a driveline prior largely retain performance even when priors are not available. On a geographically disjoint split, D2HDMap achieves 44.8 mAP, surpassing recent state-of-the-art. Additionally, noise-aware training substantially increases robustness to realistic localization error.
Authors: Yixian Tian
Abstract: We introduce a compact empirical model that quantifies how answer accuracy degrades as a function of frame budget B and temporal distance D in long video understanding -- analyzing performance when recalling content from D seconds in the past using a fraction B of total frames. Long-form models operate under strict budgets, yet no prior framework predicts how accuracy degrades as B shrinks and events recede. We fit a weighted least-squares model on ~155,000 binary predictions across ten models and three sampling strategies, deriving a law where logit-accuracy scales linearly in log-budget with a distance-dependent exponent that decays log-linearly with distance. This budget exponent \alpha(D) captures the marginal value of extra frames at distance D. The law achieves cell-level weighted R^2 = 0.05-0.75 across models. Notably, budget effectiveness at D = 1000 s differs by \approx 7.4\times between the best streaming and base models. STREAMINGVLM achieves \alpha(1000) = 1.26 (95% CI: [1.06, 1.58]), meaning a tenfold budget increase substantially improves long-distance accuracy, while the best Qwen3-VL base model reaches only \alpha(1000) = 0.17 (CI: [0.04, 0.34]). In accuracy space, a 10\times budget increase at D = 1000 s yields +29 percentage points for STREAMINGVLM versus +4 pp for the base model. Sampling strategies show model-dependent trade-offs: random sampling yields higher base sensitivity but steeper distance decay. We demonstrate how \alpha(D) enables principled budget allocation, including a model-ranking reversal at long distance, and propose it as a diagnostic metric for streaming video models.
Authors: Jinchao Ge, Lingqiao Liu, Shuwen Zhao, Lei Wang
Abstract: Vision foundation tools such as open-vocabulary detectors, segmentation models, and post-processing operators are powerful building blocks for computer vision, but their effectiveness depends heavily on how they are orchestrated: which tools are used, in what order, with what parameters, and under what visual conditions. Existing visual-programming agents typically generate a fixed solution pipeline, making them brittle under dense objects, occlusion, small targets, and domain shift. We introduce VTOS (Vision Tools Orchestration Search), a framework for adaptive visual tool orchestration through joint solution--observer search. VTOS co-searches executable solution programs that compose vision tools such as Grounding DINO, SAM, NMS, and slice-and-detect, together with observer programs that diagnose candidate solutions, identify failure modes, and generate actionable feedback. These observations are accumulated in a shared VisionThoughts knowledge base to guide subsequent search. We evaluate VTOS through two case studies: dense object counting on LVIS-Count and zero-shot plant-disease segmentation on PlantSeg-OOD, which stress different orchestration challenges including threshold calibration, NMS, slicing, mask refinement, and domain generalization. Across both tasks, VTOS outperforms static tool pipelines and agentic visual-programming baselines, showing that co-searching solutions and observers is an effective strategy for adapting vision tools to challenging computer vision tasks.
Authors: Nathan Salazar, Emmanuel Dellandr\'ea, Mathieu Lefort, Alexandre Meyer
Abstract: Large-scale human motion datasets are essential for training robust motion models for analysis, synthesis, and understanding. While marker-based motion capture provides precise data, it is costly and limited in scale and diversity. Recent advances in monocular motion capture and video-language understanding open the way to extract plausible motion from unconstrained online videos. We present a scalable pipeline for constructing in-the-wild human motion datasets. From a few keywords, the system retrieves videos, extracts 3D body and facial motion, and generates high-level textual descriptions. The pipeline is flexible, enabling targeted collection of various motions, multi-person interactions, or expressive behaviors. We demonstrate its quality by training motion reconstruction and motion generation models, showing performance comparable to models trained on traditional motion capture datasets and strong cross-dataset generalization.
Authors: Francesca Morandi, Omayma Moussadek, Federico Venturini, Mauro Suardi, Alessandro Banzatti, Francesco Cannarile, Angelo Porrello, Simone Calderara
Abstract: Open Vocabulary Action Recognition (OVAR) enables the recognition of novel actions by leveraging vision-language representations, overcoming the limitations of traditional closed-set approaches. However, achieving robust performance in real-world scenarios typically requires domain-specific fine-tuning, which is often costly and raises privacy and regulatory concerns. In this work, we propose an alternative paradigm that bypasses target-domain training and recombines knowledge from existing datasets and models. Leveraging model merging and task arithmetic, we extract and combine task vectors from models fine-tuned on diverse public OVAR datasets. We show that, in out-of-distribution settings, the resulting merged model achieves superior zero-shot generalization to the pre-trained base model. Code is available at https://github.com/omaymaMoussadek/robust-ovar
Authors: Tengjie Lin, Yutao Sun, Jingwei Ni, Shuhan Ge, Hao-Xuan Ma, Yanting Miao, Wangyue Lu, Mingshuai Chen, Tiancheng Zhao, Jianwei Yin
Abstract: Static visual question answering (VQA) benchmarks age quickly: Once the items leak into training corpora, scores can reflect memorization rather than genuine visual ability, thus obscuring real progress. Rebuilding high-quality benchmarks such as V*Bench requires substantial human annotation, yet each static release can quickly become another leaked artifact. We propose ReKey, a live benchmark protocol that randomly regenerates the answer-bearing local detail, or visual key, in real images at evaluation time. Using human-validated edit slots, ReKey samples fresh instances with new answers, construction-grounded labels, and controlled visual-search difficulty. On V*Bench, the ReKey regenerated benchmark reveals a sharp score jump across eight frontier vision-language models (VLMs): The original items score 9.5--18.8 percentage points higher than the regenerated variants. By making the visual key renewable, ReKey keeps evaluation fresh as models and training data evolve.
Authors: Matheus B. Rocha, Gustavo B. Dettogni, Renato A. Krohling
Abstract: This article presents a complementary approach for integrating multimodal medical data in cancer classification, based on state space models represented by the Mamba architecture. To this end, a mixed multimodal fusion architecture, called Mixed Fusion, was employed and developed to enhance the interpretability of the decision-making process. The proposed approach explores two variants of Mamba: one dedicated to visual processing, responsible for classifying the lesion image and generating probabilities associated with the target classes, and another focused on tabular processing, which uses these probabilities together with clinical and/or sociodemographic data to produce the final diagnosis. The experiments were conducted on two medical datasets: PAD-UFES-20, composed of clinical images and information associated with skin lesions, and NDB-UFES, consisting of histopathological images and sociodemographic data related to oral cancer. The results indicate slightly lower performance in balanced accuracy, compared with Transformer-based approaches, on PAD-UFES-20, and superior performance on NDB-UFES. Additionally, substantial gains were observed in the recall metric. Furthermore, the adoption of the Mixed Fusion architecture enables the application of the Shapley Additive Explanations (SHAP) method, increasing the interpretability of the results. These findings indicate that Mamba-based models constitute a suitable alternative for multimodal classification in medical data, especially in scenarios in which sensitivity is a relevant requirement.
Authors: Ziba Parsons, Ang Li
Abstract: Deep neural network-based LiDAR 3D object detection serves as a critical perception component in safety-critical autonomous systems. However, recent studies have revealed its vulnerability to backdoor attacks. Existing attacks typically require white-box access or label modification and focus on geometric attacks such as object disappearance or bounding-box manipulation. In this paper, we present Mirage, a black-box and clean-label backdoor attack against deep neural network-based LiDAR 3DOD. Mirage injects a small number of label-consistent poisoning samples into the training set, causing the model to learn a malicious association between a trigger pattern and an attacker-chosen target class while preserving normal training semantics. As a result, the compromised model behaves normally on benign inputs yet systematically misclassifies triggered objects as the target class during deployment. We evaluate Mirage on multiple state-of-the-art LiDAR 3DOD models and benchmark datasets. Experimental results show that Mirage achieves a 73% misclassification success rate with a poisoning rate of only 0.5%, while maintaining detection performance close to that of benign models.
Authors: Keqin Zeng, Shuting Su, Shihao Lin, Ziyue Li, Rui Zhao
Abstract: Reliable spatial decision automation, such as autonomous driving and maritime surveillance, critically depends on robust visual perception. However, real-world spatiotemporal data exhibits severe heterogeneity, often manifesting as extreme long-tail distributions for safety-critical scenarios. This data scarcity induces dataset shift that degrades detection performance and pose safety risks. While synthetic data generation offers a potential solution, existing generative approaches, such as diffusion models and Generative Adversarial Networks (GANs), often lack explicit spatial grounding and structural constraints, resulting in spatial and physical inconsistencies in generated scenes. To address these challenges, we introduce WMGen-v1, an agentic text-based world model framework for long-tail spatial data generation. WMGen-v1 employs a Large Vision-Language Model (LVLM) to construct a structured scene representation from a single reference image, while a Large Language Model (LLM) performs guidance-based scene expansion under physical plausibility and commonsense constraints. Subsequently, conditioned on the structured semantic representations produced by this reasoning process, a diffusion model generates diverse and physically grounded long-tail training data. Experiments on internal industrial datasets, ROADWork, and LaRS benchmarks demonstrate that WMGen-v1 outperforms baseline approaches. Notably, detectors trained solely on WMGen-v1 synthetic data approach real-only performance on aggregate dataset-level metrics, highlighting its potential to alleviate long-tail data scarcity for downstream spatial perception.
Authors: Changyi Li, Chao Yang, Yu Xiao, Kari Tammi
Abstract: Visual anomaly detection is a fundamental task in industrial automation. While existing approaches have achieved notable progress in identifying structural defects, the detection of logical anomalies remains relatively underexplored. In practice, structural and logical anomalies frequently co-occur in industrial workflows. Therefore, a solution capable of detecting both structural and logical anomalies is crucial for advancing comprehensive anomaly detection research. To address this limitation, we propose a unified framework, termed UniSLAD, which jointly addresses logical and structural anomalies without additional training, enabling a practical solution for dynamic industrial environments. First, we introduce a dual-feature extractor that synergistically integrates a Convolutional Neural Network (CNN) backbone for local texture perception with a Transformer backbone for global contextual reasoning, yielding richer and more comprehensive representations. Building on this foundation, we design dual-granularity feature representation modules. At the patch level, memory banks enhanced by the Mahalanobis Transform (MT) preserve representative features and support more discriminative anomaly scoring. At the image level, distribution maps are aggregated using Lower-Upper Mean (LUM) and Power Mean Pooling (PMP), yielding a more robust global representation than conventional average pooling. Extensive experiments on the two industrial benchmarks demonstrate that UniSLAD achieves competitive performance in comprehensive anomaly detection, achieving 99.4% and 93.1%, respectively. Furthermore, ablation studies verify the individual contributions and effectiveness of each proposed component.
Authors: Seunghyun Shin, Jifei Song, Wooseok Jeon, Hae-Gon Jeon, Jiankang Deng
Abstract: Camera motion control is essential for directing viewpoint changes in generative systems. However, existing methods typically condition the generation process on a single specific modality, such as explicit pose trajectories or reference videos, limiting their ability to support heterogeneous user inputs. To address this limitation, we present TriMotion, a modality-agnostic framework for camera-controlled video generation that maps video, pose, and text inputs, describing the same camera trajectory into a shared motion embedding space. Learning such a space requires synchronized supervision across modalities. Therefore, we build the Motion Triplet Dataset by extending a Multi-Cam Video Dataset with geometry-grounded motion descriptions derived from camera extrinsics. We further introduce a latent motion consistency objective that leverages the motion embedding space to encourage the generated video to follow the target camera trajectory directly in latent space, avoiding the cost of pixel-space decoding. Extensive experiments show that TriMotion generates high-quality videos that accurately follow the target camera trajectories across all three modalities. Beyond standard generation, the shared motion embedding space also enables flexible applications such as sequential motion composition and cross-modal motion interpolation.
Authors: Yixuan Lai, Tianjia Shao, Kun Zhou, Weijia Dou, Siyu Zhu, Jingdong Wang
Abstract: Generating visually consistent multi-shot videos remains an open challenge. As videos span more shots, inconsistencies can accumulate across shots, causing entities that reappear across shots -- characters, objects, and locations -- to drift away from how they first appear. We observe that viewers judge consistency by comparing each later appearance of an entity with its first clear appearance; the visual quality of this initial appearance sets the consistency ceiling for all that follows. Motivated by this, we present \textbf{GroundShot}, a training-free, model-agnostic agentic framework for entity-grounded multi-shot generation. GroundShot builds an entity-level visual memory online from accepted generated shots: it schedules shots' generation order by their expected usefulness as entity references, grounds entities from generated videos, verifies their reliability before adding them to memory, and retrieves suitable entity references from memory before each shot is generated. To evaluate this entity-centered view of consistency, we further introduce \textbf{GroundBench}, a diagnostic benchmark that measures consistency at the entity level while isolating controlled challenge dimensions. Experiments show that GroundShot improves multi-shot consistency over existing methods while requiring no additional training or model modification.
Authors: Abdullah Bin-Obaid, Maria M. Cobo, Rebeccah Slater, Lionel Tarassenko, Mauricio Villarroel
Abstract: Facial landmark localisation is a prerequisite for developing automated, non-contact neonatal pain assessment methods. Clinicians use pain scales to judge the severity of pain, many of which rely on facial expression. However, facial landmark detectors trained on adult faces perform poorly in neonatal clinical environments due to frequent occlusions caused by medical equipment, varied head poses, and challenging imaging conditions, including motion blur triggered by sudden pain-related movements. We propose an end-to-end facial landmark detector capable of predicting 68 landmarks on neonatal faces in clinical environments. We combined 37,459 single-face images from 11 public datasets, standardised to 68-point markup, with 1,123 manually annotated frames from a neonatal research dataset (totalling over 76,000 landmarks). A YOLO-based keypoint model was adapted to regress the facial landmarks, initialised with weights from a pretrained neonatal face detector. On public datasets, our proposed model achieved state-of-the-art performance: Normalised Mean Error (NME) = 5.37, Failure Rate (FR) = 12.5%, Area Under the Cumulative Error Curve (AUC) at AUC0.08 = 38.00% and AUC0.1 = 48.70%. On the clinical neonatal test set, before fine-tuning, the model achieved the lowest Detection Failure Rate (DFR) = 5.3% among all baselines and showed strong generalisation. After fine-tuning, performance improved further to NME = 6.36, FR = 22.30%, DFR = 1.77%, AUC0.08 = 29.24% and AUC0.1 = 40.25%. To the best of our knowledge, this represents the first end-to-end 68-point neonatal facial landmark detection model. With further dataset expansion and refinement, it could support downstream tasks in neonatal health monitoring and pain-related facial analysis.
Authors: Junbao Zhou, Qingshan Xu, Yuan Zhou, Xiaolong Shen, Beier Zhu, Kesen Zhao, Yiming Zeng, Chen Bai, Cheng Lu, Hanwang Zhang
Abstract: 3D Gaussian Splatting (3DGS) has emerged as a promising technique for novel view synthesis. However, 3DGS requires dense input views to achieve high-quality rendering. In sparse-view scenarios, 3DGS often prones to overfitting, resulting in noticeable artifacts and degraded rendering quality. Previous methods explore to address this issue by introducing additional priors (e.g. depth priors) or integrating regularization techniques (e.g. Dropout). However, these methods are often applied without principled guidance. In particular, prior-based augmentation typically samples novel viewpoints randomly, while Dropout-based regularization randomly removes Gaussians. The compounded randomness introduces uncertainty and instability, limiting the fidelity of novel view synthesis. In this paper, we propose a novel method for sparse-view 3DGS that incorporates Fisher Information to quantitatively guide the utilization of geometric priors and regularization. Specifically, our method comprises two key components: (1) Stereo augmentation with Fisher Information. By leveraging Fisher Information, we actively select most informative supporting views and use depth priors to curate reliable pseudo ground truths, which reduces randomness in augmentation and improves stability and rendering fidelity; (2) Uncertainty-aware regularization. We reduce the instability of Dropout-based regularization by using Fisher Information to quantitatively measure the uncertainty of each 3D Gaussian, and adaptively adjust the removal probability, leading to more stable and effective regularization. With these two components, our method effectively mitigates overfitting and improves the stability of optimization in sparse-view 3DGS, resulting in superior rendering fidelity. Extensive experiments show that our method achieves state-of-the-art performance in sparse-view novel view synthesis benchmarks.
Authors: Eduardo Moreno Judice de Mattos Farina, Mateus A. Esmeraldo, Felipe Akio Matsuoka, Paulo Eduardo de Aguiar Kuriki, Felipe Campos Kitamura
Abstract: Inference-time engineering can alter model behavior without fine-tuning. However, its utility for improving diagnostic performance in medical vision-language models (VLMs) remains unclear. We aim to evaluate whether Contrastive Activation Addition (CAA) can improve pneumonia classification in chest radiograph VLMs without updating model weights. Three frozen chest radiograph VLMs (MedGemma-4B-IT, NV-Reason-CXR-3B, and CheXOne-3B) were evaluated on the public Kermany pneumonia test set. Classification was based on the logits of the tokens Yes and No under a binary prompt. Steering vectors included a 30-pair answer-bias control, a 30-pair pneumonia text contrast, and an image-conditioned contrast derived from 30 pneumonia and 30 normal development images. A deterministic 200-image development set was used for layer and scale selection (100 images) and threshold calibration (100 images). Performance was assessed using ROC-AUC, PR-AUC, F1 score, threshold analyses, reverse-vector controls, random-vector controls, and conditional bootstrap confidence intervals. Fixed-threshold F1 improvements were frequently observed but did not consistently indicate improved diagnostic performance. For MedGemma-4B-IT. NV-Reason-CXR-3B showed the strongest benefit: calibrated F1 improved from 0.7692 in the zero-shot setting to 0.8619 with pneumonia-text steering and to 0.8727 with image-conditioned steering. For CheXOne-3B, pneumonia-text steering increased calibrated F1 from 0.8528 to 0.8666, although the confidence interval crossed zero. On this public pneumonia benchmark, CAA substantially altered prediction score distributions and operating characteristics without fine-tuning. Meaningful performance gains were observed in one of three evaluated VLMs, suggesting that activation steering may serve as a lightweight approach for adapting medical VLM behavior.
Authors: Hiroki Sakuma, Masatoshi Okutomi
Abstract: Multi-view surface reconstruction is a core problem in computer vision. One prominent line of work represents the surface implicitly as a signed distance field (SDF), optimizing it based on the photometric loss between rendered and observed pixel colors. These approaches typically employ SDF-based volume rendering to obtain a differentiable relaxation of discontinuous visibility along rays, thereby reducing reliance on silhouette supervision. In this paper, we reformulate SDF-based volume rendering as probabilistic surface rendering, where each pixel color is modeled as a mixture distribution induced by the random first ray-surface intersection. To this end, we introduce Stochastic Signed Distance Processes (SSDP), which model the SDF along each ray as a stochastic process, inducing a first-passage-time distribution for each ray. We then derive the first-passage probability for each sampling interval based on Bayesian filtering, together with its practical approximation for parallel rendering. We further show that NeuS, an existing SDF-based volume rendering method, arises as a special case of our formulation. Experiments on the DTU and MobileBrick datasets demonstrate that our method outperforms baselines in both surface reconstruction and uncertainty quantification, supporting the effectiveness of our first-passage formulation. Our code is available at https://github.com/skmhrk1209/SSDP.
Authors: Duc Minh Nguyen, Nghiem Tuong Diep, Binh Gia Nguyen, Trong-Bao Ho, Doanh Le, Tan Q. Nguyen, Thien-Loc Ha, Nhiem Tran, Bao Thach, Nhat X. Tran, Tuan A. Tran, Artur Habuda, Philip Lund M{\o}ller, Tran Nguyen Le, Daniel Sonntag, Matthias Niepert, Khoa D. Doan, Vu Duong, Hung Ngo, Minh N. Vu, Duy M. H. Nguyen, An Thai Le, Ngo Anh Vien
Abstract: Vision-Language-Action (VLA) models enable general-purpose robotic control via large-scale multimodal pretraining, yet their effectiveness under few-shot imitation learning remains limited. We conduct a systematic stress test of state-of-the-art VLA models and show that performance degrades sharply as demonstrations are reduced, revealing a key weakness of existing adaptation strategies. To address this, we introduce FOCA, a future-oriented conditioning framework for data-efficient VLA adaptation. FOCA combines explicit prediction of task-grounded future interaction embeddings with implicit alignment to future goal observations, enabling long-horizon reasoning in latent space without pixel-level prediction. This formulation naturally supports action-free co-training with synthetic videos from video world models and can be interpreted as learning a future-conditioned value-like representation. Extensive experiments demonstrate FOCA achieves 95.7% success with 20 demonstrations on LIBERO, improves 7-12% on RoboCasa, and delivers up to 26% absolute gains on real robots, establishing a new state of the art in few-shot VLA adaptation.
Authors: Luan Marko Kujavski, Rayson Laroca, Paulo Lisboa de Almeida
Abstract: As urban areas expand, automatic monitoring of parking lots becomes essential for efficient and sustainable cities. This work proposes a self-supervised approach for parking spot occupancy recognition that requires no labeled samples from the target parking lot. Building upon a self-supervised transfer learning fine-tuning protocol, the proposed training strategy consists of two self-supervised stages: first on unlabeled generic data and then on unlabeled target-specific data, followed by supervised fine-tuning using only generic parking lot labels. We adopt SimCLR with a ResNet-50 encoder and evaluate the method under a leave-one-out cross-environment protocol on three public datasets: PKLot, CNRPark-EXT, and PLds. We also introduce a two-stage deployment strategy in which a Strong General Model is initially deployed, followed by a Specialized Model that incorporates unlabeled images collected during the first N days of deployment in a self-supervised manner. Experimental results show that the Strong General Model alone outperforms supervised and self-supervised baselines, achieving an average accuracy of 97.2%, which further improves to 97.8% with the proposed two-stage strategy. These results demonstrate that self-supervised learning enables a scalable and labelefficient solution for real-world parking occupancy monitoring. Our trained models and source code are publicly available at https://github.com/LoanMaikon/Parking-Spot-Occupancy-Recognition.
URLs: https://github.com/LoanMaikon/Parking-Spot-Occupancy-Recognition.
Authors: Thomas Markhorst, Zhi-Yi Lin, Jouh Yeong Chew, Jan van Gemert, Xucong Zhang
Abstract: In this work, we propose \methodname, an LLM-based model for fine-grained human motion understanding that represents motion as a sequence of skeletal poses with explicit timestamps for each pose. Each pose encodes body joint positions and is temporally grounded with timestamp tokens, allowing the model to reason about motion order, duration, and rhythm. To study what supervision is needed for motion-language reasoning, we construct a diverse training mixture spanning pose captioning, pose question answering, motion captioning, and motion question answering. Our ablations show that the primary gains come from the diversity of pose- and motion-level supervision, while staged training provides a smaller additional benefit. Different from previous works that rely on ground-truth 3D motion capture, our approach supports both 2D and 3D skeletal motion representations through a unified pose encoder, and can optionally incorporate video to provide contextual information. Extensive experiments on BABEL-QA, HuMMan-QA, CompMo, NTU-RGB+D, and QEVD-Coach demonstrate that our method achieves state-of-the-art performance across multiple benchmarks, highlighting the effectiveness of explicit temporal encoding and diverse pose- and motion-level supervision for fine-grained human motion understanding. Notably, even when using only 2D skeletal input, our approach surpasses previous 3D-based methods.
Authors: Koichi Namekata, Yash Kant, Zhizheng Liu, Ryan D Burgert, Yuancheng Xu, Kuan Heng Lin, Emmett Steven, Julien Philip, Li Ma, Andrea Vedaldi, Paul Debevec, Ning Yu
Abstract: Filmmaking demands precise motion control and reference image compositing -- capabilities that existing methods treat separately. Point-track-conditioned image-to-video models restrict content insertion to the first frame, while reference-to-video models lack fine-grained spatial-temporal control over how reference content integrates across frames. We present Go-with-the-Track, which unifies both capabilities by jointly conditioning on multiple reference images and reference-anchored point-tracks -- extending conventional point-tracks to explicitly establish correspondences between generated frames and reference images, thus enabling precise compositing and motion control throughout the video. To achieve this, we introduce spatially-aware point-track embeddings that encode the full sequence of point-track coordinates using a coordinate-wise MLP followed by temporal pooling. This representation captures the spatial characteristics of each point-track (serving as a unique identifier), while the embedding similarity correlates directly with spatial proximity, enhancing the model's ability to distinguish and associate point-tracks. We inject these point-track embeddings into a video diffusion transformer via a lightweight adapter, resolving the pixel-to-patch resolution mismatch while avoiding the substantial motion detail loss inherent in naive point-track subsampling. We use a hybrid training strategy to train jointly on dynamic, static, and synthetic scene video datasets to boost motion controllability. Experiments demonstrate that Go-with-the-Track achieves superior motion and reference control in a single model and enables new capabilities: multi-reference conditioned video generation with point-track driven compositing, as well as camera control for both static and dynamic scenes. Project Page: https://eyeline-labs.github.io/Go-with-the-Track/
Authors: \"Umit Mert \c{C}a\u{g}lar, Alptekin Temizel
Abstract: Earth observation imagery plays a critical role in environmental monitoring, urban planning, disaster assessment, and climate analysis. While multi-spectral sensors are increasingly available, true-color (RGB) imagery remains widely used due to the power, cost, and deployment constraints of many satellite and aerial platforms. However, existing land-cover segmentation datasets are often limited in geographic coverage, scale, or public accessibility. To bridge this gap, we introduce BELDE (Building a Large-scale Earth-observation Land-cover Dataset for Europe), a publicly available dataset tailored for RGB-based remote sensing semantic segmentation. Constructed from Sentinel-2 true-color images and ESA WorldCover data annotations, BELDE contains 1,088,385 curated image-segmentation map pairs spanning Europe with 7 land-cover classes at 10 m spatial resolution, making it one of the largest publicly available RGB land-cover segmentation datasets for Earth observation. To facilitate cross-region generalization studies, we additionally introduce BELDE-K (16,607 pairs) covering the Republic of Korea and BELDE-CA-NV (88,155 pairs) covering California and Nevada in the United States. We establish baseline results using multiple semantic segmentation architectures and evaluate both in-domain and cross-domain performance. Models trained on BELDE achieve an F1 score of 83.0% on the European test set, while performance decreases to 66.4% on BELDE-CA-NV and 58.3% on BELDE-K, highlighting the challenges posed by out-of-distribution geographic domain shift. By providing a continental-scale RGB segmentation and evaluation benchmark, BELDE supports the development of robust and transferable Earth observation models. The dataset and benchmark resources will be publicly released.
Authors: Abhijit Das, Nichula Wasalathilaka, Yifan Lu, Adinath Dukre, Dwarikanath Mahapatra, Shadab Khan, Imran Razzak
Abstract: Medical vision-language models (VLMs) enable zero-shot clinical image classification, yet reliably detecting out-of-distribution (OOD) inputs at deployment remains an open problem. No static scoring method works across all shift types: Maximum Concept Matching (MCM) on FLAIR achieves 76.4% AUROC for far-OOD but only 42.4% for covariate shifts such as ultra-wide-field fundus images, effectively random. We trace this to a structural mismatch: covariate-shifted inputs are indistinguishable from in-distribution samples in softmax space, yet occupy distinct regions in the VLM embedding space. To exploit this untapped signal, we propose PROTON (PROtotype-based Test-time ONline OOD detection), a lightweight post-hoc module that maintains an online prototype bank from high-confidence test predictions and adaptively fuses prototype distance with MCM scoring via stream-level variance statistics, requiring no model modification, training data, or prompt engineering. On the ophthalmology benchmark FLAIR + FIVES, PROTON improves MCM by +23.9 AUROC on covariate shift, +8.8 on semantic shift, and +8.1 on far-OOD, making it the only zero-shot method to improve all three without hierarchical prompts or labeled data. Code is available at https://github.com/GenMI-Lab/PROTON, and the project page is available at https://genmi-lab.github.io/PROTON.
URLs: https://github.com/GenMI-Lab/PROTON,, https://genmi-lab.github.io/PROTON.
Authors: Mojgan Forootan, Mahziar Setayeshfar, Ali Darvishi, Mohammad Tashakoripour, Hamidreza Bolhasani
Abstract: Gastric intestinal metaplasia (GIM) is a precursor lesion to gastric dysplasia and adenocarcinoma whose early detection is crucial for intervening in the carcinogenesis cascade. Artificial intelligence (AI) holds considerable promise for real-time endoscopic detection and characterization of GIM. However, development of reliable AI models has been constrained by the absence of publicly available, histopathologically validated datasets that combine detailed endoscopic annotations, histological subtype (complete and incomplete), standardized grading systems, and normal mucosal patterns. GIM-ENDO was designed to fill this gap. The dataset comprises demographic data, endoscopic findings, histopathological results, and H. pylori status acquired using the Olympus EVIS X1 system with white-light endoscopy (WLE) and image-enhanced endoscopy (IEE), including narrow-band imaging (NBI) and magnifying NBI (M-NBI), along with images and video clips from 24 patients (22 GIM-positive, 2 normal controls). Annotations cover six primary IEE endoscopic signs -- light blue crest (LBC), marginal turbid band (MTB), white opaque substance (WOS), TV pattern (Fusion), atrophy, and map-like erythema (MLE) -- plus two additional endoscopic findings (AHP and GA) recorded where present. GIM subtypes (complete and incomplete) are annotated for all GIM-positive cases; OLGA and OLGIM staging are provided where complete histological sampling was available. The dataset is publicly accessible at https://doi.org/10.5281/zenodo.20707267. For the latest updates and further information regarding this dataset, readers are referred to the DataBioX website: https://databiox.com A short version of this work has been submitted to MICCAI 2026 Open Data Track.
URLs: https://doi.org/10.5281/zenodo.20707267., https://databiox.com
Authors: Qingtao Pan, Kai Ye, Zhihao Dou, Bing Ji, Shuo Li
Abstract: In multi-object text-to-image (T2I) diffusion, ensuring semantic consistency between textual prompts and generated visual content is crucial for image synthesis. However, such consistency constraint is often underemphasized in the denoising process of diffusion models. Although token supervised diffusion models can mitigate this issue by learning object-wise consistency between the image content and object segmentation maps, it tends to suffer from the problems of segmentation map bias and semantic overlap conflict, especially when involving multiple objects. In this paper, we propose ELDiff, a new evidential learning-supervised T2I diffusion model, which leverages the advantages of uncertainty metric and conflict detection to enhance the fault tolerance of unreliable segmentation maps and suppress semantic conflicts, strengthening object-wise consistency learning. Specifically, a pixel evidence loss is proposed to restrain overconfidence in unreliable labels through evidential regularization, and a token conflict loss is designed to weaken the contradiction between semantics through optimizing a measured conflict factor. Extensive experiments show that our ELDiff outperforms existing training based and train-free based T2I diffusion models on SD v1.4, SD v2.1, SDXL, SD v3.5, and Qwen-Image, without requiring additional inference-time manipulations. Notably, ELDiff can be seamlessly extended to the existing training pipeline of T2I diffusion models. Code can be found at https://github.com/QingtaoPan/ELDiff.
Authors: Yifan Shen, Pei Tian, Xinzhuo Li, Bowen Fang, Shujun Xia, Bingxuan Li, Ana Jojic, Wenming Ye, Xu Cao, James Matthew Rehg, Ismini Lourentzou
Abstract: Omni-modal models can ingest video, audio, and text, but unified access to multiple modalities does not guarantee that a model uses the right evidence. This gap is especially pronounced in social video question answering, where the answer may hinge on a gesture, vocal tone, temporal cue, or mismatch between what is said and what is visually expressed. We introduce CogniRoute, a schema-guided Mixture-of-Experts framework for social omni reasoning. CogniRoute uses a training-only cognitive schema that factorizes each example by cross-modal relation, reasoning demand, and temporal scope, and aligns global routing signatures with this structure during supervised fine-tuning. We further introduce route-aware reinforcement learning, which jointly optimizes token generation and expert allocation using rewards for answer correctness, modality-consistent reasoning, and cognitive temporal grounding. To support training and evaluation, we construct OmniSocialBench, a diagnostic social video QA resource with 118K structured training examples, grounded reasoning traces, schema labels, temporal evidence spans, and a manually verified evaluation split. CogniRoute achieves 59.38\% average accuracy on OmniSocialBench, improving over the strongest proprietary baseline by 15.33 percentage points and the strongest open-source omni baseline by 26.77 points, with the largest gains on questions requiring audio-visual coordination, conflict resolution, and temporally grounded social inference.
Authors: Aryan Das, Koushik Biswas, Moloud Abdar, Vinay Kumar Verma
Abstract: We introduce UNITY, a Universal-to-Specialized adapter for efficient and scalable composite conditioning in diffusion based image generation. Unlike prior methods that train separate adapters for each conditioning modality, UNITY jointly learns shared semantics across multiple conditioning types and subsequently specializes without modifying the underlying architecture. The proposed two stage training paradigm consists of a Universal Stage that captures cross modal representations across all conditioning modalities using half of the total training steps, followed by a Specialization Stage that refines modality specific features using the remaining training budget. At the core of UNITY are the Morphable Attention Flow (MAF) Network and Morph Wrapper modules, which enable channel aware and spatially adaptive feature alignment through learnable flow fields and attention based fusion. This constant complexity formulation supports flexible operation under both single and composite conditioning settings while significantly reducing inference latency and memory consumption. Extensive experiments across multiple datasets demonstrate that UNITY achieves state of the art image fidelity while maintaining superior memory efficiency. Code: https://github.com/arya-domain/UNITY
Authors: Adrian Cespedes, Marcelo Chincha, Dunant Cusipuma, Victor Flores-Benites, David Ortega, Arturo Deza
Abstract: As Self-Driving Cars continue to expand internationally and use multi-modal systems such as VLMs as a cognitive backbone for their Action models; how well will these systems generalize in new settings, in particular out-of-distribution (OOD) edge-case scenarios in new geographies? In this paper, we study this open question by providing a full factorial analysis with human drivers of Lima, human drivers from New York City, and VLMs and showing them dashcam footage collected from Lima and New York City -- prompting them with a variety of questions under a Visual Question Answering (VQA) paradigm. In particular, we pick these two cities as they are highly challenging driving locations where no Self-Driving Car company currently operates in, and ask questions that span 4 categories: Factual, Ratings, Counterfactual and Reasoning. We find that Humans and VLMs diverge in their responses -- though this is modulated by the type of questions asked, and that Humans answer similarly independent of where they are from (Lima/NYC). To our surprise, we did not find a strong difference in terms of answers (Humans or VLMs) that was modulated by geography, likely due to their high out-of-distribution nature. Our dataset is available at: https://huggingface.co/datasets/Artificio/robusto-2
Authors: Geon Choi, Hangyul Yoon, Nalee Kim, Jeong Yun Jang, Hyunju Shin, Hyunki Park, Sang Hoon Seo, Edward Choi
Abstract: The evaluation of vision-language models (VLMs) for chest X-ray (CXR) analysis has largely been limited to disease-presence classification without visual grounding. Such evaluations fail to verify the expert-level lesion perception necessary to ensure the clinical reliability of VLMs. To address these limitations, we introduce CheXpercept, a sequential, multi-level perception benchmark that mirrors a radiologist's cognitive workflow across coarse-level detection, fine-level contour evaluation and revision, and semantic-level attribute extraction. To ensure high clinical fidelity at scale, we construct the dataset using a semi-automated generation pipeline paired with a review by six medical experts. CheXpercept contains 10,400 QA items derived from 2,100 CXRs, covering seven clinically critical pulmonary and cardiac lesions. To demonstrate the current landscape of VLM perception, we benchmark 14 general and medical VLMs on CheXpercept. The models achieve adequate performance only at the coarse level, with accuracy degrading precipitously on deeper visual tasks. Notably, medical VLMs show almost no perceptual advantage over their general-domain counterparts, highlighting a systemic flaw in current domain adaptation. The code and dataset will be publicly available.
Authors: Tatsuya Suzuki, Kazuya Ijuin, Hideki Tomimori, Megumi Chikano, Katsushi Sakai
Abstract: The ocean plays a critical role in sustainable development, particularly in climate change mitigation. Among marine ecosystems, blue carbon ecosystems are recognized as important natural carbon sinks. In this context, this paper addresses precise seaweed classification for blue carbon quantification in Ocean Digital Twin initiatives. Conventional methods, including supervised learning (limited by data scarcity and domain gaps) and self-supervised learning (unable to assign class labels), struggle with underwater complexities and diverse seaweed species. To overcome this, we propose a novel two-stage seaweed segmentation technique. This technique first utilizes Supervised and Self-supervised Learning Model Propagation (SSL.Prop.), which leverages supervised learning for initial class information and approximate locations, guiding self-supervised learning for detailed, accurate segmentation. Subsequently, MaskFusion (MF) refines these results by merging instance-level masks for highly accurate segmentation. This integrated approach allows automatic class label assignment and mitigates domain gap effects. Specifically, instance segmentation estimates sparse point locations which then guide self-supervised learning for detailed region segmentation. Evaluated with underwater images from Yamaguchi Prefecture, our full proposed method (SSL.Prop.+MF) achieved a 0.068 mIoU improvement over USIS-SAM, demonstrating significant accuracy gains, particularly for small seaweed. This approach demonstrates strong potential for improving blue carbon quantification and marine ecosystem monitoring.
Authors: Jin-Hyuk Seok, Yatong An, Jae-Sang Hyun
Abstract: Single-shot fringe projection profilometry (FPP) has been actively studied for real-time measurement, dynamic object reconstruction, and motion-sensitive environments. Composite fringe patterns are advantageous in single-shot FPP because multiple frequency components can be encoded in a single pattern, enabling phase ambiguity resolution. Existing approaches mainly rely on Fourier transform-based methods or supervised deep learning methods. However, Fourier transform-based methods often suffer from limited accuracy and degraded performance in complex regions, while supervised methods require dense phase or depth labels, which are costly to obtain. In this work, we propose a self-supervised phase refinement framework for single-shot composite fringe patterns without requiring phase or depth labels. The proposed method exploits the scale and direction relationships between low- and high-frequency phase gradients, improving the reliability of phase separation. We also introduce a soft edge consistency loss to preserve object boundaries and fine geometric structures. Experimental results show that the proposed method achieves MAE_z and RMSE_z of 0.367 mm and 1.804 mm, respectively, outperforming the best-performing transform-based baseline, which obtains 0.402 mm and 2.785 mm. The proposed method also improves the valid-pixel ratio from 84.75 % to 95.07 %. These results demonstrate the effectiveness of self-supervised dual-frequency phase refinement for reliable single-shot 3D reconstruction without ground-truth label supervision.
Authors: Conghui Li, Junhao Huang, Chern Hong Lim, Bing Xue, Mengjie Zhang
Abstract: Stochastic segmentation seeks to represent multiple plausible masks for a single image, which is essential in safety- and quality-critical applications such as medical imaging or building defect inspection. Most existing methods introduce stochasticity by injecting continuous latent variables or by iterative denoising trajectories, whose stochastic sources are difficult to search or audit directly. We propose architecture distributions as a new stochastic source for segmentation: instead of sampling a latent variable or noise, we sample a discrete architecture from a learned distribution over operator choices at multiple searchable positions in a segmentation backbone. Each sampled architecture yields one mask through the selected active path, so inference depends on the executed subnet rather than the complete candidate bank. This approach also supports architectural provenance, since each output corresponds to a specific architecture configuration. To reduce collapse toward averaged masks, we train with set-level supervision by matching a set of architecture-sampled predictions to the annotation set using an IoU-based energy-distance surrogate. We further construct the candidate bank with evolutionary search, making the support of the stochastic source optimizable before distribution learning. The proposed method achieves state-of-the-art distribution matching and hypothesis coverage on LIDC-IDRI, and remains effective on two extension tasks. To the best of our knowledge, this is the first work to formulate stochastic segmentation as learning an architecture distribution and realizing output diversity through architecture sampling.
Authors: Tianao Li, Tjitske Starkenburg, Yu Sun, Emma Alexander
Abstract: Variational inference (VI) is a powerful method for principled posterior inference for scientific inverse imaging. VI learns the posterior distribution, often with a flow-based network, which can cheaply generate posterior samples upon optimization, and can flexibly incorporate score-based or classic priors. However, its application to large-scale image reconstruction is severely hindered by the poor scalability of the flow-based networks. In this work, we introduce ShuffleFlow, a scalable VI framework to address this challenge. Our method breaks down the problem into three parts: a pixel-unshuffling-based image coordinate sampler, a neural field as feature encoder, and a conditional normalizing flow (CNF) as posterior estimator. Specifically, our framework partitions an image into a stack of sub-images with pixel-unshuffling and uses a shared CNF to model the joint distribution of the sub-image stack. We condition the CNF on the output of a neural field, which embeds feature vectors corresponding to pixel-unshuffling sample locations to capture spatial structures, and share the flow's latent variable across the channels to model their correlations. We demonstrate our method's effectiveness and efficiency on both linear and nonlinear imaging inverse problems, and show its ability to more rapidly generate a high-sample-count posterior than diffusion samplers.
Authors: Dong-Hyun Moon, Ju-Hyeon Nam, Sang-Chul Lee
Abstract: Image forgery localization remains challenging due to diverse manipulation techniques and distribution shifts. Existing forgery localization models achieve high accuracy on benchmarks but often struggle with cross-domain generalization and robustness. In this paper, we propose SARIF (Segment Anything for Robust Image Forensics), a framework that leverages the Segment Anything Model (SAM), which has a promptable architecture and strong generalization ability. SARIF introduces a feedback-guided mask decoder and a dual-encoder design that extracts forgery-specific information to capture forensic traces while exploiting the SAM architecture. To localize manipulated regions, we design a block-wise prompting mechanism that derives forgery-specific cues from residual features between an adapted encoder and its frozen counterpart. These features are fused with the previous mask prompt to drive a feedback-based mask refinement process, enabling automatic forgery segmentation without manual input. Extensive experiments on standard forgery-localization benchmarks show that SARIF achieves strong average cross-dataset performance and robustness to common image corruptions.
Authors: Vasile Marian, Yong-Bin Kang, Alexander Buddery
Abstract: Object-centric image generation is important in settings with few labeled examples, including pedestrian analysis in smart-city scenes, traffic-sign inspection, and domain-specific object detection. Synthetic images are most useful for training and evaluation when datasets preserve object structure, bounding boxes, visual diversity, and realistic context. Existing image datasets usually target classification, detection, or scene understanding rather than controlled object-centric generation and augmentation with limited class-specific data. We present a shareable collection of three object-centric dataset resources: Cityscapes-Pedestrian, TrafficSigns, and COCO PottedPlant. The collection standardizes 256-by-256 object-centric crops and bounding-box annotations across three regimes: dense pedestrian scenes with privacy blur and occlusion, cleaner high-contrast traffic signs, and context-diverse potted-plant scenes. The release contains 3,009 TrafficSigns samples, 2,156 Cityscapes-Pedestrian manifest records, and 7,679 COCO PottedPlant manifest records. The larger COCO-derived manifest preserves contextual and multi-instance diversity, while equal-size subsets can be drawn with a fixed random seed for controlled comparisons. The release provides direct TrafficSigns data where redistribution is permitted, together with scripts, manifests, box-level annotation tables, checksums, and reconstruction documentation for the Cityscapes- and COCO-derived subsets. It is available through the Latzi/object-centric-low-data-datasets GitHub repository and Zenodo DOI 10.5281/zenodo.20573001. The collection supports label and split inspection, subset creation, reconstruction from upstream data, and evaluation of object-centric image generation or synthetic-data augmentation methods on shared records.
Authors: Jiho Choi, Sang Jun Lee
Abstract: Remote photoplethysmography (rPPG) is a camera-based technique for measuring physiological signals, particularly cardiac activity. From the remotely measured signals, heart rate can be estimated, which is crucial for health monitoring. In this study, we investigate a driver health monitoring system based on remote heart rate estimation. However, driving environments represent uncontrolled settings where videos are subject to varying illumination conditions and frequent head movements. We introduce MS-rPPG, a multi-spectral framework that combines RGB with near-infrared (NIR) face video to alleviate rPPG estimation under challenging driving conditions. To combine the complementary features from two spectral videos, we propose a cross-spectral linear modulation (CSLM) strategy based on frequency-domain analysis. Moreover, we introduce MS-Mamba, a novel state space model designed to effectively model long-range temporal dependencies while jointly capturing cross-channel interactions between multi-spectral features. We collected a real-world dataset called MS-Drive, which was recorded from 50 participants while driving the vehicle. The proposed method was evaluated on the MR-NIRP Car dataset and MS-Drive datasets. The experimental results indicate that MS-rPPG shows better robustness and heart rate estimation accuracy than previous methods, highlighting its promise for driver health monitoring. The codes are available at github.com/ziiho08/MS-rPPG.
Authors: Jeff Brown, Tim Farkas, Gleb Razgar, Edward S. Boyden
Abstract: Proofreading--correcting segmentation errors in 3D brain reconstructions--is the rate-limiting step in synapse-resolution connectomics. We release ConnectomeBench2, a unified multi-species dataset of over 716,485 expert-labeled proofreading decisions with >4,500,000 associated images spanning four major open connectomes (mouse, human, zebrafish, fly), spanning both split and merge error correction. Trained on this dataset, a single Vision Transformer with shared encoders for mesh geometry and electron microscopy reaches human-level accuracy across species for split error correction and merge error identification, with performance scaling with data size and modality. Beyond accuracy, we show that the model is well-calibrated within distribution, that measures of distribution distance predict where calibration and accuracy will degrade on unseen data, and that connectomics-specific pretraining and active learning-based sample selection show potential to substantially reduce the labeling effort needed to extend to new species and brain regions. The benchmark provides the infrastructure to train and evaluate increasingly capable vision models for connectomic proofreading. Data and code availability. The ConnectomeBench2 dataset is released on Hugging Face at https://huggingface.co/datasets/jeffbbrown2/ConnectomeBench2. The accompanying codebase is available on GitHub at https://github.com/timfarkas/ConnectomeBench2.
URLs: https://huggingface.co/datasets/jeffbbrown2/ConnectomeBench2., https://github.com/timfarkas/ConnectomeBench2.
Authors: Di Dai, Bo Liu, Youcheng Li, Haojun Yu, Zhouhang Bian, Quanlin Wu, Dong Wang, Sichen Meng, Hongye Xuan, Zijie Lan, Shenda Hong, Liwei Wang
Abstract: Mammography is an essential tool for breast cancer detection, with millions of examinations conducted annually. However, publicly available high-quality mammography datasets for AI development remain limited in both scale and annotation richness, particularly regarding pathological subtype coverage and structured diagnostic reasoning annotations. In this paper, we present MammoExpert, the first mammography dataset with Chain-of-Thought reasoning annotations across three diagnostic phases: (i) primal observation, (ii) factual assessment, and (iii) diagnostic synthesis. Comprising 2,379 mammography images covering 67 WHO-classified histopathology subtypes, each exam provides 42 radiographic features annotated by nine senior radiologists. We evaluate its performance on the breast lesion classification task, demonstrating superior accuracy and reasonability compared to existing classification models. Combining public dataset CBIS-DDSM with MammoExpert yields 7.1\% classification accuracy improvement, while the training model to learn CoT reasoning achieves another 4\% gain on the MammoExpert test set. Similar improvements are observed on INBreast and Vindr datasets, where the full approach yields accuracy gains of 6.9\% and 6.7\%, respectively. MammoExpert can serve as a benchmark for interpretable breast lesion diagnosis through explicit CoT reasoning.
Authors: Dongseok Shim, Julian Tanke, Kengo Uchida, Christian Simon, Koichi Saito, Takashi Shibuya, Shusuke Takahashi, Yuki Mitsufuji
Abstract: Human motion generation has been widely studied across diverse input modalities, text, music, and video, and recent efforts have unified these into single multimodal frameworks. However, while morphological factors such as gender and body shape are known to produce distinct kinematic signatures, no existing unified framework incorporates this into generation, treating all subjects as morphologically equivalent. We present Odoriko, the first unified multimodal motion generation framework that reflects subject bio-morphological information directly in synthesized motion output. Rather than averaging over subject variation, Odoriko generates motion that is consistent with who is moving, not just what they are asked to do, across text, music, and video conditions within a single model. When explicit morphological information is unavailable, Odoriko additionally recovers subject morphology alongside motion, unifying estimation and generation in one framework. Extensive experiments across text-to-motion, music-to-dance, and video-to-motion benchmarks demonstrate that Odoriko matches or exceeds prior specialized models on standard metrics, while enabling morphology-consistent generation that no existing unified framework supports.
Authors: Kahim Wong, Kemou Li, Yiming Chen, Haiwei Wu, Jiantao Zhou
Abstract: AI-assisted image editing threatens trust in financial, legal, and identity records. The GenText-Forensics Challenge at ACM MM 2026 addresses this by requiring structured forensic reports, in which integrating detection, pixel-level localization, and natural language explanation for multilingual text-centric forgery images. We present SEED, a modular system with three components. First, a similarity-guided pipeline augments training with diverse synthetic forgeries. Second, a single ViT, built on DINOv3 with LoRA adaptation, jointly performs detection and pixel-level localization while preserving pre-trained priors with minimal trainable parameters. Third, an evolving harness takes the detector's predictions and generates a complete forensic report via an MLLM, iteratively improved through a proposer-evaluator loop optimizing report quality. SEED ranked 3rd in the GenText-Forensics Challenge. Code and data are available at https://github.com/KahimWong/GenText-Forensics-3rd-Place.
URLs: https://github.com/KahimWong/GenText-Forensics-3rd-Place.
Authors: Jiaming He, Jiashu Zhang, Guanyu Hou, Shuhan Ye, Hanwei Zhu, Yi Yu, Xudong Jiang
Abstract: Text-to-video (T2V) diffusion models have made it increasingly easy to synthesize realistic and temporally coherent videos, while recent personalization techniques allow such models to imitate a specific subject, style, or motion pattern from only a few reference clips. This capability creates a new data-misuse risk: videos shared online can be collected and used for unauthorized T2V fine-tuning. Existing protective perturbations are mainly designed for image recognition or text-to-image personalization, and therefore focus on corrupting static appearance cues rather than the temporal denoising dynamics that make video personalization possible. To address this gap, we introduce ChronoLock, the first proactive protection framework that makes released videos difficult to exploit for unauthorized T2V personalization. ChronoLock targets the motion-learning process directly by optimizing bounded perturbations over temporal denoising trajectories. It first disrupts intra-chunk temporal adaptation with a diffusion objective that combines fitting error, frame-relative denoising relations, and adjacent-frame variation, and then enlarges inter-chunk boundary mismatch to weaken long-range motion continuity. Transformation-sampled updates further improve robustness to common preprocessing operations.Experiments on UCF Sports and HMDB51 with popular T2V backbones and personalization scheme show that ChronoLock effectively reduces motion imitation under automatic metrics and human evaluation.
Authors: Joohyeok Kim, Taejin Jeong, Jinyeong Kim, Seong Jae Hwang
Abstract: The high cost of spatial transcriptomics (ST) has driven extensive studies into predicting gene expression directly from H&E histology images. However, this prediction task faces an inherent limitation, as tissue morphology alone provides insufficient information to fully resolve underlying gene expression. To address this limitation, a recent study leverages partial gene expression to guide the prediction process alongside histology images. Building on this paradigm, we approach the prediction task as a spatial imputation problem, employing a Masked Autoencoder (MAE) to utilize a small fraction of gene expression as genetic anchors for inferring whole-slide gene expression profiles. Specifically, we propose a bio-saliency score and a learning-to-rank strategy to adaptively identify the most informative spots within the tissue. Based on these identified spots, our framework selects contiguous regions as genetic anchors to ensure suitability for real-world ST profiling hardware. To effectively leverage these anchors, we design a cross-modal joint encoder that integrates visual and genetic modalities. By aligning the selected anchors with their corresponding visual features via contrastive learning, the encoder generates robust joint representations to accurately predict gene expression across the whole slide. Notably, our framework consistently surpasses existing methods in both histology-only prediction and spatial imputation, achieving superior accuracy even without genetic anchors and further excelling with as little as 10% transcriptomic coverage. Our code is available at https://github.com/Kyyle2114/CAMMST.
Authors: Zhe Shuai, Xiaopeng Xie, Yikun Zeng
Abstract: Video world models are increasingly used in autonomous driving to forecast future scene evolution and provide future-aware spatio-temporal representations for downstream action prediction. In perception-to-action pipelines, these representations can directly influence ego-vehicle waypoint planning, making the learned future dynamics a critical security-sensitive component. Despite their promise, the training-time security risks of autonomous-driving video world models remain largely unexplored. We present BadDreamer, a transferable spatio-temporal backdoor attack that targets the perception side of this pipeline. Unlike conventional backdoors that manipulate image labels, prompt outputs, or action supervision, BadDreamer poisons the learned transition dynamics of a video world model. It constructs trigger-erasure sequences in which an oncoming yellow delivery rider is visible in the observed context frames but erased from the future frames. After fine-tuning on a small fraction of such sequences, the compromised world model learns a hidden conditional association: when the physical trigger appears, it hallucinates a future where the rider disappears and the road appears clear. We further show that this corrupted future-aware representation can transfer to the downstream action module without directly modifying ego-trajectory labels, inducing unsafe non-evasive waypoint predictions. Our experiments instantiate this attack on a representative open-source perception-to-action pipeline, revealing a representation-level safety risk in autonomous-driving video world models and highlighting the need for backdoor-aware validation beyond clean generation quality.
Authors: Xiangyu Li, Ran Su
Abstract: Matched multi-omics can improve WSI-based biomarker and prognosis prediction, but most existing pipelines use omics as a paral lel feature stream or textual context rather than as an explicit retrieval constraint. HERO asks whether observed omics can be a testable mor phology hypothesis: a sparse pathway-to-morphology prior maps DNA methylation and miRNA into a K-dimensional intent vector m (K=16), TF-IDF retrieval over structured 10 captions selects endpoint-relevant regions, and a cosine gate c=cos(m,v) triggers deterministic deficit driven repair when c<{\tau}c. This closed-loop design bounds VLM calls, reduces reliance on embedding-based semantic matching, and makes every retrieval and verification step lexically auditable. On TCGA-BRCA (930WSIs, patient-level 5-fold CV), HERO sets new state-of-the-art across ER, PR, HER2, subtype, and risk prediction, outperforming both multimodal fusion and VLM-based baselines.
Authors: Han Jang, Junhyeok Lee, Songsoo Kim, Chae Young Lim, Hyeonjin Goh, Heeseong Eum, Kyu Sung Choi
Abstract: Medical Vision-Language Models (Med-VLMs) achieve strong expert-level performance, yet their ability to generate patient-accessible descriptions remains underexplored. With the 21st Century Cures Act now mandating immediate patient access to diagnostic imaging results, evaluating whether Med-VLMs can bridge this Expert-Lay Gap is both urgent and clinically consequential for patient education and shared decision-making. To this end, we introduce MedLayXPlain, the first large-scale multimodal benchmark and evaluation framework for Medical Lay Language Generation (MLLG). MedLayXPlain-122K provides 122,789 region-grounded samples across 8 imaging modalities from 12 publicly available source datasets, each comprising a medical image with paired expert and lay captions anchored in a three-level Unified Medical Language System (UMLS) ontology hierarchy spanning 7 semantic groups, 43 semantic types, and 2,411 medical concepts. Lay captions are constructed via Hierarchical Ontology-Verified Refinement (HOVER), a three-step pipeline combining patient-centric vocabulary mapping, LLM-based constrained rewriting, and cross-model visual verification to enforce semantic equivalence while preventing hallucination. We further introduce MedLayEval, a lightweight 3B evaluator distilled from a 27B verifier that scores expert-lay alignment across five clinically grounded attributes, addressing the poor correlation between standard NLG metrics and clinical judgment. Benchmarking 33 VLMs on MedLayXPlain-122K reveals a systematic Expert-Lay Gap: medical VLMs achieve strong expert captioning but suffer significant lay-register degradation, while general-purpose VLMs produce more accessible language yet lack clinical precision, confirming that neither current paradigm adequately serves patient-facing communication.
Authors: Sergio Lanza, Jae Hee Lee, Stefan Wermter
Abstract: Vision Language Models (VLMs) have demonstrated impressive performance in tasks requiring joint understanding of images and text, such as image captioning and Visual Question Answering (VQA), but our understanding of their internal processes remains limited. Recently, Sparse Autoencoders (SAEs) have emerged as a promising tool to support the interpretation of concepts encoded in VLMs. However, most SAE-based approaches focus only on textual or visual concepts separately, ignoring multimodal concepts. This limitation hinders a comprehensive understanding of VLMs, since concepts that integrate both modalities can be misclassified. Moreover, previous visual approaches often produce low-quality visual concept descriptions that are vague or incomplete, limiting their usefulness for understanding model reasoning. We propose a framework based on SAEs to extract and analyze visual, textual, and multimodal concepts from VLMs. For each neuron, we propose a candidate human-interpretable concept and compute the alignment between the concept and the dataset samples using cosine similarity scores. Experiments on a VQA dataset (LLaVA-NeXT) demonstrate that our framework improves visual concept quality by up to 45\% compared to existing SAE-based methods, while maintaining high textual concept quality and enabling systematic identification of multimodal concepts. This work contributes new insights into the conceptual space of VLMs, providing a structured approach to distinguish between visual, textual, and multimodal concepts. The code is available at https://github.com/PHDLanza/Multidata_SAE
Authors: Houssam El Mir
Abstract: Pedestrian attribute recognition (PAR) assigns semantic labels to detected pedestrians and is useful in surveillance, video retrieval, and human-centered graphics applications. This paper presents a two-stage framework in which YOLOv8n detects pedestrians and ResNet18-based models classify gender, estimate apparent age, and predict 61 binary attributes from each pedestrian crop. PETA and PA-100K are combined through semantic attribute mapping, producing a unified training corpus of more than 100,000 pedestrian images while retaining the PETA attribute space. On the reported test splits, the system obtains 99.89% gender classification accuracy, a 4.23-year apparent-age mean absolute error, and 89.96% multi-attribute accuracy with a 36.32% macro F1-score and 58.80% micro F1-score. Runtime measurements indicate 25-30 FPS on an NVIDIA RTX 5060 GPU. The results show that a lightweight detector-classifier pipeline can support real-time PAR, while low macro F1 indicates that rare attributes remain challenging.
Authors: JungHoon Sung, Boeun Kim, Chu Xin, Hyung Jin Chang, ChangHo Kim, Sang-Il Choi, Younggeun Choi
Abstract: To generate natural and accurate sentence-level sign language, synthesizing the "gloss", the fundamental semantic unit, is essential. However, most current sign-language production (SLP) methods generate entire sequences at once. While this end-to-end approach is often efficient, it is prone to temporal drift and hand motion blur as sentences get longer, and fails to accurately control individual glosses. In this paper, we propose the Context-aware Gloss-wise AutoRegressive Diffusion model (GARD), a gloss-wise diffusion framework that models coarticulation by conditioning on both semantic (linguistic) and kinematic (motion) contexts. To ensure natural continuity between gloss motions, GARD introduces two additional strategies: i) Inter-Gloss Transition Guidance, which applies gradient-based guidance to kinematically align inter-gloss boundaries and ensure seamless pose consistency. ii) Global Motion Harmonizer, refining the entire gloss motion sequence based on the boundary poses adjusted by Inter-Gloss Transition Guidance. Extensive experiments on Phoenix-T and CSL-Daily datasets demonstrate that GARD achieves superior performance over existing SLP methods in terms of both linguistic accuracy and motion similarity.
Authors: Jijian Zhao
Abstract: 3D Gaussian Splatting achieves exceptional real-time rendering, but its substantial computational and storage demands hinder widespread deployment. Existing accelerated paradigms often aggressively prune primitives for rapid convergence, causing severe loss of high-frequency details. To address this, we tackle the fundamental problem of achieving both exceptional rendering quality and ultra-fast reconstruction speed. In this paper, we propose ACE-GS, a progressive optimization framework tailored for accurate, compressed, and efficient scene representation. We realize that precise primitive management is the key to breaking this trade-off. Therefore, we first design a momentum consistency-guided densification strategy, strictly constraining primitive growth onto authentic geometric manifolds to avoid computational waste while significantly accelerating convergence. Building upon this efficient initialization, we deploy a statistical sensitivity-driven sparsification mechanism to precisely prune redundant primitives, yielding a further compressed footprint. Finally, to thoroughly compensate for the risk of micro-structure loss caused by the aforementioned strict primitive control, we introduce a cross-dimensional residual frequency compensation scheme that explicitly back-injects high-frequency error energy into primitive attributes, perfectly restoring sharp geometric details. Extensive experiments validate our superiority. While maintaining a highly compact scene representation, our system achieves up to 3.7 times training acceleration against the rapid framework Speedy-Splat. Requiring only 3 to 5 minutes to converge, ACE-GS secures the highest structural similarity and achieves a peak PSNR improvement of up to 0.89 dB over the original 3DGS, establishing a new benchmark for ultra-fast and high-fidelity novel view synthesis.
Authors: Talha Ilyas, Deval Mehta, Zongyuan Ge
Abstract: Video-based seizure detection is essential for the management of epilepsy patients, offering a non-invasive complement to electroencephalography. While several deep learning approaches have been developed for video-based seizure detection, none are inherently interpretable, limiting their adoption and translation into clinical practice. We present, to our knowledge, the first exploration of a neurosymbolic framework for video-based seizure detection that directly addresses this gap. Our approach (1) extracts patient-centric skeleton sequences from epilepsy monitoring units via a prompt-guided foundation model, (2) predicts binary spatio-temporal concept activations grounded in clinical motor semiology guidelines, and (3) composes them via differentiable logic into interpretable Boolean rules with auditable contributions. Furthermore, to mitigate false positives arising from the traditional binary formulation (seizure vs.\ non-seizure), we sub-classify non-seizure segments into clinically relevant normal activities, providing the model with fine-grained discriminative supervision. Evaluated on two public seizure video benchmarks, our framework achieves 89.78% sensitivity with 0.06 false detections per hour on SAHZU and 85.27%,0.09 on IEEE, while producing complete three-level interpretability: every prediction decomposes into which motor primitives were detected, how they were logically composed, and how much each rule contributed to the clinical decision. We publicly release all annotations, extracted pose sequences, our data pipeline and code, https://github.com/Mr-TalhaIlyas/CDSD/.
Authors: Ali Saeidan
Abstract: Early detection of aphid infestation in crops is essential for preventing yield loss and reducing unnecessary pesticide use. Hyperspectral imaging combined with Spectral Information Divergence (SID) analysis offers a non-destructive approach for monitoring plant health; however, deep learning methods applied to hyperspectral data are often limited by small dataset sizes. In this study, a data-efficient generative adversarial network (FastGAN) was employed to augment a hyperspectral SID dataset of faba bean leaves containing healthy and aphid-infested samples. The trained generator produced 10,000 synthetic images preserving structural and spectral characteristics of real samples. Image quality was evaluated using Frechet Inception Distance (FID), demonstrating stable convergence and realistic reconstruction of leaf morphology and infestation patterns. The augmented dataset was used to train four classification architectures: VGG16, ResNet-50, EfficientNet, and Vision Transformer (ViT). Results showed that dataset augmentation significantly improved classification robustness, with performance progressively increasing from classical convolutional networks to transformer-based models. The ViT model achieved the highest accuracy and F1-scores, while EfficientNet provided strong balanced performance and ResNet-50 showed moderate improvements over VGG16. Confusion matrix analysis confirmed reduced false negatives and improved disease detection when using advanced architectures. The findings demonstrate that FastGAN-based augmentation effectively enhances hyperspectral plant disease classification and that transformer-based models provide the most reliable discrimination between healthy and infested leaves.
Authors: Mahmoud Hazem, Karim Hammoudi
Abstract: Nowadays, more and more disasters of different natures are appearing. Several disaster assessment approaches have been developed in order to identify damaged areas from aerial images. These damaged areas contain rich material that could be recycled towards several ecological purposes. In this paper, we present a lightweight approach that permits the efficient detection of recyclable material. Experimental results show the potential of the proposed approach towards localizing recyclable materials. Accordingly, we provide a rare dataset of material images that we labeled towards supporting the development of recyclable material detectors. The dataset of labeled material images is publicly available at: anonymous.
Authors: Nidhal Eddine Chenni, Arunkumar Rathinam, Djamila Aouada
Abstract: Unsupervised domain adaptation (UDA) enables robust transfer of knowledge from simulated to real environments while exploiting a subset of unlabeled target data to improve real-world performance. Existing UDA methods for Object pose estimation often rely on global feature matching, multi-stage larger frameworks, or image translation pipelines, which tend to overlook the pose-specific information embedded in feature representations. To bridge this limitation, we introduce CAPLR that targets the adaptation of pose-sensitive features in localized regions, ensuring that domain alignment preserves the geometric cues essential for accurate pose estimation. CAPLR achieves UDA with three key components: (1) Efficient Cross-Domain Pairing strategy leveraging intermediate features to identify pose similar image pairs across domains without supervision; (2) Contrastive Alignment to perform feature alignment at localised regions in both intermediate and task-specific representations; and (3) Consistency-Based Pseudo-Label Refinement to improve reliability by encouraging stable target predictions. Extensive experiments demonstrate that CAPLR achieves state-of-the-art performance across multiple well-known object pose estimation benchmarks featuring diverse and challenging scenarios.
Authors: Adnan Mustafic, Halim Benhabiles, Adnane Cabani, Kristhian Andr\'e Oliveira Aguilar, Romain Amigon, Cl\'ement Bardin, Chiara Bentifece, Marin Boehm, K\'evin Bouchard, Laura Burattini, Diedre Carmo, Fahima Idiri, Matthis Lahargoue, Ilaria Marcantoni, Hicham Messaoudi, Cyril Meyer, Farid Meziane, L\'eon Morales, Let\'icia Rittner, Agnese Sbrollini, L\'eonard Zipper, Karim Hammoudi
Abstract: We propose NoduLoCC2026, a challenge on lung nodule detection and localization in chest X-ray images. We have provided a dataset for both tasks and received submissions from 5 international teams. The participating teams' solutions are presented in this work along with results on an external dataset used for testing. Proposed methods show good performance on the classification task. The best method shows a balanced accuracy score of 0.72 and AUC-ROC of 0.79. We highlight the limitations of current approaches for the localization task, with the best approach having predicted the correct number of nodules on 53\% of the test images with a median distance of 12.83mm, showing that it is a more challenging task than the first one. The challenge website is available via https://gt-i2mdp.github.io/website/nodule_challenge.html.
URLs: https://gt-i2mdp.github.io/website/nodule_challenge.html.
Authors: Marwane Hariat, Gianni Franchi, David Filliat, Antoine Manzanera
Abstract: We present Casper3D, a lightweight probabilistic framework for converting noisy multi-view 2D foundation-model embeddings into a latent 3D semantic representation. We model view-level semantic features as noisy observations of an underlying 3D semantic state and infer this state with a set-based variational model that incorporates relative pose during multi-view reasoning. Casper3D is trained by predicting held-out semantic observations from novel viewpoints, while remaining aligned with visual and text semantic spaces for open-vocabulary 3D understanding. The framework is backbone-agnostic and applies to both language-aligned and self-supervised embeddings. Experiments show that Casper3D produces more stable 3D semantics than simple multi-view pooling, especially in ambiguous and noisy settings.
Authors: Zheng Zhang, Lihe Yang, Tianyu Yang, Chaohui Yu, Yixing Lao, Xiaoyang Guo, Biao Gong, Fan Wang, Hengshuang Zhao
Abstract: We present SCOPE (Scale-Consistent One-Pass Estimation of 3D Geometry), a novel approach for estimating 3D geometry from extended monocular video sequences, where existing methods struggle to maintain both geometric accuracy and temporal consistency across hundreds of frames. Our approach generates affine-invariant 3D point maps with shared parameters across entire sequences, enabling consistent scale-invariant representations. We introduce three key innovations: viewpoint-invariant geometry aligning multi-perspective points in a unified reference frame; appearance-invariant learning enforcing consistency across exponential timescales; and frequency-modulated positioning enabling extrapolation to sequences vastly exceeding training length. Experiments across diverse datasets demonstrate significant improvements, reducing relative point map error by 24.2% and temporal alignment error by 34.9% on ScanNet compared to state-of-the-art methods. Our approach handles challenging scenarios with complex camera trajectories and lighting variations while efficiently processing extended sequences in a single pass. Project page: https://scope3d.github.io/.
Authors: Damianos Galanopoulos, Vasileios Mezaris
Abstract: This paper introduces the CERTH-ITI solution for the MediaEval NewsImages 2026 challenge, which focuses on generating images related to news headlines. Inspired by the Actor-Critic paradigm in reinforcement learning, we present a test-time, model-agnostic Actor-Critic Image Generation approach (ACIG). ACIG generates prompts for image creation, produces the images, evaluates the generated results, and if needed refines the image generation prompts accordingly in a feedback loop. ACIG achieved the best results in the NewsImages 2026 challenge, according to the challenge's leaderboard.
Authors: Vandita Shukla, Kilian Meier, Lucie Laporte-Devylder, Camille Rondeau Saint-Jean, Jenna M. Kline, Blair R. Costelloe, Devis Tuia, Fabio Remondino, Benjamin Risse
Abstract: We introduce WildBox, a dataset and benchmark for monocular 3D detection of wildlife from drone video, comprising 237,505 3D bounding box annotations across seven African savanna species grouped into six benchmark classes. Annotations follow a KITTI/Omni3D-compatible format in a per-segment scale-normalised camera frame, with instance identities maintained across each segment. We evaluate two open-vocabulary monocular 3D architectures, OVMono3D-LIFT and DetAny3D, under zero-shot, ground-truth 2D box prompt, and supervised fine-tuning protocols. Open-vocabulary 2D foundation models provide usable zero-shot wildlife localisation (50.55 AP@50), but zero-shot 3D detection collapses to 0.00 AP across both architectures and every 2D-input condition tested, including ground-truth 2D box prompts, thus isolating the failure to the 3D stage. Fine-tuning on WildBox recovers performance to 8.68 +/- 0.47 AP-BEV@0.50 and 13.17 +/- 0.69 AP3D macro. Depth contributes 84% of normalised Hausdorff distance after fine-tuning and over 99% in zero-shot, identifying monocular aerial depth as the dominant open problem in this regime. A coarse-to-fine curriculum, i.e. pretraining on a merged zebra class before fine-tuning on the Grevy's/plains split, improves macro 3D performance with less total compute, with the largest gains on the two zebra subclasses. WildBox is released with video-level splits, evaluation code, and baseline checkpoints to enable progress in 3D wildlife perception from drone video.
Authors: Asl{\i} \c{C}elik
Abstract: Supervised video pretraining is a common transfer learning practice for improving downstream action recognition performance. However, it requires large-scale labeled source datasets, and the effectiveness of the learned initialization is influenced by the similarity between the source and target domains. Constructing such labeled pretraining datasets for different target domains is costly and difficult to scale. To address these limitations, this study proposes a label-efficient video learning framework that combines annotation-free video pretraining with target-label-set-aware fine-tuning. During pretraining, a vision-language model (VLM) generates textual descriptions of unlabeled videos, which are processed to construct an interpretable semantic pseudo-label space. A frozen video-language model then produces zero-shot soft target distributions over this space, allowing a student video encoder to learn semantically rich representations without manual source annotations. During downstream adaptation, target-label-set-aware fine-tuning combines supervised learning from labeled target videos with zero-shot distillation over the actual target label set, helping preserve VLM-derived semantic guidance while adapting the pretrained encoder to the target task. Experiments on UCF101 and HMDB51 show that the proposed framework outperforms the compared semi-supervised video action recognition methods across all evaluated limited-label regimes. Moreover, the annotation-free pretraining stage learns transferable representations that provide an effective initialization for full-data fine-tuning, despite relying on a comparatively modest unlabeled pretraining pool.
Authors: Nichula Wasalathilaka, Abhijit Das, Imran Razzak, Dwarikanath Mahapatra
Abstract: Medical image re-identification (MedReID) enables longitudinal patient linkage but remains vulnerable to shortcut learning and often produces decisions that clinicians cannot audit against named anatomy. We propose Graph-of-Differences (GoD), which grounds identity comparisons in explicit anatomical structure. Each image is represented as an anatomy graph whose nodes correspond to named anatomical regions; given an image pair, soft node correspondence is established, and differences are computed over matched anatomy. A graph-level difference alignment objective ties these anatomy-matched differences to the global backbone difference, ensuring the retrieval signal is anchored in homologous structures rather than arbitrary spatial tokens. Explanations are defined over named graph nodes and quantitatively audited via node insertion/deletion tests, replacing unstable pixel heatmaps with verifiable structure-level evidence. On internal benchmarks, GoD improves Rank-1 by +7.1 pp on fundus and +3.1 pp on CXR over a strong frozen-backbone baseline, with further gains on zero-shot external transfers confirming that anatomy grounding improves both accuracy and generalization. Code is available at https://github.com/GenMI-Lab/GoD.git.
Authors: Guangcheng Chen, Lihuang Fang, Huaqi Tao, Yicheng He, Li He, Hong Zhang
Abstract: Recent indoor occupancy prediction methods adopt Gaussian primitives as a sparse 3D representation for computational efficiency. However, their training relies on voxel classification, which imposes only local constraints and lacks global supervision on the distribution of the primitives. Therefore, they inevitably predict spurious primitives in empty regions, undermining both representational and computational efficiency. To address this, we propose Feed-forward Likelihood Maximization (FLM), a novel framework that reformulates occupancy prediction as voxel distribution estimation. In FLM, a network is trained to predict a mixture model that maximizes the likelihood over ground-truth occupied voxels in a feed-forward manner. To enable end-to-end training of networks and voxelization of a standard mixture model, we define mixture weights as normalized primitive volumes to implicitly enforce simplex constraints and derive novel voxelization formulas. Based on FLM, our FLM-Occ, a novel method that is capable of relocating randomly initialized primitives over long distances to model a scene. On Occ-ScanNet, FLM-Occ achieves superior accuracy using only 32 superquadrics, 2.7% of the prior SoTA, while running 3.7 times faster.
Authors: Caio Silva
Abstract: Deep learning in computational microscopy is severely constrained by the scarcity of densely annotated datasets. While synthetic data generation has bridged this gap in macroscopic computer vision, traditional graphics engines rely on geometric ray-tracing, failing to capture the micro-optical phenomena required for microscopy. Conversely, while wave-optics formulations exist, rendering them computationally tractable at the scale required for deep learning remains a massive systems challenge. To address this, we introduce the Optical Synthetic Object Generator (OSOG), a high-performance, fully differentiable forward-modeling engine. Drawing on established physical models of diffraction and phase retardation, OSOG maps continuous Optical Path Difference (OPD) calculations into a highly optimized, PyTorch-native Structure-of-Arrays (SoA) architecture. We validate this computational framework across three axes: First, object detection models (YOLOv11-OBB) trained purely on OSOG-generated data achieve robust zero-shot transfer to real-world highly occluded Lysozyme micrographs. Second, we introduce DiffOSOG, demonstrating that the engine's end-to-end differentiability allows for the exact recovery of continuous optical parameters via curriculum-guided inverse rendering. Finally, OSOG bypasses the $\mathcal{O}(N)$ bottlenecks of sequential ray-tracing, demonstrating sub-linear scaling by synthesizing 40,000 complex wave-optic particles in under 50 milliseconds (\>20 FPS). By providing a fast, scalable, and physically grounded tensor pipeline, OSOG enables true real-time, on-the-fly dataset generation.
Authors: Dwarikanath Mahapatra, Abhijit Das, Behzad Bozorgtabar, Zongyuan Ge, Sudipta Roy, Deepak Nayak, Mauricio Reyes, Imran Razzak
Abstract: Multimodal medical imaging fuses complementary anatomical and functional information, yet modalities frequently disagree in pathologically heterogeneous regions. Current segmentation models handle this in one of two inadequate ways: deterministic fusion that averages away disagreement, or post-hoc uncertainty estimation decoupled from the fusion process that produces it. Both obscure the clinically critical question: why is this prediction unreliable? We present EnTrust, a framework that treats inter-modal conflict as the primary source of predictive uncertainty. Our EnFuse module decomposes multimodal features into three disentangled components: shared anatomical consensus (F_c), modality-specific cues (F_{u,m}), and spatially localized conflict signals (F_{cf}), with independence enforced via a cross-covariance objective. This structured decomposition conditions SegDiff, a diffusion-based generative segmentation model whose sampled hypotheses diverge specifically in regions of modal disagreement. TrustMap then translates this hypothesis divergence into calibrated, pixel-wise uncertainty using ensemble entropy, conflict-guided perturbation probing, and a learned calibration head, enabling clinicians to understand not only where predictions are uncertain, but why. Across four benchmarks spanning brain, cardiac, lesion, and oncology domains, EnTrust achieves state-of-the-art segmentation accuracy while reducing calibration error by 40% compared to the strongest baseline. Notably, it outperforms 5x deep ensembles using a single model at roughly half the memory footprint. Code and checkpoints are available at https://github.com/GenMI-Lab/EnTrust.git.
Authors: Arlindo Luciano Tulumba Roberto, Hyungjoon Kim
Abstract: Despite recent progress in Vision-Language Models (VLMs), mixed-domain image-caption datasets for both general-purpose and CCTV-based video surveillance systems remain limited. To address this gap, we introduce a large-scale multimodal dataset comprising 141,364 images, 981,947 image-level captions, 1,742,264 region-level captions, and 1,391,779 bounding box annotations. Each image is associated with an average of seven image-level captions describing different aspects of the overall scene, as well as seven region-level captions for each annotated bounding box. These complementary caption types are designed to help VLMs learn fine-grained visual attributes, including object categories, estimated sizes, colors, actions, states, and surrounding environmental context. We demonstrate the effectiveness of the dataset on two important downstream tasks: image captioning and object detection. Experimental results show that lightweight VLMs, including SmolVLM-256M-Instruct, BLIP, BLIP2, and Qwen2.5-VL 3B-Instruct, can be effectively fine-tuned using our dataset. Our dataset and code are publicly available at https://zenodo.org/records/20418601.
Authors: Yuxun Qu, Minyu Zhou, Yongqiang Tang, Chenyang Zhang, Wensheng Zhang
Abstract: Generalized Category Discovery (GCD) aims to classify old categories and discover new ones from unlabeled data. Recent multi-modal approaches introduce retrieved or synthesized texts into a dual-branch architecture to provide semantic cues complementary to visual features. However, the cross-modal synergy in existing dual-branch methods remains coarse and incomplete: the two modalities are encoded independently with the bias and noise in the derived text left unaddressed during encoding, and existing mutual learning strategies operate only on global class-level anchors, lacking fine-grained relational supervision. To address these limitations, we propose the Synergistic Dual-Branch Adaptation (SDBA) framework, which serves as a plug-and-play enhancement compatible with existing dual-branch methods such as GET and TextGCD. SDBA comprises two components: the cross-modal synergistic adapter inserts lightweight adapters into both branches and further injects visual information into the text adapter at each encoder layer to enhance text feature learning during encoding; the neighborhood mutual learning module enforces consistent local neighborhood distributions between the two branches via bidirectional KL divergence, providing fine-grained relational supervision for both old and new classes. Extensive experiments on six benchmarks demonstrate state-of-the-art performance, and consistent improvements on different baselines validate the broad scalability of the proposed framework.
Authors: David Pascual-Hern\'andez, Roberto Calvo-Palomino, Inmaculada Mora-Jim\'enez, Jose Mar\'ia Ca\~nas-Plaza
Abstract: In this report, we present our submission to the GOOSE 2D Fine-Grained Semantic Segmentation Challenge, organized as part of the Workshop on Field Robotics at ICRA 2026. The challenge combines data from the GOOSE and GOOSE-Ex datasets, which comprise more than 13k images captured from 4 distinct camera setups, annotated using a hierarchical taxonomy of 56 fine-grained classes and 11 broader categories. Starting from SegFormer as a baseline, we progressively improve segmentation performance through increased training crop sizes, a transition to the query-based Mask2Former architecture, and test-time augmentation. Our experiments show that query-based segmentation significantly outperforms the baseline model. Furthermore, increasing the crop size used during training yields substantial gains, highlighting the relevance of preserving scene context for fine-grained semantic disambiguation. Our final submission, using test-time augmentation, achieves an mIoU of 69.6% on the challenge test set, providing a strong baseline for fine-grained semantic segmentation in outdoor environments. To facilitate reproducibility and future research, code and weights will be made publicly available at https://github.com/RoboticsLabURJC/outdoor-fine-grained-segmentation .
URLs: https://github.com/RoboticsLabURJC/outdoor-fine-grained-segmentation
Authors: Tom\'as Lima, Daniel Nov\'ak, Eduard Bak\v{s}tein
Abstract: Accurate segmentation of subcortical regions is critical for neurosurgical planning and functional research. Most automated methods rely on template space coregistration, which may compromise patient-specific accuracy, particularly in small structures. We identify a need to evaluate whether native space approaches offer a measurable advantage, which we evaluate in the context of movement disorders. We developed two UNet-based segmentation pipelines of the Subthalamic Nucleus (STN) - a common surgical target in Parkinson's Disease - and the neighbouring Red Nucleus (RN) and Substantia Nigra (SN). We collected 7T and 3T MRI data from five public datasets. The pipelines were evaluated in the native-space against manual labels. We further investigated the effect of the template resolution. Motivated by the hypothesis that models may better learn target boundaries in higher field, we tested the transferability of 7T-trained models to 3T clinical images, and whether synthetic 3T training data - generated via a disentangled representation learning method - could help bridging this domain gap. On held-out 7T data, the native pipeline consistently outperformed the template one. For the STN, native-space Dice reached 0.775 +- 0.055 versus 0.713 +- 0.051 (1 mm template), with HD95 of 0.79 +- 0.24 mm versus 1.17 +- 1.10 mm, respectively. Similar advantages were observed for the RN and SN. Increasing template resolution did not improve accuracy. When applied to 3T images, all models showed a considerable performance drop. Adding synthetic 3T data yielded only modest improvements, though without degrading 7T performance. Native-space segmentation is preferable for applications requiring patient specific anatomical fidelity, such as the surgical planning in PD. Bridging the 7T-to-3T domain gap remains an open challenge, motivating future work on domain adaptation tailored to subcortical structures.
Authors: Hongyang He, Jiuming Liu, Victor Sanchez
Abstract: Vision-Language-Action (VLA) models enable robots to predict actions directly from visual observations and language instructions, but adapting them to new environments still depends on costly action-labeled demonstrations. To reduce this dependence, we study semi-supervised VLA adaptation under limited supervision signals, where only a small portion of trajectories contain robot actions and the remaining trajectories provide action-unlabeled vision-language observations. Unlike standard semi-supervised learning, the missing supervision is an embodied action signal that must be visually grounded, language-consistent, physically feasible, and temporally stable. To address this problem, we propose SemiVLA, a self-distilled teacher-student framework that learns from reliable pseudo-actions on unlabeled trajectories. SemiVLA introduces a VLA-specific reliability controller to assess vision-language alignment, action feasibility, and temporal transition consistency, and further updates the teacher through a Bottleneck-Projected Alignment Update to avoid noisy feedback contamination. With OpenVLA as the backbone, SemiVLA consistently improves multiple PEFT strategies across LIBERO and CALVIN. Under 10\% labeled trajectories, SemiVLA with Selective LoRA achieves 89.0\% average success on LIBERO, outperforming supervised LoRA by 8.0 points without extra inference cost.
Authors: Philippe Weinzaepfel, Christian Wolf, B\"ulent Mert Sariyildiz, Guillaume Bono, Gianluca Monaci
Abstract: Transformers are AI's workhorse with strong performance in modeling sequential data, but their computational cost becomes prohibitive when processing long sequences. We target long-horizon streaming vision and robotics applications like map-free pose estimation, where it is particularly impractical to store and maintain a history of observations. Recurrent Transformers address this limitation by maintaining fixed-size memory but their performance lags behind that of transformers operating over the full observation history. We argue that this gap does not stem from architectural limitations, but from differences in how these models learn to compress past information. Without access to an observation history, recurrent models must explicitly decide what to retain in memory at each step, a significantly harder learning problem. In this work, we propose a distillation approach that transfers the compression strategy of a classical full-history transformer to a recurrent variant. We enable this by designing a teacher model that explicitly compresses its observation history into a fixed-size bottleneck representation. By directly supervising the student's memory with this bottleneck representation, we align the two compression mechanisms. We show that this approach allows to train a recurrent latent robotic memory with linear-time complexity while substantially narrowing the performance gap to full-history transformers.
Authors: Wei Xu, Maoxiang Chu, Yuelong Fan, Guanghao Liao, Yinxiang Yu, Zhi Chen, Haotian Wang, Yutian Zhu
Abstract: Student behavior detection is important for intelligent classroom analysis but remains challenging in large-class scenarios due to dense instance co-occurrence, asymmetric occlusion, depth-wise scale variation, and fine-grained semantic degradation in distant targets. Existing classroom behavior datasets and general-purpose detectors are insufficient to characterize and address these challenges. This paper constructs the Highly Congested Classroom Behavior (HCCB) dataset, containing 50,229 student behavior instances across seven categories: reading, writing, heads up, sleeping, looking around, bowing head, and using phone. HCCB provides a challenging benchmark that integrates dense distributions, severe occlusion, scale variation, and fine-grained behavioral semantics. To address these issues, we propose ODER-HSFNet, a YOLO-based detection framework tailored to highly crowded classrooms. At its core, ODER-HSFNet introduces three task-specific innovations: the Occlusion-aware Deformable Edge Rectifier (ODER), which strengthens boundary evidence under occlusion; the Hypergraph-State Spatial Fusion (HSSF) module, which integrates local structure enhancement, state-space contextual modeling, and high-order relation aggregation; and the Occlusion-Calibrated Detection Head (OCDetect), which suppresses low-quality Pre-NMS candidates and reduces false positives from occlusion boundaries and neighboring instances. Experiments on two classroom behavior detection datasets show that ODER-HSFNet outperforms mainstream YOLO-series methods, achieving 60.60%/80.12% mAP50:95/mAP50 on HCCB and 57.36%/74.65% on SCB-D3-S. Ablation studies further verify the effectiveness of the proposed design for highly crowded classroom behavior detection.
Authors: Serdar Ozsoy, Lars Doorenbos, Federico Spurio, Gianpiero Francesca, Juergen Gall
Abstract: Procedural mistake detection is important for quality control and user assistance across many disciplines. Recent work in this field has achieved significant gains by using the reasoning capabilities of Video-Language Models (VLMs) as components within multi-stage pipelines, which consist of separate modules for supervised temporal action segmentation, error detection, and explainability. Consequently, they remain dependent on tailored training datasets and require task-specific training, limiting their wider applicability. To remedy this, we introduce zero-shot procedural mistake detection and propose a unified Zero-shot Procedural Mistake detection (ZeProM) framework that jointly solves procedural mistake detection and temporal action segmentation with a single pre-trained VLM. By evaluating our framework on two canonical mistake detection benchmarks, EgoPER and CaptainCook4D, we find that ZeProM can perform these tasks successfully, while approaching, or even outperforming, the performance of fully supervised methods. For instance, we achieve a 4.4 point improvement in EDA and a 2.0 point improvement in F1@.5 on average over all five EgoPER tasks compared to the strongest supervised methods. Overall, our results show the potential of unified methods for procedural mistake detection, and we hope this will steer the field away from highly complex pipelines and toward more generally applicable solutions.
Authors: Andreas Schliebitz, Heiko Tapken, Martin Atzmueller
Abstract: Self-supervised learning (SSL) typically relies on a backbone encoder followed by a small multilayer perceptron (MLP) projection head, which is conventionally discarded after training, while backbone quality is assessed via costly linear probing on labeled data. We argue that this approach including discarding the projector is rather computationally wasteful. Instead, we propose replacing the MLP head with a radial basis function network (RBFN), whose interpretable center and shape parameters can be exploited to judge representation quality without labels or a separate classifier. To this end, we introduce Scale-Normalized Separation (SNS), a novel label-free quality metric derived solely from the kernel centers and shapes learned during training. Across five canonical SSL architectures (MoCo, SimCLR, BYOL, SwAV and SimSiam) and four image classification datasets, we show that RBFN projection heads are competitive drop-in replacements for standard MLP projectors. We recommend constructing them with three RBF layers activated by the Gaussian radial basis function. Moreover, SNS exhibits strong to very strong positive correlation with established logistic regression metrics, demonstrating that a trained RBFN projector can act as a reliable proxy for backbone representation quality. We additionally publish a novel PyTorch compatible image classification dataset based on Google's Open Images V7 to facilitate reproducible research into representation learning.
Authors: Yutaka Yoshinaga, Naoya Chiba, Koichi Hashimoto
Abstract: Recent advances in large pre-trained models have led to remarkable progress in instance segmentation on general images. However, industrial scenarios remain challenging. Instance definitions are often application-specific and inconsistent, and the domain gap from general imagery is substantial due to weak textures and limited contextual cues. Consequently, a direct application of existing models is unreliable. We propose Boundary-by-Mask, a few-shot instance segmentation framework that supervises boundaries instead of interior appearance. Given a few RGB images and corresponding instance masks, the method extracts rich visual features using a foundation-model encoder and trains a lightweight Signed Distance Function (SDF) head to predict boundary-aware distance maps. Segmentation masks are obtained through an SDF-to-mask reconstruction process. By explicitly estimating contours, the framework achieves reliable instance separation even on low-texture and color-uniform surfaces. The instance definition is conditioned by the instance mask. Replacing the mask specifies the segmentation target, such as the whole object or a sub-part. A pixel-wise shallow MLP head enables rapid training. Experiments on industrial parts and food items with ambiguous boundaries show strong few-shot generalization, robustness in feature-poor conditions, and precise control over mask-level targets.
Authors: Haodong Li, Lulu Shao, Haolin Lu, Yu Fu, Yen-Ru Chen, Seemandhar Jain, Manmohan Chandraker
Abstract: Reconstructing compositional 3D scenes from a single image is a fundamental challenge in 3D world modeling. Recent methods can recover high-fidelity, complete 3D objects and predict plausible scene arrangements, but most still treat scene reconstruction primarily as a visual and geometric prediction problem. Their outputs may therefore contain floating objects, interpenetrations, or unstable-contact artifacts, limiting their physical validity and downstream usability in simulation, robotics, and interactive environments. We present $\phi$-Scene, a physically grounded approach to open-vocabulary and compositional image-to-3D scene reconstruction. The key premise is that a reconstructed scene should not be treated merely as a set of objects with predicted poses, but as a stable physical system. Accordingly, $\phi$-Scene formulates reconstruction as topology-driven physical assembly: it infers how objects support one another, orders them accordingly, and progressively settles each object against its already stabilized support context. For each object in topological order, SDF-based optimization first resolves penetrations against the pre-settled support context, and rigid-body simulation then settles the object into a stable contact configuration under real-world physical constraints. Experiments on 3D-Front show that $\phi$-Scene achieves the strongest overall performance among out-of-domain methods and remains highly competitive with in-domain baselines. Human and VLM evaluations further show strong preference for $\phi$-Scene in visual quality, reference alignment, and physical plausibility. Finally, dedicated physical plausibility metrics covering static contact quality and dynamic stability demonstrate that $\phi$-Scene substantially reduces penetration artifacts while producing much lower post-simulation drift, indicating more stable and physically grounded 3D scenes.
Authors: Marei Freitag, Olesia Korchevaia, Luca Freckmann, Anwai Archit, Constantin Pape
Abstract: Vision foundation models have substantially advanced computer vision, enabling state-of-the-art performance in zero- and few-shot settings. They have been successfully applied to biomedical imaging tasks ranging from organ segmentation in computed tomography to cell segmentation in light microscopy. Electron microscopy (EM) is a central modality for analyzing cellular ultrastructure due to its nanometer-scale resolution. However, the application of foundation models in EM has so far been limited to specific organelles, such as mitochondria, largely due to the diversity of segmentation tasks and the scarcity of comprehensively annotated data. As a result, EM segmentation still predominantly relies on supervised learning, requiring extensive manual annotation and limiting ultrastructural analysis. To address this gap, we propose $\mu$Match, a framework for semi-supervised learning and domain adaptation that leverages foundation models. We implement state-of-the-art student-teacher-based methods and evaluate multiple foundation models (SAM, SAM2, $\mu$SAM, DINOv2/v3) on challenging EM tasks, including mitochondrion, nucleus, and neurite segmentation. Our results demonstrate consistent improvements over strong baselines and highlight a path toward substantially reducing the annotation effort in EM.
Authors: Di Yang, Mahmoud Ali, Quan Kong, Gianpiero Francesca, Francois Bremond
Abstract: Vision-language models such as CLIP have recently achieved strong performance on a wide range of visual understanding tasks. However, most existing models rely primarily on appearance-level supervision from images or videos, and do not explicitly model human motion, which is essential for fine-grained and human-centric action recognition task as actions are defined by temporally structured and physically grounded body movements. To address this problem, we propose Transferable skeleton MOtion Representation (T-MOR), a motion-aware framework that learns transferable action representations from skeleton sequences with the aid of video and language supervision during training. T-MOR adopts a multi-modal contrastive learning scheme that aligns skeleton motion with visual and textual representations, while performing inference using only lightweight skeleton inputs. To support large-scale pre-training, we construct PoseCap-1M, a new dataset that contains over one million synchronized video, skeleton, and text triplets covering diverse human activities. We evaluate T-MOR on a range of human-centric action recognition benchmarks, including action classification and frame-wise temporal detection. Experimental results show that T-MOR consistently improves performance across multiple datasets, such as Toyota Smarthome, Penn Action, UAV-Human, TSU, and Charades. In addition, T-MOR demonstrates strong generalization ability in few-shot and zero-shot settings, highlighting the effectiveness of motion-centric and embodied representations for transferable action understanding.
Authors: Sidi Mohamed Sid'El Moctar, Achraf Ait Laydi, Alexandre Beber, Marcus Braun, Zdenek Lansky, Yousef El Mourabit, Helene Bouvrais
Abstract: Accurate segmentation of curvilinear structures remains challenging in biomedical imaging due to their thin geometry, complex topology, and sensitivity to noise. This is particularly critical for microscopy images of cytoskeletal network, where low signal-to-noise ratios and dense filament crossings often lead to fragmented or inaccurate segmentation. In this work, we propose CurvSegFlow, a segmentation framework based on time-conditioned flow matching. Instead of predicting a segmentation mask in a single pass, the method models segmentation as a dynamic process that progressively refines a noisy initialization into the target structure through a learned velocity field. The proposed model combines a U-Net backbone with triple-term loss function and temporal embeddings to guide the refinement process across reconstruction stages. This formulation enables gradual error correction and improves the continuity of thin structures. CurvSegFlow is evaluated on multiple synthetic and real microtubule datasets, as well as on public benchmarks of retinal vessels, corneal nerves and coronary arteries. Across datasets, the method achieves competitive or superior performance compared to established segmentation models, with consistent improvements in precision and structural continuity, particularly under low signal-to-noise conditions. These results show that flow-based iterative refinement provides a robust and general framework for curvilinear structure segmentation. Overall, the proposed approach improves segmentation quality in challenging imaging conditions and generalizes effectively across modalities without architectural changes.
Authors: Bharath Pillai, Varun Viswapriyan, Christopher Stewart, Tanya Berger-Wolf, Jenna Kline
Abstract: Scaling wildlife monitoring for real-world conservation deployments requires automated analysis of smart sensors that operate under severe annotation scarcity. We propose leveraging expert knowledge of species activity patterns as an annotation-free validation signal for multimodal monitoring pipelines. We operationalize agreement as the alignment of independently derived hourly activity curves both with each other and with published behavioral priors-a three-way convergence that rules out shared-data confounds and dataset-internal correlation as alternative explanations. Our vision pipeline combines zero-shot species detection via BioCLIP 2, sliced inference to handle deployment-constrained camera positioning, and geometry-based geographic localization from camera trap imagery. Our acoustic pipeline detects species vocalizations via a fine-tuned classifier. We validate the pipeline on a breeding herd of Milu deer and demonstrate that both modalities independently recover activity patterns consistent with known deer behavioral ecology with minimal manual annotation. The framework applies to species detectable in both visual and acoustic modalities for which behavioral priors are documented in the literature, suggesting a practical path toward self-validating wildlife-monitoring pipelines at conservation scale.
Authors: Zijian Fu, Xiangyang Chu, Mengshi Qi, Huadong Ma, Guanghao Zhang, Wei Li
Abstract: Instruction-conditioned trajectory prediction is an emerging problem in autonomous driving, where a model predicts the future ego trajectory not only from visual scene context and historical motion, but also from a natural-language maneuver instruction. This paper presents our submission to the doScenes Instructed Driving Challenge, built upon OmniDrive, a vision-language-action driving agent with 3D perception, reasoning, and planning capabilities. We adapt OmniDrive to the doScenes setting by training it on instruction-annotated nuScenes scenes and generating a 6-second ego trajectory represented by 12 future waypoints. To improve multi-view visual grounding, we further introduce a DVPE-style divided-view perception module into the OmniDrive perception head. Instead of attending globally to all camera features, the proposed module groups query features and image tokens into divided local view spaces and performs visibility-aware cross-attention within each view. This design reduces irrelevant cross-view interference and helps the model better align language instructions with local driving-relevant visual evidence. The code is publicly available at: https://github.com/feel12348/doscenes-omnidrive.
Authors: Bita Azari, Zoe Stanley, Avneet Batra, Poorvi Bhatia, Hali Kil, Manolis Savva, Angelica Lim
Abstract: Facial expressions are nonverbal social signals used in human interaction, but facial expression recognition datasets often focus on static images, basic emotion categories, or single deterministic annotations. We introduce Chehre, an emoji-prompted video dataset for analyzing dynamic facial expressions across a wide range of expressions for exploring inter-individual perceptual diversity. In Chehre, participants were prompted to express and record 40 facial emojis. Later, their facial motions were transferred onto synthetic faces to preserve privacy. A separate group of annotators analyzed the anonymized videos using emoji and label annotations, resulting in 2,111 high quality videos collected from 203 performers and validated by 902 annotators. We define two benchmark tasks: dominant expression recognition, which tests whether models recover the top human-rated labels, and distributional expression recognition, which tests whether models capture the diversity of human responses. We benchmark recent vision-language models using random sampling and persona prompting to generate multiple predictions per video. Results show that both tasks are challenging: among the models evaluated, the best-performing model achieves only 32.5% Top-1 accuracy on dominant expression recognition and a Spread Ratio well below the human reference on distributional recognition. Chehre provides a benchmark for evaluating diverse, dynamic, and distributional facial expression recognition
Authors: Jiehui Huang, Yuechen Zhang, Bin Xia, Jiahao Wang, Xu He, Zhenchao Tang, Meng Chu, Xin Tao, Pengfei Wan, Jiaya Jia
Abstract: Generating a coherent multi-shot video requires structured cross-shot memory. Subject appearance, scene context, and speaker identity must persist across cuts. Existing approaches either train end-to-end over fixed-length sequences and cannot scale, generate shot-by-shot with memory banks that grow linearly, or orchestrate pretrained generators under an LLM planner without a multi-shot-aware backbone. We present UnityShots, a memory-driven multi-shot audio-video generation system built on LTX-2.3, trained on annotated cinematic and music-video shots. The video stream maintains two fixed-size slots, a long-term memory (LTM) slot anchored to the opening shot and a short-term memory (STM) slot holding the immediately preceding tail, both updated at every cut by a boundary-conditioned gate that fuses visual cut probability and beat-tracker signals. The audio stream injects a reference speaker token at every shot to preserve vocal timbre without a sliding audio bank. A discrete cut-type prior, learned through AdaLN, becomes an inference-time control knob over transition strength. We release a benchmark of $200$ multi-cultural multi-shot sequences spanning six ethnic regions and ten or more languages, with per-shot reference identities, reference audio, and per-boundary transition labels. Evaluated across I2V, T2V, and R2V conditioning modes, UnityShots leads open-source baselines on every cross-shot coherence metric and matches the strongest closed-source system on the multi-shot axes.
Authors: Nirjhor Datta, M. Sohel Rahman
Abstract: We present ENLIGHT, a fast and training free framework for low-light image enhancement based on direct optimization of a perceptual objective. Unlike deep learning approaches that require large scale training data and supervision, ENLIGHT operates in a zero-shot manner by optimizing image quality at inference time. The method employs a two stage global to local optimization strategy. In the first stage, ENLIGHT performs global illumination adjustment to improve visibility while maintaining structural consistency and avoiding excessive noise enhancement. In the second stage, a shadow aware refinement selectively improves low-intensity regions through masked local optimization, enhancing visibility without overexposure. To balance quality and efficiency, we introduce two modes: Fast, which uses a multi-objective formulation combining entropy, gradient preservation, and noise regularization, and Ultrafast, which reduces computational cost via a lightweight approximation of the same objective. The framework is optimizer agnostic and supports both evolutionary and lightweight local search methods. Experiments on BAID, Backlit300, LIME, MEF, NPE, and DICM demonstrate that ENLIGHT achieves competitive perceptual quality (MUSIQ, NIQE, BRISQUE) with significantly lower inference time. Qualitative results further show improved contrast, preserved structural details, and controlled noise amplification, making ENLIGHT a practical and interpretable alternative to learning based methods.
Authors: Xuan Qi, Daniele Berardini, Dario Serez, Vito Paolo Pastore, Vittorio Murino
Abstract: Unsupervised domain adaptation (UDA) aims to learn a target-domain classifier from labeled source data and unlabeled target data under distribution shift. Recent diffusion-based UDA methods approach this problem by synthesizing labeled target-style images and training on the resulting synthetic data. However, their performance depends heavily on the conditioning design: class prompts provide only coarse guidance, while domain adaptation modules mainly control appearance, which may leave target-style synthesis insufficiently specified. We propose VT-DUDA, a visual-token conditioning framework for diffusion-guided UDA. Instead of relying only on text prompts, VT-DUDA uses source images to provide additional instance-level visual context for target-style synthesis. Specifically, VT-DUDA maps each source image to a compact sequence of visual tokens and forms a hybrid conditioning context by concatenating these tokens with the corresponding text embeddings along the cross-attention context dimension of a latent diffusion model. This provides instance-dependent conditioning beyond text alone, while synthesis is performed with the target-domain adapter branch. Because guidance is represented explicitly as a token sequence, the same interface also permits inference-time manipulation of the conditioning signal through token selection and token-strength adjustment. The proposed method preserves the standard diffusion objective and can be integrated into existing adapter-based diffusion frameworks without modifying the backbone. Across Office-31, Office-Home, and VisDA-2017, VT-DUDA improves average target-domain accuracy over strong discriminative and diffusion-based UDA baselines. The results suggest that, in generation-based UDA, a stronger conditioning interface can improve the downstream usefulness of synthetic target-style data.
Authors: Yue Cao, Jianyang Gu, Vyacheslav Kungurtsev, Yu Hu, Jozsef Hamari, Zheng Liu, Mohsen Zardadi
Abstract: Dataset distillation (DD) has proven to reduce training cost while preserving accuracy. While promising, the factors that make one distilled dataset more effective than another remain poorly understood. In this work, we investigate this question through the lens of discrete visual tokenizers. Whereas many prior DD efforts emphasize matching global data distributions, we suggest that the effectiveness depends on which semantic concepts are captured and how they are composed. Discrete visual tokenizers provide a finite vocabulary that enables direct statistical analysis of such compositional structure. Through quantitative analysis of token-level statistics, we introduce the structural score to measure the adequacy of token compositions. We observe that distilled datasets with balanced token composition yield higher validation performance. On the other hand, divergence from the original data does not necessarily harm performance. We further show that samples with high structural scores in the discrete token space can effectively guide diffusion-based DD. Our findings highlight the importance of token composition in dataset effectiveness, offering a principled complement to distributional similarity considerations in DD.
Authors: Awais Rauf, Ahmed Hasssan, Greg Slabaugh
Abstract: Understanding long videos requires fine-grained perception and multi-step, higher-order reasoning over complex, long-range spatio-temporal dynamics. Vision-language models (VLMs) encode video frames into visual tokens and attempt to perform both perception and multi-step planning latently, within a single forward pass. This coupled formulation, however, is bottlenecked by the LLM's limited capacity to discover and execute multi-step strategies in its latent representations. To address this bottleneck, we propose Hierarchical Programmatic Probing (HPP), a framework that decouples semantic perception from higher-order temporal reasoning by reformulating long video understanding as iterative, programmatic exploration of a hierarchically segmented video. Specifically, a coding-capable LLM plans and executes a multi-step strategy in an interactive coding environment, probing the video for information and invoking a VLM for localized perception on demand. To make probing tractable over long videos, we introduce three components: information-density-aware hierarchical segmentation, late-interaction semantic retrieval, and structured probing functions for coarse-to-fine temporal localization. We validate HPP on LongVideoBench, which requires both fine-grained perception and long-range relational reasoning, and show that decoupling the two via iterative programmatic probing yields substantial gains. Further results on EgoSchema, VideoMME, and MLVU demonstrate the effectiveness of our approach across diverse long-video benchmarks.
Authors: Zhipeng Xu, De Cheng, Xinyang Jiang, Nannan Wang, Dongsheng Li, Xinbo Gao
Abstract: Single domain generalization (SDG) aims to learn a robust model, which could perform well on many unseen domains while there is only one single domain available for training. One of the promising directions for achieving single-domain generalization is to generate out-of-domain (OOD) training data through data augmentation or image generation. Given the rapid advancements in AI-generated content (AIGC), this paper is the first to propose leveraging powerful pre-trained text-to-image (T2I) foundation models to create the training data. However, manually designing textual prompts to generate images for all possible domains is often impractical, and some domain characteristics may be too abstract to describe with words. To address these challenges, we propose a novel Progressive Adversarial Prompt Tuning (PAPT) framework for pre-trained diffusion models. Instead of relying on static textual domains, our approach learns two sets of abstract prompts as conditions for the diffusion model: one that captures domain-invariant category information and another that models domain-specific styles. This adversarial learning mechanism enables the T2I model to generate images in various domain styles while preserving key categorical features. Extensive experiments demonstrate the effectiveness of the proposed method, achieving superior performances to state-of-the-art single-domain generalization approaches.
Authors: Omprakash Chakraborty, Leo Fillioux, Ismail Ben Ayed, Jose Dolz
Abstract: Deep neural networks often produce poorly calibrated confidence estimates, overstating their certainty even when predictions are incorrect. Temperature Scaling remains the most widely used posthoc calibration method due to its simplicity and effectiveness, yet its global, uniform rescaling of logits fails to correct the highly heterogeneous structure of miscalibration observed across the confidence spectrum. In particular, the largest correctness confidence discrepancies arise in different quantile regions depending on the setting, low confidence predictions, where uncertainty matters most, tend to exhibit the largest correctness confidence discrepancies, which standard TS leaves largely unaddressed. We introduce Quantile Adaptive Temperature Scaling (QaTS), a simple and efficient post hoc calibration method that adapts the temperature as a function of a predictions empirical confidence quantile. By mapping confidences into the quantile space, QaTS normalizes the calibration problem, makes the structure of miscalibration explicit and enables a monotone temperature function that adapts across quantiles while leaving well calibrated high confidence predictions largely unchanged. preserving high confidence behavior. This quantile aware formulation aligns naturally with a reparameterized Expected Calibration Error (ECE) objective and yields a sample wise temperature that is robust across a variety of challenging scenarios, such as class imbalance and distributional shifts. Across a broad range of datasets, architectures, evaluation scenarios and diverse tasks, QaTS consistently, and substantially, outperforms state of the art post hoc calibration methods, delivering more reliable and trustworthy confidence estimates without modifying model predictions.
Authors: Shiva Parsarad, Parth Shandilya, Isabel Wagner
Abstract: Medical image segmentation is widely used for disease detection but relies on sensitive data, raising privacy concerns as trained models can leak information. Differential privacy, typically implemented via Differential Private Stochastic Gradient Descent (DPSGD), provides a solution, though at the cost of reduced utility. Recent DPSGD variants, including Automatic clipping (Auto-S), Normalised SGD with perturbation (NSGD), and Per-sample adaptive clipping (PSAC), have shown promise in image classification, but their behavior in medical segmentation remains underexplored. We evaluate these methods across binary and multi-class tasks and analyze gradient alignment, showing that prior assumptions, particularly for PSAC, do not consistently hold. We further demonstrate that combining clipping strategies with morphological refinement improves segmentation quality under privacy constraints. Finally, we propose an adaptive DP-Morph variant that captures class-specific structures and enhances performance in multi-class settings.
Authors: Prithvi Raj Singh, Satyendra Singh
Abstract: We present MARLNet (Motion-Aware Reinforcement Learning Network), a PPO-based bounding-box refinement agent that incorporates a constant-velocity motion prior into the observation state and an action smoothness penalty into the reward function. The agent operates on 268-dimensional observations encoding the current proposal, a kinematic prediction, the previous action, and a 256-dimensional EfficientNet-B0 crop feature, and learns a five-dimensional policy controlling coordinate adjustments and a binary termination trigger. Evaluated on Pascal VOC 2012 and VisDrone 2019, MARLNet trains stably across all regularization strengths tested and achieves consistent gains in detection success rate at $\text{IoU} \geq 0.5$: up to $+0.011$ on VOC ($\lambda_\text{phys}{=}0.10$), where the motion prior prevents the overshooting that causes plain PPO to regress on this metric, and $+0.007$ on VisDrone ($\lambda_\text{phys}{=}0.70$), where unconstrained PPO achieves a larger gain ($+0.025$) owing to the weaker base detector. Through reward design ablations and training dynamics analysis, we identify a reward interference in which combining a constant-velocity deviation penalty with an absolute IoU term causes trigger collapse, and show that replacing it with the action smoothness penalty resolves this failure. We further characterize a representational ceiling facing crop-feature refinement agents that share a backbone with their base detector, confirmed through a global-plus-local observation ablation. Project page: https://prithviraj97.github.io/marl-net
Authors: Yifan Yang, Wenjing Gong, Kaili Zhang, Lei Zou, Zhengzhong Tu, Hao Li, Zongrong Li, Xinyue Ye
Abstract: Due to the increasing frequency and intensity of extreme climate events, there is a clear demand for intelligent, scalable, and autonomous approaches to disaster damage assessment. Existing methods, largely based on supervised learning and task-specific fine-tuning, struggle to generalize under domain shifts, long-tailed data distributions, and heterogeneous geospatial data sources, especially in disaster scenarios. They also often lack the ability to integrate and reason across multimodal geospatial information, such as satellite images and street-view images. In this paper, we introduce RAPID, a reproducible multi-agent pipeline for interpretable disaster damage assessment, including damage-level assessment, damage-type interpretation, and actionable suggestions for response, remediation, and recovery. RAPID coordinates specialized agents to perform cross-view understanding, image restoration, structured damage recognition, and geographical reasoning across heterogeneous data modalities. Without task-specific fine-tuning, RAPID supports zero-shot damage assessment by jointly using complementary information from remote sensing and ground-level perspectives. The system produces fine-grained, interpretable assessments and automatically generates location-specific, decision-relevant disaster reports to support early-stage emergency response. We evaluate RAPID across hurricanes, floods, wildfires, and earthquakes using multiple cross-view imagery inputs, including pre- and post-disaster street-view images, post-disaster remote sensing imagery, and street-view image pairs. Experiments show that RAPID achieves 0.92 overall accuracy for multi-disaster type classification and up to 0.627 for cross-view damage severity prediction, highlighting its potential as a foundational framework for autonomous disaster intelligence.
Authors: Zhiyuan Tao, Srikumar Sastry, Matthew J Thompson, Elizabeth G Campolongo, Net Zhang, Ziheng Zhang, Hilmar Lapp, Yu Su, Tanya Berger-Wolf, Nathan Jacobs, Wei-Lun Chao, Jianyang Gu
Abstract: Multimodal contrastive learning has enabled zero-shot visual classification by aligning images with textual categories. However, in hierarchically structured label spaces, existing methods often produce predictions that are inconsistent across taxonomic levels. For example, a model may predict a fine-grained category whose parent category contradicts its simultaneously predicted higher-level label. By analysis, the issue originates from false negative labels when contrastive comparison involves multiple taxonomic levels. To this end, we propose to restrict contrastive comparisons to categories within the same taxonomic level. In addition, we adopt a group-balanced design, ensuring each taxonomic level receives adequate optimization. As a result, the proposed framework improves both hierarchical consistency and classification accuracy from coarse to fine granularity. We train our model with TreeOfLife-10M based on BioCLIP and evaluate it across multiple hierarchical classification benchmarks, where the model demonstrates significantly improved hierarchical consistency in both Euclidean and hyperbolic spaces. Notably, on iNaturalist 2021 (iNat21), our method improves average accuracy across levels by 30.47% over the baseline, highlighting its effectiveness for hierarchical zero-shot classification.
Authors: Aman Goyal, Kshama Nitin Shah, Kemmannu Vineet Venkatesh Rao
Abstract: Automated classroom engagement recognition holds substantial promise for scalable learning analytics, yet the suitability of modern Vision-Language Models (VLMs) for this task under zero-shot conditions remains largely unexplored. We present a systematic benchmark that evaluates five widely-used VLMs: CLIP, BLIP-VQA, GPT-4o, LLaVA-1.5-7B, and Qwen2.5VL-7B-Instruct across two complementary educational datasets: DAiSEE, an individual-student video dataset (300 sampled test clips), and the Student Classroom Behaviour dataset (SCB, 1,168 scene-level images). Each model is probed with three prompt variants spanning minimal, rubric-anchored, and chain-of-thought designs. Our experiments reveal three primary failure modes of zero-shot VLMs for engagement recognition: (1) near-random performance on individual students, with Cohen's kappa never exceeding 0.10 on DAiSEE; (2) severe class collapse, where models assign 85-100% of predictions to a single engagement level regardless of visual content; and (3) extreme prompt sensitivity, with accuracy swings of up to 32 percentage points on identical images depending solely on prompt phrasing. Remarkably, scene-level classification on SCB is substantially more tractable: CLIP and GPT-4o achieve kappa approximately 0.60 when prompted with behaviorally-grounded rubrics. We also document a practical barrier for deployment: GPT-4o's safety filters reject 98% of chain-of-thought requests involving individual student faces. Our findings provide a calibrated baseline and surface critical design considerations for the use of VLMs in educational observation systems.
Authors: Yanghui Song, Nanqing Liu, Haonan Yin, Yingjie Gao, Chengfu Yang, Qi Ming
Abstract: Open-vocabulary semantic segmentation (OVSS) in remote sensing images aims to segment categories beyond a fixed label space. Recent SAM 3-based methods provide a promising training-free foundation, yet three key issues remain: (1) a single class-name prompt lacks sufficient semantic coverage for complex remote sensing categories; (2) expanding each category into multiple prompts introduces redundant online text encoding; and (3) directly aggregating multiple prompt responses propagates noisy activations into the final prediction. To address these issues, we propose ProC-SAM3, which calibrates SAM 3's prompt interface for remote sensing OVSS from three complementary aspects. First, we construct an offline prompt pool where a Category Matcher groups MLLM-generated candidates into per-category sets, and Expansion Constraints further refine each set using category-specific prior knowledge. Second, the resulting text embeddings are cached and reused across all test images, eliminating repeated text encoding. Third, we introduce Presence-Guided Residual Fusion to gate unreliable decoder outputs by prompt presence and confidence, followed by peak-preserving class aggregation that retains fine-grained activations for small and sparse objects. Experiments on eight benchmarks show that ProC-SAM3 achieves an average mIoU of 56.1%, outperforming the previous best training-free method by 3.9 percentage points. Code will be available at https://github.com/YanghuiSong/ProC-SAM3.
Authors: Yu-Syuan Xu, Hao-Lun Sun, Hao-Wei Chen, Hsien-Kai Kuo, Chun-Yi Lee
Abstract: Arbitrary-scale image super-resolution (ASISR) aims to reconstruct high-resolution images from low-resolution inputs over a continuous range of upscaling factors. While traditional pixel-regression approaches often produce overly smooth results that lack realistic details, recent diffusion methods can produce sharper and more realistic textures. However, these diffusion techniques frequently introduce the risk of structural hallucinations. To address these issues, we propose Fidelity- and Perception-Aware Local Implicit Attention (FPLIA), a framework that effectively integrates fidelity-oriented features into a diffusion pipeline to produce realistic and faithful reconstructions for ASISR. We introduce a Fidelity and Perception Attention Module (FPAM), which applies both self-attention and cross-attention to fidelity-oriented and perceptual features to enhance representational capacity. To further exploit their complements, we design a Fidelity and Perception Select Module (FPSM) that adaptively selects the most representative features for RGB values prediction. We conduct extensive experiments to validate the effectiveness of these components. Both qualitative and quantitative results show that FPLIA delivers superior perceptual realism while maintaining reconstruction accuracy on standard ASISR benchmarks. The source code is accessible at the following repository: https://github.com/XUSean0118/FPLIA.
Authors: Qing Xu, Xiangjian He, Wenting Duan, Jiebo Luo, Zhen Chen
Abstract: Cell segmentation is critical for computational pathology and biomedical discovery. While recent Vision Foundation Models (VFMs) have demonstrated remarkable universal feature representations, unlocking their full potential for cellular imaging is currently bottlenecked by resource-intensive adaptation paradigms. Existing methods typically rely on fine-tuning heavy visual encoders, leading to extensive computational overhead and a dependency on large-scale annotations. To address this, we propose the EffiCell-Seg framework for highly efficient cell segmentation without re-training the visual encoder. Our core insight is that pretrained VFMs intrinsically encode complementary structural priors: global saliency for localizing potential cells, and local morphological patterns for delineating cellular structures. To harness these priors, we devise a Cell Structure Prompt Encoder (CSP-Encoder) that synthesizes semantic-aware saliency and principal morphological features from frozen VFM representations into explicit structural prior maps. Moreover, we propose a Synergistic Mask Decoder (SM-Decoder) that enforces contextual consistency by jointly predicting geometric distance fields and semantic maps via mutual cross-guidance. Extensive experiments demonstrate that EffiCell-Seg outperforms state-of-the-art methods across diverse cell imaging modalities while requiring only ~5M trainable parameters, over 130x fewer than fully fine-tuned VFM counterparts. The code is available at https://github.com/xq141839/EffiCell-Seg.
Authors: Saif ur Rehman Khan, Imad Ahmed Waqar, Sebastian Vollmer, Andreas Dengel, Muhammad Nabeel Asim
Abstract: Automated chest X-ray report generation requires precise cross-modal grounding to ensure clinically reliable descriptions. However, existing vision-language models rely on implicit attention mechanisms that fail to enforce explicit region-word correspondence and disease-level consistency. We propose Game-Theoretic Alignment Network (GTA-Net), a vision-language framework that formulates report generation as a cooperative game-theoretic alignment problem. The model introduces a BinaryGameAligner that models interactions between image regions and text tokens using similarity-based payoff matrices with Shapley-inspired importance weighting. To enforce clinical semantics, we further develop a Disease-Aware Ternary Aligner, which captures joint interactions among images, reports, and structured disease concepts. GTA-Net combines a Swin-based visual encoder with a LoRA-adapted large language model and is trained with a unified objective for generation and alignment. Experiments on CheXpertPlus and IU-XRay demonstrate state-of-the-art performance across standard generation metrics and improved clinical consistency, highlighting the effectiveness of explicit game-theoretic alignment for medical vision-language generation.
Authors: Abdirashid Omar, Jonghyuk Park
Abstract: Remote sensing change detection (CD) from bi-temporal imagery is critical for applications such as urban monitoring, disaster assessment, and environmental management, yet robust localization remains challenging under sparse changes, noisy labels, and appearance variations. In this paper, we propose Context Sampling Attention (CoSA), a lightweight decoder-side refinement module that explicitly leverages bi-temporal feature correlation as a control signal for adaptive change-aware feature enhancement. This differs from conventional attention mechanisms that rely on implicit feature weighting without explicit temporal control. In the implemented FC-Siam setting, CoSA computes normalized same-location cross-correlation between paired decoder features, converts low correlation into a change gate, and injects the resulting gated residual at native 1/8 and 1/16 feature scales through learnable residual scaling. This design enables effective discrimination between stable and ambiguous regions without relying on computationally expensive global attention. Extensive experiments on four benchmark datasets (LEVIR-CD, S2Looking, DSIFN, and CLCD) demonstrate consistent improvements over strong baselines, achieving 1.5-2.6% gains in changed-class F1 while introducing negligible parameter overhead. Ablation studies confirm that multiscale placement and learnable residual gating are both important for peak performance. These results indicate that CoSA establishes a practical and effective refinement paradigm for enhancing temporal discriminability in Siamese change detection frameworks.
Authors: Xuyang Wang, Zhenyu Li, Jian Ding, Habib Slim, Peter Wonka, Hongdong Li, Mohamed Elhoseiny
Abstract: Reconstructing articulated objects from sparse images requires recovering complete geometry, movable parts, and motion parameters. Recent methods typically separate geometry reconstruction, part reasoning, and articulation estimation into different stages. This separation can weaken consistency between shape, active parts, and motion, while also incurring substantial inference cost. We introduce Artic-O, an end-to-end, feed-forward framework for articulated object reconstruction via latent geometry learning. Instead of fitting geometry in image or view space, Artic-O maps sparse multi-state observations into a pretrained latent geometry space, where a frozen flow-matching decoder provides a complete-shape prior for recovering visible and occluded structures. To connect geometry with articulation, Artic-O fuses visual tokens, geometry latents, and point-wise decoder features in an image-grounded part-reasoning module for active-part segmentation and articulation prediction. We further train the model with a geometry-to-articulation curriculum and a decoupled two-pass strategy to balance reconstruction and part-level supervision. On PartNet-Mobility, Artic-O achieves strong reconstruction quality while being substantially more efficient than LARM, a strong prior method. It reduces Chamfer Distance, improves F-score, and achieves comparable or better articulation accuracy across most joint metrics, while reducing inference time from 9 minutes to about 0.3 seconds per object.
Authors: Changjun Li, Runqing Jiang, Lian Xu, Ye Zhang, Qingyong Hu, Yulan Guo
Abstract: Vision Transformers have achieved remarkable success in many fields, yet their deployment on edge devices remains challenging due to their substantial computational demands. Post-Training Quantization (PTQ) offers an attractive solution by compressing models using a small calibration set with minimal training overhead. However, most existing PTQ works adopt a static quantization paradigm that is uniformly applied to all instances. Given the substantial diversity of natural images, the activation distributions vary significantly across samples, making these methods inherently suboptimal. In this paper, we propose ScalePredictor, a dynamic quantization framework for accurate and efficient quantization scale learning of ViTs. We first reveal a hidden correlation between the distribution range of shallow-layer activations and the optimal scales of deeper layers. Based on this, we develop a scale learning mechanism that integrates an efficient range extraction approach to capture robust range statistics at the shallow stage, which are then fed into a Taylor-motivated polynomial scale projection module to generate all quantization scales simultaneously. With the efficiency of polynomial approximation, ScalePredictor introduces insignificant computational overhead while avoiding costly just-in-time calibration. Extensive experiments on ImageNet demonstrate that ScalePredictor consistently outperforms prior PTQ methods, achieving a more favorable accuracy-efficiency trade-off. Code and additional results are shown in the supplementary materials.
Authors: Xinlong Chen, Jiafu Tang, Yue Ding, Yizhuo Jia, Bozhou Li, Bohan Zeng, Yang Shi, Shihao Li, Yiyan Ji, Qiang Liu, Weihong Lin, Yuanxing Zhang, Pengfei Wan, Liang Wang, Tieniu Tan
Abstract: Accurate and comprehensive video captions with consistent subject references are critical for downstream understanding and generation tasks. However, few existing benchmarks can objectively and comprehensively evaluate these properties across diverse durations and scenarios, thereby hindering the advancement of video captioning models. To bridge this gap, we propose CapRiCorn-1K, a comprehensive benchmark designed to evaluate both video captioning quality and subject referential consistency across long temporal horizons and diverse video domains. To accommodate varied evaluation needs, our benchmark supports both audiovisual and visual-only settings. Extensive experiments on CapRiCorn-1K reveal that current models generally struggle to generate accurate and comprehensive captions while maintaining consistent subject references. Moreover, as video duration increases, both the overall caption quality and subject referential consistency decline. Notably, our evaluation metrics exhibit strong correlations with the performance of downstream understanding and generation tasks conditioned on the generated captions, further validating their effectiveness. The project is available at https://github.com/xlchen0205/CapRiCorn-1K .
Authors: Houzhang Fang, Ruixuan Huang, Qiuhuan Chen, Xiaolin Wang, Yi Chang, Luxin Yan
Abstract: Infrared small target detection (IRSTD) in high-resolution images is crucial for many practical applications, such as surveillance of unmanned aerial vehicles (UAVs) and UAV-based ground monitoring. However, IRSTD remains challenging due to the small size and weak features of targets, as well as significant interference from complex dynamic backgrounds. Existing detection methods often suffer from redundant computations on non-target background regions and insufficient exploitation of target context information, which limits their performance in complex backgrounds. To address these issues, we propose an efficient coarse-to-fine infrared small target detection framework with attention prior-guided knowledge distillation, termed ECFNet. In the coarse stage, we design a region binary classification network (RBCN) on grid-based multi-scale feature maps to efficiently recognize target-containing context region proposals while suppressing complex backgrounds. Moreover, we introduce a novel denoising-assisted training strategy that incorporates noisy ground-truth (GT) masks into the feature maps of RBCN and trains the network to reconstruct the GT masks through a denoising task, thereby enhancing its ability to distinguish target proposals from background regions and accelerating convergence. In the fine stage, we customize a lightweight target detector to the coarse stage's region proposals for balancing accuracy and efficiency. Furthermore, we propose a knowledge distillation strategy guided by the teacher-student cross-attention prior. This mechanism directs the student to focus on critical target regions, thereby enhancing the discriminative feature representation for infrared small targets. Extensive experiments on three real infrared datasets demonstrate that our method outperforms both existing single-stage and two-stage approaches while maintaining high real-time processing efficiency.
Authors: Oanh N. Tran, Thanh Quoc Hung Le, Oscar Chew, Kuan-Hao Huang, Khoa D. Doan
Abstract: Vision-Language Models (VLMs) struggle as query-relevant objects become smaller. To address this, recent training-free approaches dynamically retrieve and zoom into local image regions. However, we show that indiscriminately applying retrieval ignores a critical vulnerability: the resolution-context trade-off. Patch-based zooming recovers details for small targets, but can split large objects and destroy global spatial context; attention-based retrieval better preserves large objects, but remains less reliable on tiny details; and global perception is often fastest when retrieval is unnecessary. Motivated by these failure modes, we introduce ViRGo (Visual Retrieval or Global Perception), a lightweight framework that formulates visual retrieval as an adaptive routing problem. ViRGo estimates object scale from the VLM's intrinsic localization heads during the initial forward pass and combines it with semantic token confidence to select between global perception, patch-based retrieval, and attention-based retrieval with minimal additional computation. Experiments across multiple VQA benchmarks and object-size groups show that ViRGo improves the accuracy-efficiency trade-off: it matches patch retrieval on small details, leverages attention-based retrieval for larger objects, and reduces inference time by routing to the global baseline when zooming is unnecessary.
Authors: Wenhu Zhang, Kun Cheng, Changyuan Wang, Shiyao Li, Yuechen Zhang, Wenbo Li, Jiajun Zha, Jingyi Zhang, Kang Zhao, Jiaya Jia
Abstract: Few-step distillation for video diffusion models has attracted significant attention, driven by the urgent demand for efficient deployment in real-world scenarios. However, Distribution Matching Distillation (DMD), a leading paradigm, tends to degrade under limited NFE budgets, manifesting in video generation as layout instability, oversaturation, and broken motion dynamics. We trace this failure to a structural limitation: standard DMD is an intra-sample distribution-matching objective with coordinate-wise gradients, and thus imposes no explicit constraint on the relational geometry across batch elements or temporal frames, leaving the underlying copula largely unregulated. Combined with the mode-seeking tendency of its reverse-KL objective, this absence of relational guidance makes DMD prone to collapsing into local optima in the few-step regime. Motivated by this insight, we propose Copula-aware DMD (CoDMD), a lightweight relational regularizer that reuses score estimates already produced by the frozen teacher and the online fake model to construct pairwise relation matrices across samples and frames. These are matched through a supplementary distributional objective that requires no additional networks, datasets, or sampling trajectories. On the Wan-2.1-T2V model series at 1.3B & 14B scales, CoDMD distills 50-step teachers into 4-step students, achieving an approximate 25$\times$ speed-up while attaining VBench scores of 84.46 & 84.87, outperforming prior trajectory-based (rCM 82.81 & 84.05) and distribution-based (DMD 83.38 & 83.81) methods.
Authors: Zahiriddin Rustamov, Nadia Badawi, Rafat Damseh, Nazar Zaki
Abstract: Training medical image classifiers on entire datasets is wasteful when annotation budgets are limited: not all samples contribute equally, yet acquiring expert labels is expensive. Active learning reduces annotation cost through iterative querying, but assumes repeated access to an oracle and requires multiple rounds of model training. One-shot geometry-based methods such as facility location avoid retraining but operate on pairwise distances that ignore the local structure of the data manifold. We propose a graph-based one-shot selection method that operates entirely on frozen foundation model embeddings. Given embeddings from a pretrained encoder, we construct a k-nearest neighbor graph over all training samples and derive a two-term coverage kernel from the heat diffusion kernel, capturing both direct and two-hop neighborhood relationships. Greedy facility location on this kernel selects class-balanced subsets that maximize coverage of the data manifold. The two-term kernel matches the full spectral heat kernel in selection behavior while reducing computation to sparse matrix operations with a single hyperparameter. We evaluate on five MedMNIST datasets spanning histopathology, radiology, and microscopy, comparing against both training-dynamics and geometry-based baselines. Our method achieves the highest balanced accuracy on nine of ten dataset-ratio conditions, with the largest gains on class-imbalanced datasets where global graph construction captures cross-class structure that per-class methods miss, all without any model training during selection. Code is available at https://github.com/zahiriddin-rustamov/graph-coverage-selection.
URLs: https://github.com/zahiriddin-rustamov/graph-coverage-selection.
Authors: Chad M. Topaz, Niny Arcila-Maya, Elizabeth Munch, Zofia Stanley, Lori Ziegelmeier
Abstract: Fingerprints are the most widely deployed biometric. Verifying whether two impressions come from the same finger typically relies on minutiae, small landmarks such as skin ridge endings and bifurcations. These landmarks are extracted through a multi-stage pipeline of image enhancement, skeletonization, minutiae detection, and alignment. We investigate an alternative: using topological data analysis to represent the full pattern of skin ridges and valleys directly, bypassing minutiae detection and the downstream matching pipeline. We apply persistent homology, a topological tool that tracks how loops in the ridge pattern form and fill in across spatial scales, producing multi-scale summaries of ridge geometry. We develop and compare a range of verification methods on a standard benchmark dataset, FVC2000 DB1. Even the simplest topological summaries, with no trained parameters, substantially outperform geometry-only baselines. A trained method achieves an AUC of 0.91, while an optimal-transport method excels at the strictest false-accept thresholds, suggesting they capture different aspects of the ridge pattern. Fusing these two approaches yields the best performance at every low false-accept threshold we examine. Our results establish that these topological summaries capture substantial fingerprint identity information, far more effective for verification than raw pixel-level geometry. Because the entire pipeline is openly specified, it offers a transparent complement to minutiae-based systems, and we provide a modular framework for constructing, evaluating, and combining topological verification methods.
Authors: Yuan-Zhih Lin, Huu-Thang Nguyen, Huu-Phu Do, Hong-Han Shuai, Ching-Chun Huang
Abstract: Diffusion-based video editing has made significant progress; however, achieving precise and temporally consistent object-level control, especially in multi-object scenarios, remains challenging due to attention leakage, identity drift, and unstable temporal dynamics. In this work, we propose IDAGEdit, a training-free framework for fine-grained multi-object video editing with strong temporal consistency. The framework adopts Layout-guided Attention Modulation to facilitate coherent multi-object editing, while Instance-level Masks are introduced to preserve individual object identity and enforce localized attention within each object region, thereby enabling fine-grained, object-level editing. Extensive qualitative and quantitative evaluations demonstrate that our method improves temporal stability and multi-object controllability over state-of-the-art video editing approaches.
Authors: Zubair Abbas, Muhammad Umair, Muqaddas Hameed
Abstract: Apparent emotion in natural images is often not visible from the face alone. The face may be small, hidden, or neutral, while posture and scene context carry much of the evidence. This work studies context-aware emotion recognition on EMOTIC with an image-only two-stream model. A ResNet-18 body stream encodes the target-person crop, and a CLIP ViT-B/16 scene stream encodes the full image. The fused feature predicts 26 categorical emotion labels and the continuous valence, arousal, and dominance values. This study examines whether small context-debiasing or rare-class training changes still help after adding a CLIP scene encoder. The clean two-stream model is compared with simplified CCIM-style intervention, CLEF-lite context-bias subtraction, ASL tuning, and class-balanced sampling under the same implementation pipeline. No tested variant improves over the clean two-stream model, which achieves 34.52% mAP on the EMOTIC test split. CLIP gives the model broad scene semantics, but the simplified causal, counterfactual, and rare-class changes do not automatically improve performance. Most remaining errors are in rare and subtle emotion categories, so the next step should focus on label relationships and finer subject-context interaction.
Authors: Jiahong Chen, Jinghao Wang, Ziwen Wang, Zi Wang, Banglei Guan, Qifeng Yu
Abstract: Single-reference unseen object 6D pose estimation reduces object onboarding by estimating poses of arbitrary novel objects from only one reference view. Recent correspondence-based pipelines have achieved robust performance with vision foundation model (VFM) features. However, they typically treat these features as intra-view descriptors, leaving dense visual-semantic cues, including appearance, structure, and context, insufficiently exchanged across views before geometric decoding. Consequently, the decoded point features may lack joint semantic and geometric discriminability, making correspondence estimation still difficult in challenging cases. Instead of processing features independently, we build the correspondence pipeline around an early cross-view semantic prior. Specifically, cross-view semantic interaction (CVSI) enables dense query and reference VFM tokens to exchange semantic context and form a cross-view prior. Nevertheless, direct CVSI may disturb the VFM token structure, while the resulting semantic prior still needs 3D representation consistency for rigid correspondence. To make this CVSI prior reliable for 3D correspondence learning, we introduce two complementary training-time constraints: the intra-view structure preservation (IVSP) loss preserves the original intra-view token affinity structure during interaction, while the reference-anchored geometric consistency (RAGC) loss enforces spatial representation consistency of decoded point features. The final pose is recovered from learned correspondences through weighted SVD. We further construct a challenging view-pair protocol from the BOP Challenge datasets YCB-V and TUD-L to evaluate robustness in difficult matching scenarios. Extensive experiments on six benchmarks under different view-pair settings show that our method achieves state-of-the-art performance while maintaining comparable inference speed.
Authors: Zixuan Liu, Kaijie Yu, Chun He, Xiaoxu Cai, Xinhai Ye, Haishuai Wang, Gongyin Ye, Jiajun Bu
Abstract: Morphological traits provide important evidence for phylogenetic reconstruction and evolutionary relationship analysis. Recent image-based approaches have introduced deep learning, particularly convolutional models, to derive morphological features from specimen images, but these methods generally rely on single-modality visual representations and do not explicitly incorporate morphological semantics. This study proposes a morphology-aware multimodal alignment framework for insect phylogenetic reconstruction. The framework combines specimen images with curated morphological descriptions by adapting a vision transformer through parameter-efficient fine-tuning and supervised contrastive learning, followed by image-text alignment in a shared latent space. The learned image embeddings are then used as continuous traits for Bayesian phylogenetic reconstruction. On the public Rove-Tree-11 dataset, comparative and ablation experiments across multiple visual backbones and feature adaptation strategies demonstrate that multimodal alignment improves topological agreement with the reference phylogeny. The results indicate that the proposed framework can derive morphology-aware visual traits for computational phylogenetic reconstruction.
Authors: Scott Chase Waggener, Lakshman Tamil
Abstract: Breast arterial calcification (BAC) on screening mammograms is an emerging cardiovascular risk biomarker, but quantitative use requires reproducible segmentation and expert pixel-level labels are costly. We present BAC-JEPA, a label-efficient segmentation framework trained on procedurally generated arterial calcification inserted into real mammographic backgrounds with exact masks. Candidate backgrounds were selected from model-screened mammograms with low predicted BAC response; the generator samples arterial structure, disease burden, radiographic appearance, and hard-negative distractors including nonarterial calcifications and metallic objects. Synthetic masks are paired with mammography self-supervised Vision Transformer encoders and a high-resolution convolutional decoder to produce full-resolution segmentation maps. The study used 75,472 mammography studies from 34,956 patients for background selection and representation learning, trained on synthetic images from 10,000 backgrounds, selected checkpoints with 1,000 development backgrounds, and evaluated transfer on all 1,000 human-labeled BacSeg synthetic 2D mammograms. On held-out synthetic validation data, the larger backbone achieved IoU 0.5325 and Dice 0.6357. On BacSeg, image-level classification from segmentation probability maps reached AUROC 0.8719, with 0.8547 for the smaller backbone. Four-view inference required 110.68--213.63 ms on an RTX 5090 GPU, and severe-preset synthetic image generation averaged 2.7071 s per image on a multicore workstation. These results indicate that BAC-specific synthetic supervision can produce useful image-level transfer without human pixel-level training masks, while expert-reviewed real-mammogram segmentation remains necessary for clinical validation and calibration.
Authors: Taeho Kang, Nairan Zhang, Yelin Kim, Yujiao Shi, Youngki Lee
Abstract: Accurate yaw estimation is a bottleneck in cross-view localization between ground view and Bird's Eye View (BEV). Existing methods couple yaw with translation and rely on height or projection assumptions that degrade under large yaw ambiguity. We disentangle yaw from location accuracy and introduce LAYS, a radially invariant line-consensus voting method. By exploiting the radial invariance of our formulation, we achieve sub-degree yaw precision via 3D voting over all candidate poses, while eliminating the need for accurate location. Our key observation is that a ground-image column matched to BEV pixels induces the same yaw across all camera positions along the radial direction of the pixels. LAYS matches BEV pixels to ground columns using feature similarity and accumulates the induced yaw votes into discrete 3D bins, where correct correspondences along the radial line concentrate into a sharp peak for the correct yaw. Experiments on Mapillary, Ford, KITTI, and VIGOR show significant gains under unknown yaw, particularly for normal FoV with unknown yaw (+28$\sim$45\%p), and using LAYS as a yaw prior improves downstream 3-DoF localization.
Authors: Zeyu Xia, Kan Ma, Sibo Cheng, Thomas Blackburn, Ziling Peng, Kewei Zhu, Weihang Zhang, Dunhui Xiao, Alexander J Knowles, Rossella Arcucci
Abstract: The performance of advanced materials for extreme environments is underpinned by their microstructure, including the size and distribution of reinforcing phases. Chromium-based superalloys are a recently proposed alternative to conventional face-centred-cubic superalloys for high-temperature applications, such as Concentrated Solar Power, and their development requires efficient measurement of precipitate volume fraction and size distribution from electron microscopy images. Traditional fixed-threshold image processing is sensitive to background noise, generalises poorly across materials, and requires substantial manual measurement effort. To address these bottlenecks, this study proposes DT-SegNet, an end-to-end two-stage deep learning scheme based on YOLOv5 and SegFormer for object detection and segmentation in electron microscopy images. The approach combines the training efficiency of convolutional neural networks at the detection stage with the segmentation accuracy of a Vision Transformer. Numerical experiments show that DT-SegNet substantially outperforms state-of-the-art segmentation tools offered by Weka and ilastik across metrics including accuracy, precision, recall, and F1-score. The model provides a useful tool for alloy-development microstructure examinations and helps address the large datasets associated with high-throughput alloy development.
Authors: Ronald L. P. D. de Jong, Tim J. M. Jaspers, Raf A. H. Vervoort, Aron F. H. A. Bakker, Yiping Li, Jip L. Tolenaar, Jelle P. Ruurda, Willem M. Brinkman, Josien P. W. Pluim, Marcel Breeuwer, Daan de Geus, Fons van der Sommen
Abstract: Accurate recognition of anatomical structures is essential for safe and effective minimally invasive surgery (MIS), yet it remains underexplored in surgical computer vision due to limited annotated data and methods tailored primarily to natural scenes. In this work, we present a combined dataset and model framework to advance anatomy-aware perception in MIS. First, we introduce ATLAS-120k, a large-scale clip-level semantic segmentation dataset comprising over 120,000 annotated frames from 100 surgical videos spanning 14 procedures and multiple modalities, including laparoscopic and robot-assisted surgery. The dataset captures substantial procedural variability and was created using a scalable annotation pipeline that integrates expert manual labeling, automated propagation, iterative refinement, and surgeon verification to ensure high-quality annotations. Second, we propose ATLAS (Anatomy Recognition with Context Learning using Foundation Representations), a video semantic segmentation model specifically designed for surgical anatomy recognition. Unlike conventional approaches that emphasize object tracking, ATLAS leverages foundation-model embeddings together with lightweight temporal reasoning to incorporate contextual cues such as procedure type, surgical phase, and short-term visual memory. This design enables temporally consistent and accurate predictions while maintaining real-time feasibility. Together, the dataset and model establish a practical foundation for robust surgical scene understanding and support the development of clinically applicable guidance systems for minimally invasive surgery. The models, dataset annotations and annotation platform are publicly available at: https://github.com/TimJaspers0801/ATLAS.
Authors: Hiroki Nishizawa, Hubert P. H. Shum, Yoshihiro Fukuhara, Hirokatsu Kataoka, Shigeo Morishima
Abstract: 4D dynamics (3D geometry evolving over time) is a fundamental representation of the physical world and plays a crucial role in world modeling (e.g., animation and games). Owing to the scarcity of large-scale, long-horizon 4D mesh data with arbitrary shapes, early text-to-4D methods rely on distillation or test-time optimization from video diffusion priors, making inference prohibitively slow. Recent feed-forward generators greatly reduce inference cost but offer limited spatiotemporal controllability, and short-horizon generation often leads to error accumulation in long-horizon sequences. We propose a novel feed-forward in-betweening framework for arbitrary 4D meshes with keyframe conditioning. Building on universal mesh-animation latents, we introduce a frame-wise mesh VAE that encodes each frame into topology-agnostic latent tokens anchored by a reference mesh for keyframe conditioning. We further introduce a keyframe-conditioned rectified flow model with an MMDiT backbone that synthesizes non-keyframe frames conditioned on sparse keyframes. Experiments show strong performance and improved controllability on both DyMesh16 and DyMesh32 benchmarks.
Authors: Niyoj Oli, Sachin Acharya, Sandesh Pokhrel, Sanjay Bhandari, Ramesh Rana, Nikesh Mani Shrestha, Ram Bahadur Gurung, Yash Raj Shrestha, Prashnna K Gyawali, Binod Bhattarai
Abstract: Gastrointestinal cancers represent a growing health burden in the South Asian region, driven largely by rapid changes in socio-economic conditions & lifestyle habits. However, early diagnosis of such malignancies remains a significant challenge, largely due to a lack of modern equipment, lack of financial support, and a scarcity of GI experts. AI-assisted diagnosis & report generation, show great promise in alleviating this problem by providing low-skill manpower the technical expertise to perform diagnosis. However, almost all open-source, publicly available datasets are predominantly collected from the European region, with no representation from the South Asian region. The lack of open-source GI datasets from diverse geographic regions has made it difficult to assess whether population bias is present in existing models, and to develop geographically inclusive AI tools for automated GI diagnosis. To address this gap, we introduce SAGE: An Expert-Annotated South Asian GI Endoscopy dataset for image captioning, multi-label classification, and visual question answering (VQA) tasks. It consists of 1,300 images, their captions along with hallucination tag, 18 labels and 14,726 question-answer pairs making it well-suited for diverse range of tasks including classification, benchmarking, and fine-tuning large multimodal models (LMMs). We further conducted benchmarking of multi-class classifiers on the effect of population shift in GI imaging AI tasks, and contemporary LMMs on their performance. Our study reveals that task-specific models, such as multi-class classification models, suffer the most, with an average performance drop of 58% when evaluated on the South Asian dataset. For contemporary LMMs, benchmarking reveals a substantial drop in the average GREEN score for anatomical landmark detection (0.308) and abnormality detection (0.410).
Authors: Sourabh Sharma, Sonam Gupta, Sadbhawna Thakur
Abstract: Achieving human-like reasoning in Vision-Language Models (VLMs) remains a long-standing challenge. Recent approaches leverage Chain-of-Thought (CoT) rationales generated by human annotators or proprietary models to improve reasoning, which is costly and difficult to scale. Self-training offers a promising alternative by using models own outputs as supervision. However, existing methods often suffer from visual hallucinations -- where rationales describe non-existent visual content, and language shortcuts -- where predictions rely on textual priors rather than true visual grounding, as rationales are typically filtered only by answer correctness without verifying visual perception. To address this limitation, we propose a perception-verified self-training framework that enforces visually grounded reasoning. First, our method employs a CoT template (caption-reasoning-conclusion) that disentangles perception from reasoning, enabling independent verification of visual understanding. To compensate for the absence of ground-truth captions, we propose PerceptEval, an unsupervised method that evaluates caption quality based on its alignment with visual and textual elements present in the image. Using caption verification together with answer correctness, we partition the data into three subsets: easy (correct caption and conclusion), medium (correct caption but incorrect conclusion), and hard (incorrect caption). Building on this partitioning, we design a two-stage curriculum learning strategy. In Stage 1, the model is trained on easy examples and subsequently in Stage 2, medium samples are incorporated through a caption-guided reasoning enhancement procedure that regenerates reasoning conditioned on verified captions. Only regenerated samples with the correct conclusions are retained.
Authors: Khoa Pham, Sindhuja Penchala, Jiacheng Li, Andy Perkins, Noorbakhsh Amiri Golilarz
Abstract: Medical image segmentation plays an important role in computer aided diagnosis, treatment planning, and disease monitoring. U-Net has been widely used for biomedical image segmentation because of its encoder decoder structure and skip connections. However, conventional convolution based U-Net models may have limited ability to capture long range dependencies and global contextual information, which can affect performance in complex segmentation tasks. This paper presents a comparative study of five U-Net based architectures: U-Net 3D, Residual U-Net, Attention U-Net, UNETR, and Swin UNETR. The models are evaluated on two benchmark datasets: BraTS 2023 for brain tumor segmentation and DRIVE for retinal vessel segmentation. Experimental results show that Swin UNETR achieves the best overall performance, with Dice scores of 0.8965 on BraTS 2023 and 0.8078 on DRIVE. The results suggest that transformer based U-Net variants are effective for segmentation tasks requiring global contextual modeling, while residual learning remains useful for fine structure segmentation. This study provides practical insights into model selection for medical image segmentation across volumetric MRI and retinal imaging tasks.
Authors: Ninon Liz\'e Masclef, Taisija Demcenko, Antonella Catanzaro, Nataliya Kosmyna
Abstract: This paper explores a novel brain decoding model for 3D shape perception through a dual pathway architecture mirroring biological vision. Our bio-inspired approach implements separate decoding modules for object identity and spatial orientation, inspired by ventral and dorsal pathways, during continuous rotations. We employ circular regression for angle prediction and develop EEG-conditioned multiview diffusion for 3D reconstruction. Our approach successfully decodes both object identity and spatial orientation from EEG signals and enables 3D reconstruction from neural activity, with interpretability analyses revealing temporally structured involvement of ventral, dorsal, and motor-related channels rather than a static ventral dominance in supporting object and angle decoding.
Authors: Meng Hua, Chenghong Bian, Deniz Gunduz
Abstract: Orthogonal frequency division multiplexing (OFDM)-based integrated sensing and communication (ISAC) systems commonly extract target parameters by peak-searching a delay-Doppler map (DDM) constructed from reflected pilots. In multi-target scenarios, this results in ambiguity: the DDM does not reveal which physical target produced which peak, and two targets within the same delay-Doppler resolution cell cannot be separated. We propose a vision-assisted OFDM-ISAC framework that resolves both limitations by fusing wireless and visual modalities. The transmitter encodes an onboard street-view image with deep joint source-channel coding (DeepJSCC) and transmits it over the same OFDM waveform used for sensing; the receiver reconstructs the image, runs a fine-tuned YOLOv5 detector and fuses the resulting per-target features (bounding-box coordinates and class labels) with the DDM and transmitter-receiver geometry through a learned multi-modal network. To stabilize training of the high dimensional delay and Doppler classifiers, we introduce a Kullback Leibler loss against triangular soft labels centered on the ground-truth bin. On a Blender-rendered vehicular testbed, the proposed framework achieves a 16 cm localization root mean square error (RMSE) and a 10.8 ns delay RMSE. An ablation study confirms that removing the visual modality causes a 60x degradation in localization. These results highlight the potential of vision to overcome the data-association and resolution limits of single-modality ISAC.
Authors: Rui Wang, Quentin Lohmeyer, Siyu Tang, Mirko Meboldt
Abstract: Dynamic 3D Gaussian splatting faces a fundamental tension between motion consistency and visual fidelity. Deformation-based approaches preserve temporal correspondence but suffer from motion over-factorization, oversmoothing high-frequency dynamics. In contrast, 4D-primitive methods capture fine visual details yet incur temporal overparameterization, breaking object identity and leading to severe storage overhead. To resolve this, we introduce Multi4D, a framework for high-fidelity dynamic Gaussian Splatting based on multi-level competitive allocation. Instead of a monolithic representation, we distribute modeling capacity across three structured levels: static structure, persistent dynamic geometry, and transient appearance primitives. Through shared rasterization and residual-driven optimization, these levels dynamically compete to explain photometric error, enabling adaptive specialization without pre-assigned decomposition. This allocation preserves long-term motion consistency while capturing fine dynamic detail, achieving state-of-the-art rendering quality and real-time performance with significantly fewer dynamic primitives. Furthermore, because our representation explicitly tracks compact persistent Gaussians over time, semantic features can be embedded afterward, enabling Multi4D to achieve state-of-the-art 4D segmentation accuracy with an order-of-magnitude speedup. Project page: https://batfacewayne.github.io/Multi4D.io/
Authors: Wenhao Wang, Franziska Boenisch, Michael Backes, Adam Dziedzic
Abstract: Memorization in machine learning models enables high performance on rare in-distribution samples by capturing their atypical patterns. However, it also causes harmful retention of noise and outliers, degrading generalization. While memorization has been extensively studied in both supervised and self-supervised learning in the vision domain, it remains unexplored in multi-modal contrastive learning. We address this gap by introducing MultiMem, the first metric designed to quantify memorization in multi-modal contrastive learning. Through our systematic analysis, we demonstrate that cross-modal semantic misalignment has the strongest influence on memorization, with text being the dominant modality driving memorization, followed by video, image, and audio. We show that targeted augmentations applied across all modalities effectively reduce memorization as measured by our MultiMem metric and improve model performance. Overall, this work establishes the first framework for measuring and mitigating memorization in multi-modal contrastive learning, preventing harmful data retention and contributing to higher-performing models.
Authors: Mohamed Dhouib, Ye Zhu, Sonia Vanier, Aymen Shabou
Abstract: Localizing document tampering is extremely challenging, as manipulations are crafted to appear visually consistent and often leave only subtle traces that are nearly invisible to the human eye. In prior work, evaluation has been largely dominated by synthetic benchmarks that closely match the training distribution, and methods have shown steady progress under this setting. However, these gains often translate poorly to human-made forgeries and to cross-domain evaluation, where both the source documents and the tampering pipeline can change, leading to a distribution shift. In addition, since the introduction of the Frequency Perception Head for the discrete cosine transform (DCT) modality, it has become a standard choice, and subsequent work has largely focused on downstream modules and fusion strategies rather than revisiting the backbone itself. To help close this gap in cross-domain performance and improve the DCT backbone design, we propose \textbf{DiffNet}, a relatively simple yet effective RGB--DCT early-fusion architecture driven by two key design choices. First, to ensure that the decoder aggregates multi-scale inconsistency evidence rather than operating on raw, content-heavy activations, we apply a lightweight multi-level discrepancy transformation at the output of each backbone stage, replacing features with magnitude-only responses to learned zero-sum filters. Second, we design an efficient DCT-domain backbone that relies on a lightweight frequency-index-aware DCT--quantization joint embedding. Our approach achieves state-of-the-art performance on cross-domain and human-made document tampering localization, outperforming prior methods by around 30\%, with up to $7\times$ higher throughput than the previous best model.
Authors: Xiwen Li, Xiaoya Tang, Bodong Zhang, Tolga Tasdizen
Abstract: Idling Vehicle Detection (IVD) seeks to determine, at the final frame of a video clip, whether any vehicle is idling, meaning the vehicle is stationary with its engine running, using synchronized video from a remote surveillance camera and multichannel audio captured by spatially distributed wireless microphones along the roadside. Prior full-image, clip-level fusion approaches tend to overfit scene background and full-frame context, produce unstable temporal decisions, and lack an explicit spatial prior to align vehicles with microphones, which makes them brittle under domain shift and data inefficient. Instead, we introduce TAVR-IVD, an audio-visual framework guided by multi-object tracking. Our method detects vehicles, links detections into tracklets, and classifies each vehicle by operating on its tracklet. This design raises the effective signal-to-noise ratio, stabilizes temporal decisions through tracklets, enforces an explicit spatial prior to align vehicles with microphones, and adapts across domains with limited calibration annotations while remaining detector agnostic and efficient. To evaluate deployment robustness, we further curate two evaluation extensions, AVIVD-LT and AVIVD-M, covering inter-day and cross-site shifts.
Authors: Gagandeep Singh, Aaditya Yadav, Priyanka Singh
Abstract: Recent advances in vision-language models and generative editing systems have made it increasingly easy to produce persuasive multimodal misinformation by altering images, text, or both jointly. However, existing datasets focus mainly on authenticity, out-of-context mismatch, or manipulation type, and rarely capture how strongly an edit changes the likely interpretation of a post. We introduce T-IMPACT, a first-release severity-aware benchmark for manipulated news-style image-text pairs. T-IMPACT contains 98,786 examples spanning pristine, image-only, text-only, and joint manipulations, with a calibrated continuous severity signal, coarse low/medium/high labels, and supporting grounding metadata. Starting from a news image-text pair, the pipeline extracts semantic anchors, grounds them spatially, performs localized image edits and constrained caption rewrites, and calibrates contextual-impact scores using limited human ratings. In this release, the calibrated continuous score is the primary severity target, while the low/medium/high bands should be interpreted as coarse operating buckets rather than balanced classes. Experiments show that current models recover some authenticity signal, but severity prediction remains substantially harder and only weakly aligned with human judgment. T-IMPACT provides an initial benchmark for studying multimodal manipulation beyond binary real/fake classification toward graded contextual impact.
Authors: Junxiong Lin, Haoran Wang, Xinji Mai, Zeng Tao, Xuan Tong, Ivy Pan, Wenqiang Zhang
Abstract: Identity-Preserving Text-to-Video Generation (IPT2V) seeks to synthesize a temporally coherent video from a reference image and a textual description, while simultaneously preserving the subject's identity and allowing fine-grained control over facial dynamics. Although recent methods such as ID-Animator and ConsisID inject identity features only at inference time, they ignored the ID-irrelevant information contained in Facial embedding, leading to monotonous or inaccurate facial movements that poorly follow the prompt. We introduce Identity-Action Decoupling (IaD) framework as well as two loss function Identity Decoupling Loss and Text Alignment Loss to solve this problem. Without any subject-specific fine-tuning, IaD yields videos that (1) maintain cross-temporal identity consistency and (2) exhibit rich, controllable expressions and scene variations that closely match the input text.
Authors: Junxiong Lin, Xinji Mai, Qianyu Guo, Haoran Wang, Zeng Tao, Xuan Tong, Ivy Pan, Wenqiang Zhang
Abstract: Fidelity and perceptual quality are two inherently competing and conflicting objectives in the image super-resolution (SR) task. Different loss functions focus on these objectives to varying extents. Regression losses enhance the model's fidelity but lack sufficient attention to high-frequency details, resulting in a loss of fine details. In contrast, perception losses improve the model's visual quality but may introduce undesirable artifacts. Balancing these two optimization goals can be viewed as a Multi-Objective Optimization problem. Existing methods are limited to cautiously adjusting weight parameters between these losses, overlooking the underlying Interest Entanglement problem. To address this problem, we explore the inherent frequency-domain conflict between the regression objective and the perceptual objective, and analyze the causes of Interest Entanglement in SR tasks. According to our findings, we propose the Shared-Feature-Representation based Super-Resolution framework (SFR), which decouples the learning process of different optimization objectives, allowing the model to explore a common optimization direction for both goals and achieve an effective balance between them. To better leverage shared features, we also proposed the InfoSqueeze module, which filters redundant information through a dimensionality reduction and expansion process, effectively transforming features into a consistent space. Quantitative and qualitative experiments across five representative datasets affirm the superiority of SFR.
Authors: Shuning Chang, Weihua Chen, Jiasheng Tang, Hao Xu, Zeyu Zhang, Hangjie Yuan, Yu Lu, Ruigang Niu, Fan Wang, Bohan Zhuang, Yi Yang
Abstract: Recent advances in video generation have made minute-level synthesis possible; however, generating long videos remains challenging due to error accumulation, attribute drift, and the limited availability of long video data. In this paper, we introduce an infinite-length video generation framework that focusing on addressing these issues and produces high-quality, dynamic, and identity-consistent single-shot long videos. We first finetune a diffusion model as a video extension model on large-scale short video data to autoregressively generate temporally coherent clips. Inspired by the success of large language models (LLMs), we adopt causal attention computation between clips to further finetune this model on long video data. In this way, the tokens in one clip (short video) are computed by bidirectional attention while tokens among clips are computed by unidirectional attention. This design leverages the strengths of modern diffusion models while preserving long-term context information, effectively mitigating error accumulation and attribute drift. To achieve memory efficiency during inference, we adopt a key-value (KV) caching mechanism to maintain a constant KV memory. Furthermore, we introduce truncation-rectified flow (T-RFlow) technique to further suppress error accumulation. Experimental results demonstrate the effectiveness of our method. Our framework establishes a new benchmark for realistic and coherent minute-level video synthesis.
Authors: Wen Guo, Fulong Cai, Wuzhou Quan
Abstract: Event cameras enable high-frequency visual perception with microsecond latency, offering advantages for dynamic scenes. However, event-based small object detection remains challenging due to sparse asynchronous measurements and weak object responses that are easily disrupted by noise. Limited spatial support causes small-object signals to lose temporal continuity, resulting in fragmented and unstable predictions. To address this issue, we propose a physics-guided advection-consistent modeling framework, termed PACT, which formulates event evolution as a motion-driven feature transport process. Instead of relying solely on local spatio-temporal aggregation, PACT propagates features along estimated velocity fields and enforces trajectory-level consistency through advection constraints. This design preserves weak event responses over time and prevents their degradation under complex background interference. Technically, PACT integrates motion-aware feature extraction with a differentiable advection-based transport operator, enabling coherent motion representation and effective noise suppression during temporal evolution. Extensive experiments on benchmark event-based datasets demonstrate that PACT consistently outperforms state-of-the-art methods, achieving improvements of 20.72\% in IoU and 15.03\% in accuracy while maintaining comparable computational efficiency. The code is publicly available at https://github.com/fulongcai/PACT.
Authors: Edwin Kwadwo Tenagyei, Lei Wang, Ugochukwu Ejike Akpudo, Jun Zhou, Yongsheng Gao
Abstract: Parameter-efficient fine-tuning (PEFT) has become a practical solution for adapting large pretrained vision transformers (ViTs) to downstream tasks while updating only a small subset of parameters. However, existing adapter-based methods perform adaptation independently for each token, implicitly assuming that token refinements should be learned in isolation. This token-wise formulation overlooks the structured relationships among tokens that naturally arise in visual scenes, potentially leading to redundant updates and spatially inconsistent feature refinement. In this work, we revisit the design of parameter-efficient adapters and propose to perform adaptation in hyperedge space rather than token space. We introduce HyperAdapter, a hypergraph-based adapter architecture that enables structured, group-aware adaptation through soft token routing. HyperAdapter constructs a soft hypergraph over ViT tokens using prototype-based assignments, aggregates token features into latent hyperedge representations, applies lightweight bottleneck adaptation at the hyperedge level, and diffuses the resulting updates back to tokens via the hypergraph incidence structure. This design injects an explicit structural inductive bias into PEFT while preserving the modularity and efficiency of standard adapters. Extensive experiments across diverse visual benchmarks demonstrate that structured hyperedge adaptation consistently outperforms strong PEFT baselines under comparable parameter budgets, with particularly pronounced gains on tasks requiring structured reasoning. Our results suggest that the choice of adaptation space is a critical yet underexplored dimension in parameter-efficient transfer for ViTs.
Authors: Songtao Tian, Guhan Chen, Bohan Li, Jingyi Ma, Zixiong Yu
Abstract: Consistency distillation has significantly accelerated the inference of diffusion models. In this work, we reveal an intriguing asymmetry: while Logit-Normal sampling priors are highly efficacious for standard iterative generation, consistency distillation exhibits a distinctly different difficulty profile (e.g., U-shaped). We identify that the primary optimization bottlenecks reside at the boundary stages (initialization or final refinement) rather than the intermediate steps. To address the limitations of static sampling in accommodating evolving learning requirements, we propose Curvature-Adaptive Consistency Flow Matching (CACFM). By formulating distillation as a dynamic decision process, CACFM employs a lightweight Reinforcement Learning agent to actively probe Probability Flow ODE trajectories, automatically constructing an efficiency-oriented curriculum that prioritizes critical regions without manual scheduling. Integrated with a novel Flow Distribution Matching Distillation (DMD) objective, our approach achieves new state-of-the-art results on large-scale models such as FLUX and SDXL. It effectively mitigates structural deformities and preserves high-frequency details in extreme few-step regimes, achieving unprecedented visual fidelity.
Authors: Vasileios E. Papageorgiou, Georgios Petmezas, Dimitrios-Panagiotis Papageorgiou, Leandros Stefanopoulos, Nicos Maglaveras
Abstract: This study introduces a computationally efficient convolutional neural network (CNN) architecture enhanced with transfer learning for multi-cancer detection using biomedical images. The proposed lightweight CNN model is designed to reduce computational complexity while maintaining high classification performance, making it suitable for deployment in resource-constrained environments. We evaluate this approach on three distinct tumor datasets comprising brain magnetic resonance imaging (MRI) and lung and kidney computed tomography (CT) scans. The model achieves test accuracy of 90.85 +- 2.22%, 98.64 +- 2.43% and 99.92 +- 0.08% for brain, lung, and kidney cancer classification, respectively, using 5-fold stratified cross-validation (CV). Transfer learning is employed by pretraining the model on one cancer type and fine-tuning it on the others, requiring only 20 additional epochs to achieve performance comparable to models trained from scratch. The fine-tuning process involves updating the classification part of the CNN and requires approximately 0.014 seconds per image per epoch using an NVIDIA GeForce GTX 960. Comparative evaluations show that the proposed model outperforms several state-of-the-art pretrained architectures, such as Xception, VGG16, VGG19, MobileNetV2 and DenseNet121. Overall, the model's effectiveness is evaluated across three types of cancer with distinct morphological characteristics, assessing its performance on both MRI and CT imaging modalities and demonstrating robust performance across diverse tasks and data types. These findings underscore the potential of streamlined deep learning (DL) frameworks in accelerating cancer diagnosis without sacrificing accuracy, especially in settings with limited computational resources.
Authors: Haodi Liu, Xinhang Yang, Kunda Yan, Sen Cui, Zeyu Zhang, Changshui Zhang
Abstract: Robots operating in everyday environments must understand fine-grained human actions, intentions, and contextual cues from broad views where people occupy only small regions, a capability unmet by current systems. While open-vocabulary action recognition methods remain limited to assigning predefined labels, and vision-language models (VLMs) face an inherent trade-off between informational richness and factual fidelity in their outputs, neither approach achieves the deep semantic interpretation required for reliable human-robot interaction. We propose Gold Points Sniper (GPS), a novel framework that empowers lightweight VLMs with self-guided multimodal reasoning capabilities for fine-grained human action understanding. Our approach comprises three key modules: Gold Points Extractor trains VLMs to identify critical action-relevant details, Selective Socratic Questioner validates and refines these details through selective self-questioning, and Semantic Entailment Evaluator quantitatively assesses factual consistency using semantic entailment classification. Extensive experiments on our curated instruction-tuning dataset based on the CAP benchmark demonstrate that GPS-enhanced lightweight VLMs achieve substantial performance improvements, with some models reaching performance comparable to proprietary GPT-4o while maintaining superior factual accuracy. Our work establishes a reliable foundation for fine-grained action understanding in domestic robotics, enabling robots to safely interpret human behavior through information-dense yet factually grounded descriptions. Source code, training configurations, annotation prompts, and dataset details are released at https://github.com/Haodi-Liu/GPS-Gold-Point-Sniper.
Authors: Prajwal Gatti, Simon Jenni, Fabian Caba Heilbron, Dima Damen
Abstract: We address the problem of training on long-tailed data for video action recognition. We propose to augment the training set using a text-to-video generative model, conditioned on diverse text prompts grounded in action profiles and training exemplars. Our approach, called Gen2Balance, converts an imbalanced training set into a balanced combination of real and generated video clips. To effectively learn from such data, we employ a two-stage training strategy that mitigates domain shift and yields significant improvements. We evaluate on long-tailed versions of standard benchmarks: UCF-101 (UCF-LT) and a 100-class subset of Kinetics (K100-LT) selected to prioritise temporally challenging actions. Gen2Balance improves accuracy over the strongest baselines for long-tailed learning by 5.1% and 7.0% on the respective datasets. On rare actions from the RareAct dataset (e.g., cut keyboard), Gen2Balance improves accuracy by 31.9%, demonstrating effectiveness for scarce actions. By varying the amount of synthetic data added, we show that partial balancing already achieves 79% of the performance gains at 27% of the compute cost on K100-LT, highlighting the practical scalability of Gen2Balance.
Authors: Yufei Zhang, Changhao Chen
Abstract: Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires agents to follow natural-language instructions in unseen scenes. While Large Models (LMs) have advanced VLN-CE, their performance remains severely degraded by real-world visual corruptions, a critical yet underexplored domain constraint. We introduce Temporal Conditional Flow Decorruptor (FlowDec), a novel image restoration framework tailored for LM-based VLN-CE. FlowDec integrates a hybrid temporal conditioning strategy to align the generative flow path with historical context and employs action-centroid guided filtering to dynamically assess and integrate outputs. Extensive experiments demonstrate that FlowDec outperforms state-of-the-art decorruption methods in both navigation accuracy and generation latency. Our approach establishes a robust, efficient paradigm for resilient embodied navigation in unpredictable real-world conditions.
Authors: Wenzhen Yuan, Jiacheng Ruan, Wutao Xiong, Chengping Zhao, Ting Liu, Yuzhuo Fu
Abstract: We conduct a systematic study of 18 widely used vision-language benchmarks and identify three major issues: 1) many items do not rely on visual cues and therefore fail to effectively measure multimodal understanding; 2) many items are already close to performance saturation for current LVLMs, which limits their discriminative power; 3) a small number of anomalous items affect the reliability of evaluation results. To this end, we propose MMGist, a curated benchmark that covers seven capability dimensions and contains 7,262 items. MMGist is constructed through a three-stage pipeline, which sequentially combines text-ablation filtering, cross-model saturation filtering, and anomaly detection filtering. We conduct extensive experiments on 27 leading LVLMs and compare MMGist with the raw pool of 23,250 items. The results show that MMGist preserves model rankings with high fidelity, with Spearman $\rho = 0.98$, while reducing evaluation items by 69\% and improving cross-model discrimination by 78\%. Further results indicate that Visual Logic remains a systematic weakness of current LVLMs, while knowledge-intensive dimensions such as Expert Knowledge dimensions remain important factors for distinguishing closed-source models from open-source models. These findings suggest that high-quality evaluation should prioritize visual dependency, discriminative power, and reliability, rather than simply pursuing benchmark scale.
Authors: Manveen Kaur, Rajmeet Singh, Saeed Mozaffri, Shahpour Alirezaee
Abstract: Commercial greenhouse cucumber production is graded by fruit length, which drives harvest scheduling, labour allocation, and logistics. Manual measurement with thread or caliper is accurate but infeasible at commercial scale. This paper presents CucumberVision, a non-contact length estimation framework using an Intel RealSense D435 RGB-D camera. A YOLO26n instance segmentation model locates cucumbers, and SAM (ViT-B backbone) refines each detection to a pixel-precise mask. Five methods are evaluated under matched conditions: (M1) a dominant-axis skeleton scan-line baseline; (M2) PCA on the bounding-box depth point cloud; (M3) SAM mask with medial-axis skeletonisation; (M4) a hybrid keypoint-guided approach using a YOLO26-pose model predicting five anatomical landmarks (KP0--KP4) with piecewise 3D arc-length; and (M5) a novel medial arc spline method fitting a cubic spline through the 3D medial axis of the SAM mask and computing arc length by trapezoidal integration -- the first such application to elongated vegetable measurement. All methods share five-frame burst depth averaging, colour-stream intrinsic alignment, and adaptive method selection with cascading fallbacks ensuring 100% coverage. A benchmark of 48 captures across seven cucumbers in three size categories (small ~8 cm, medium ~13 cm, large ~25 cm) with thread-based ground truth establishes a significant accuracy hierarchy: M1 (MAPE 9.68%) > M2 (5.31%) > M4 (5.51%) > M3 (5.82%) > M5 (4.13%). M5 significantly outperforms all competitors at Bonferroni-corrected alpha=0.0125. A secondary contribution is identifying a 12--18% length underestimation caused by using depth-stream rather than colour-stream intrinsics after rs.align(rs.stream.color) -- an under-reported error source. The complete system is released open source and runs in real time on a single consumer-grade GPU.
Authors: Quanyuan Ruan, Jiabao Lei, Xingyi Du, Xifeng Gao
Abstract: UV parameterization is a fundamental step in 3D content creation, yet producing production-ready UV layouts remains challenging due to the gap between geometric distortion objectives and the stylistic preferences of professional artists. While classical methods optimize handcrafted energy functions, artist-authored UVs exhibit structural patterns such as straightened seams, axis-aligned islands, and flexible interior deformation, properties that are difficult to explicitly formulate. In this work, we present DreamUV, an end-to-end learning framework that formulates UV unwrapping as a generative Flow Matching problem. Rather than predicting a single optimal parameterization, DreamUV learns a mesh-conditioned transport process that maps noise samples to a distribution of artist-like UV layouts. To reflect real-world authoring practices, we introduce a boundary-aware training strategy that prioritizes seam geometry, and a Model-in-the-Loop Finetuning(MITL) scheme that explicitly accounts for discretization errors during sampling and stabilizes transport dynamics under heterogeneous supervision. We evaluate DreamUV on a large-scale dataset of professionally authored UV layouts. Experiments demonstrate that our method produces significantly straighter boundaries and tighter axis-aligned islands than both classical and learning-based baselines, while maintaining competitive distortion metrics. Qualitative results and a user study with professional artists further confirm that DreamUV generates UV layouts that are not only valid, but aligned with practical production requirements.
Authors: Ruixun Liu, Lingyu Zhang, Lanxuan Xue, Kaiyu Li, Bowen Fu, Xiangyong Cao
Abstract: Humans can effortlessly reason about scenes across different viewpoints, yet it remains unclear whether Vision-Language Models (VLMs) possess similar cross-view spatial abilities. Satellite-street scene pairs, with their complex contexts and extreme viewpoint variations, provide an ideal testbed. Motivated by this, we introduce CVSBench, a large-scale benchmark for evaluating cross-view spatial reasoning through satellite-street pairs. This benchmark supports multiple tasks, including cross-view VQA, cross-view grounding, and viewpoint identification. CVSBench comprises 3,297 cross-view image groups with 9,468 object-level annotations and 40,679 question-answer (QA) pairs, enabling systematic and controlled evaluation of cross-view spatial reasoning. Extensive evaluations reveal that advanced VLMs struggle to maintain object-level and layout consistency under drastic viewpoint changes. To bridge this gap towards human-like spatial cognition, we investigate two categories of approaches: spatially grounded reasoning and the incorporation of cognitive map inputs. Our findings demonstrate that language-only reasoning yields marginal improvements, while incorporating visual spatial imagination via a 3D scene imagination pipeline substantially improves cross-view reasoning. These results highlight the necessity of explicit visual-spatial representations for robust spatial cognition in VLMs. Our data and code are released at https://huggingface.co/datasets/zlyzlyzly/CVSBench.
Authors: Xingyun Liu, Yuqi Li, Jinhui Xiang, Pinyan Tang, Chong Wang
Abstract: Projection Mapping (PM) enables seamless superimposition of digital content onto real-world 3D objects, serving as a fundamental technique for immersive visualization, digital twins, and interactive art. Although text-to-image diffusion models have greatly facilitated customized content creation, directly integrating them into practical PM pipelines remains challenging due to the mismatch between idealized 2D generation and physical constraints. To bridge this gap, this paper formalizes two application-level generative paradigms: the cooperative paradigm (harmonizing generated semantics with physical attributes) and the adversarial paradigm (eliminating surface interference via radiometric compensation). Based on this, we propose ConPhyG, a unified controllable physically-guided generative multi-projection mapping framework that enables creators to interactively adjust physical constraints and flexibly switch generative paradigms. In cooperative mode, multi-dimensional physical priors (per-pixel gamut, depth, and edges) are injected into the diffusion process. In adversarial mode, the framework releases the generative potential and applies bounded numerical optimization for multi-projector radiometric compensation. It allows users to dynamically switch constraints to balance artistic freedom with physical feasibility. Furthermore, we extend ConPhyG to 360-degree multi-view consistent PM using a sequential generation strategy. Quantitative and qualitative evaluations on a real-world four-projector setup demonstrate that ConPhyG significantly outperforms state-of-the-art methods in geometric alignment, gamut utilization, and semantic fidelity.
Authors: Hongqiao Dong, Wenhao Chi, Ruobing Liang, Xiaokui Yang, Wenhua Liang, Peng Hou, Wenjun Pu, Yipeng Zhao, Ping Chen, Haiping Liu, Jianxing He, Bo Liu
Abstract: Medical expert annotators are scarce, and blind reliance on artificial intelligence (AI) can be misleading, motivating approaches in which humans, particularly junior medical trainees or even non-medical personnel, collaborate with AI to achieve robust medical segmentation. Although the Segment Anything Model (SAM) shows promise for general-purpose image segmentation, its performance in human-AI collaboration for specialized medical tasks has not been thoroughly evaluated. Here we present Hi-Seg, a human-in-the-loop segmentation framework for pulmonary nodules built on SAM. Humans iteratively refine prompts through trial-and-error learning and semantic reasoning, progressively guiding SAM toward higher-quality masks. Using chest CT scans from 1,179 patients across 12 centers, we conducted the first large-scale external validation of collaborative human-SAM segmentation. Across all annotator groups, Hi-Seg achieved a mean Dice score of almost 85%, outperforming five state-of-the-art deep learning models by 10-22% and 13 SAM variants by 1-29%. Hi-Seg improved segmentation accuracy while reducing annotation time for medical annotators, and briefly trained non-medical annotators achieved performance comparable to that of the junior medical student. These findings suggest that human-in-the-loop segmentation can reduce clinician workload, enable scalable crowdsourced annotation, and transform clinical workflows by facilitating the safe and efficient integration of foundation models into routine clinical practice.
Authors: Mahmood Alzubaidi, Raden Muaz, Uzair Shah, Mohammed Ammar, Khalid Alyafei, Mowafa Househ, Marco Agus
Abstract: Automated frame selection for fetal biometry remains under addressed, with most prior work targeting generic quality assessment or downstream measurement pipelines that assume suitable frames are available. We introduce FetSelect, a task-specific framework that pairs a frozen vision foundation backbone with a hybrid multi-head design: a Task-Gated classification head and a Detection-derived quality head combined via learned fusion. We curate 6,486 expert-labeled frames across four targets: Crown-Rump Length (CRL), Nuchal Translucency (NT), Nasal Bone (NB), and Scalebar, and adapt the backbone with BYOL pretraining on 19,019 unlabeled images. On a held-out test set (974 frames), FetSelect achieves mean AUROC 0.956 and mean correlation 0.818 with expert quality annotations. Ablations confirm that hybrid fusion surpasses single-head variants, and ultrasound-specific self-supervision yields consistent gains. Evaluation on external clinical videos and 509 external CRL images demonstrates task-specific discrimination.
Authors: Tianqi Wei, Xin Yu, Zhi Chen, Scott Chapman, Zi Huang
Abstract: Microscopic imaging provides essential visual evidence for studying plant biology and pathology at the cellular and subcellular levels. However, existing benchmarks on vision-language models primarily focus on macroscopic plant imagery, while the microscopic domain remains underexplored. To address this gap, we present PlantMicro, a comprehensive benchmark for evaluating vision-language models (VLMs) in microscopic plant imagery. PlantMicro integrates more than 5,000 images collected across diverse hosts, biological domains, and imaging modalities. Building on this diversity, we design a set of complementary tasks that capture different facets of microscopic image understanding. To support these tasks, we construct over 9,000 VQA pairs that systematically evaluate the capabilities of VLMs. Experiments on PlantMicro show that current VLMs struggle with fine-grained recognition and biologically grounded reasoning. For example, GPT-5 achieves 34.93% accuracy on the pathogen classification task, which is only modestly above the random-guessing baseline. The results highlight a significant gap in current VLMs' ability to comprehend plant microscopic images. PlantMicro provides a standardized foundation for advancing VLMs toward reliable and comprehensive microscopy-level plant understanding.
Authors: Giovanna Herculano Tormena, Davi Nascimento Ara\'ujo, Germano Coimbra Soares de Carvalho, Gustavo Bruno Centenaro, Rafael Janowski Pozzer, Rodrigo Akira Azevedo Kurosawa, Danilo Aires Alves, Filipe Thiago Xavier de Campos, Pedro Henrique Macedo dos Santos, Pedro Augusto Prado Mota, Ricardo V. Godoy, Jo\~ao Manoel Herrera Pinheiro, Marcelo Becker
Abstract: Sexual identification of decomposed cadavers challenges traditional methods dependent on visual anthropological analysis. This study evaluates state-of-the-art deep learning (including YOLO26, YOLO11, ConvNeXt-Tiny, EfficientNetV2, ViT-B16, VGG16, and ResNet50) with transfer learning to automatically determine biological sex from forensic computed tomography (CT) scans. We analyzed 141 autopsied cadavers from the Forensic Medical Institute of Goi\^ania-GO, including a broad age range and varying conditions of preservation. The three-dimensional reconstructions of the pelvis and skull were converted into standardized two-dimensional profile projections, contributing to the study of this new technical approach. Data augmentation techniques compensated for sample limitations. Two scenarios were validated: binary and quaternary classification (one class per sex vs. one class per anatomical region of each sex). The best-performing model achieved highly consistent results on the pelvis region and still satisfactory performance on the skull region, reaching an overall patient-level accuracy of 95.65%, recall of 92.86%, F1- score of 94.36%, and precision of 97.22%, maintaining consistent performance across the evaluated cases, including those with trauma-related artifacts. Results indicate the technical feasibility of the methodology, demonstrating that deep learning models can provide objective, high-speed skeletal analysis. Since the study was conducted using data from a single institution and a single computed tomography scanner, further validation across multiple centers and scanners is required to assess the generalizability of the proposed approach
Authors: Yikuang Yuluo, Ao Wang, Shen Kuan, Yujie Liu, Wang Liao, Ying Chen, Shuangyang Zhong, Yixing Huang, Fuquan Wang
Abstract: Sparse-view computed tomography is a severely ill-posed inverse problem, where recent 3D Gaussian Splatting methods offer an efficient explicit representation for tomographic reconstruction. However, we find that projection-domain optimization can be misleading in this setting: the rendered projections may continue to improve while the reconstructed volume deteriorates. We identify this failure mode as Projection-Volume Fidelity Divergence (PVFD), a representation-level optimization drift caused by anisotropic Gaussian deformation and view-specific primitive co-adaptation under sparse Radon constraints. To characterize this behavior, we introduce geometry- and volume-level diagnostics that measure needle-like Gaussian degeneration and the stability of the voxelized density field. Based on these observations, we propose LADES, a ground-truth-free optimization controller for sparse-view Gaussian tomography. LADES combines Linearly Annealed Dropout, which applies strong stochastic masking in early training to disrupt premature primitive co-adaptation and gradually restores full capacity for structural consolidation, with Structure-Aware Early Stopping, which terminates densification according to the saturation of Gaussian population growth rather than validation PSNR. Experiments on sparse-view CT reconstruction show that LADES improves volumetric fidelity, suppresses structural degeneration, and substantially reduces training time while maintaining competitive projection accuracy. These results suggest that robust Gaussian-based tomography requires monitoring and controlling volumetric structure, rather than optimizing projection fit alone.
Authors: Merve Kocabas, Gege Gao, Bernhard Sch\"olkopf, Andreas Geiger
Abstract: Diffusion and flow-based generative models produce strong images, yet their controllability remains largely endpoint-centric: users specify conditions and receive final outputs, while the intermediate generative dynamics remain hidden. Recent methods have begun to exploit generation order and process decomposition to improve sample quality, but still treat intermediate states as internal computation rather than objects for interaction. We propose Trajectory Forcing (TF), a trajectory-centric framework that makes the generation path explicit, semantic, and editable. TF organizes synthesis as a sequence of semantically structured stages, progressing from global layout to object-, part-, and detail-level representations. Each stage produces a decodable latent state that can be inspected, evaluated, and locally edited before the next stage begins. To instantiate this path, we derive coarse-to-fine teacher hierarchies by clustering pretrained visual representations such as DINOv2, and train a hierarchy-conditioned one-step flow-matching model at each level. We further introduce trajectory-aware metrics that measure structural consistency and local controllability beyond endpoint quality metrics such as FID. Experiments show that TF achieves competitive sample quality while exposing coherent intermediate states and supporting localized edits across semantic levels. By shifting the focus from final images to the generative path itself, TF opens a route toward controllable, trajectory-aware image synthesis.
Authors: Yingjie Zhang, Shuai Li, Peng Wang
Abstract: Out-of-Distribution (OOD) detection is essential for ensuring the robustness and reliability of object detection systems deployed in safety-critical applications. While prior research has mainly focused on uni-modal detectors or vision-language model (VLM) based classifiers, the potential of VLM-based object detectors in OOD scenarios remains underexplored. In this work, we take the first step toward building OOD object detection methods upon VLMs. We identify two challenges specific to VLM detectors: (i) their text-guided attention enhances foreground with ID labels but treats background uniformly, leaving potential OOD regions unexploited for separating in-distribution (ID) from OOD instances; and (ii) their sigmoid-based multi-label outputs are incompatible with softmax-based OOD scores, calling for scoring functions consistent with VLM probabilistic outputs. Hence, we introduce Negative Label Guided Attention and Scoring (NegAS). To address (i), we propose a negative label guided attention module (NegA), where LLM-generated, visually-similar but semantically-different negative labels are used to guide attention toward potential OOD background regions. To address (ii), we introduce a novel sigmoid-based OOD scoring function (NegS) that leverages both ID and negative labels, producing strong responses for ID instances and suppressed responses for OOD ones. Extensive experiments demonstrate that our approach improves OOD detection performance by a large margin while maintaining ID accuracy, e.g., reducing the FPR95 by 11.4% on the COCO dataset and 25.5% on the OpenImages dataset compared to the baseline model. While initially designed for dense VLM detectors like YOLO-World, we successfully adapt NegAS to Grounding DINO, a query-based VLM transformer and achieve significant improvements, demonstrating the generalizability of our framework.
Authors: Xianghui Wang, Feng Chen, Wenbo Zhang, Hua Yan, Zixuan Wang, Changsheng Li, Yinjie Lei
Abstract: Vision-Language-Action (VLA) models provide a unified paradigm for robotic manipulation, yet their real-world deployment is often bottlenecked by execution efficiency. While existing efforts predominantly focus on compute-centric efficiency to reduce per-step inference latency, the intrinsic \textbf{policy efficiency} of these models remains largely unexplored. Policy efficiency is fundamentally affected by two factors, namely the effective executable length of predicted action chunks and the total physical steps required to complete a task. These two factors jointly determine the total number of forward inference calls during execution. We observe that current VLA policies struggle with planning unreliability and action redundancy, suffering from severe prediction degradation at the tail of action chunks and tending to generate unnecessarily redundant physical steps. To address this, we propose \textbf{PolicyTrim}, a reinforcement learning-based post-training framework that extends the reliable action chunk length and reduces redundant physical steps. For reliable chunk extension, we employ a dynamic exploration strategy that explicitly rewards the successful completion of longer executable lengths, progressively pushing the trustworthy prediction horizon to its empirical limit. For step efficiency, we design a redundancy-aware reward that directly favors successful task completions with fewer steps while penalizing unreproducible shortcuts, effectively eliminating redundant physical actions. Extensive experiments across three benchmarks and three VLA models demonstrate that PolicyTrim improves action chunk utilization by 3$\times$ and reduces physical execution steps by 51.4\%. Ultimately, our framework delivers up to a 5.83$\times$ end-to-end deployment speedup without compromising task success rates.
Authors: Yutong Hu, Siyuan Tan, Shaocheng Yan, Pengcheng Shi, Qingwu Hu, Jiayuan Li
Abstract: Humans localize places by integrating perceptual cues from vision with semantic reasoning from language, forming a scene understanding that is both intuitive and structured. Although existing geo-localization models have made substantial progress in cross-view and cross-modal settings, they are largely built upon point-to-point alignment, which is insufficient for joint vision-language queries. In such queries, visual and textual cues do not simply act as independent references, but jointly define a semantic subspace for locating the target. In this paper, we formulate vision-language geo-localization (VLGL) with joint image-text queries as a multi-anchor geometric alignment problem and propose a unified framework for this setting. To realize this formulation, we propose Multi-Anchor Projection Similarity (MAPS), a new metric which constructs an anchor plane from visual and textual query features in a high-dimensional space and measures similarity by the projection length of the target feature onto this plane. Unlike cosine similarity which evaluates isolated pairwise relations, MAPS captures the geometric consistency between the target feature and the joint query subspace, providing a more discriminative ranking criterion during retrieval. To make the learned representation consistent with this geometry, we further introduce a MAPS-based contrastive loss that drives target features toward the corresponding anchor plane. The proposed framework, similarity metric, and training objective jointly yield state-of-the-art performance in VLGL.
Authors: Nicol\`o Savioli
Abstract: Modern Referring Image Segmentation (RIS) systems generate multiple candidate masks per expression but rely on a simple heuristic--typically the argmax detection score--to select the final output. We identify query selection as a failure-case bottleneck: although heuristic selection succeeds on 82-93% of samples, the residual 7-18% of failures dominate the error budget, leaving a best-query selection gap of 3-11% mIoU. We introduce Venice-H1, a lightweight, backbone-decoupled post-hoc re-ranking module that encodes each candidate through multi-scale grid signatures--compact spatial descriptors pooled onto 4x4, 8x8, and 16x16 grids--and feeds them to a Transformer-based re-ranker with a Failure Gate (ROCAUC 0.78-0.82) that intervenes only when the default choice is likely suboptimal. Instantiated on DeRIS-L and DeRIS-B, Venice-H1 achieves delta_fail of +1.40 and +0.89 mIoU with strictly positive 95% CIs on all 16/16 (split, backbone) pairs and harmful-switch rates below 0.53%. Zero-shot transfer to medical referring segmentation (MS-CXR, M3D-RefSeg-2D) yields +1.16 and +0.51 mIoU without RIS-backbone fine-tuning. The module adds approximately 11.3M parameters and under 1 ms latency.
Authors: Junhao Chen, Chanyu Zhu, Zheqi Lv, Keting Yin, Shengyu Zhang
Abstract: Autoregressive visual models (AVMs) based on next-scale prediction have emerged as a prominent paradigm for image and video synthesis. However, decomposing the generation process into discrete scales with varying granularities in AVM makes semantic errors difficult to identify and correct, thereby undermining the quality of the final output. Prior efforts to enhance AVM can be categorized into training-based and training-free approaches. Although training-based efforts to enhance AVM generation quality come at substantial computational cost, existing training-free methods neglect intermediate generation states, leaving semantic errors undiagnosed and allowing them to accumulate into the final output. In this paper, we focus on training-free paradigms and propose Gazer, a framework that integrates multimodal large language model feedback into the AVM sampling loop for in-generation semantic correction. Concretely, Gazer operates via two cooperating stages: the Reflective Diagnosis stage diagnoses semantic errors from intermediate states, while the Semantic Correction stage rewinds and rectifies the generation trajectory to realign with the target prompt. Experiments on compositional image and video benchmarks demonstrate that Gazer improves semantic alignment and compositional accuracy across multiple AVMs without additional training.
Authors: Jiayu Huo, Jingyuan Hong, Meng Zhou, Liyun Chen, Le Zhang
Abstract: Anomaly detection is essential for medical image analysis, where pathological regions often appear as rare deviations from normal anatomical structures. While training-based methods have achieved promising performance, they require task-specific optimization and extensive normal data, which limits scalability across modalities and institutions. Training-free approaches offer greater flexibility by leveraging pretrained visual representations, yet existing methods typically rely on simple nearest-neighbor retrieval and naive aggregation strategies, which may fail to capture hierarchical semantics and ignore the reliability of multiple anomaly responses. In this work, we propose HiMatch-AD, a DINOv3-driven hierarchical matching framework for training-free medical anomaly detection. Our method first retrieves semantically relevant normal references via dual-branch matching that jointly considers global CLS-token similarity and patch-level representations. Hierarchical anomaly maps are then generated across multiple transformer stages by comparing clustered normal features with query representations. To robustly aggregate anomaly responses, we introduce a unified uncertainty-based fusion mechanism that adaptively weights maps according to their reliability. The entire framework operates without any task-specific training. Extensive experiments on the BMAD benchmark, including brain MRI, liver CT, and retinal OCT datasets, demonstrate that HiMatch-AD consistently outperforms both training-based and DINO-based state-of-the-art methods, which highlights the effectiveness of multi-level matching and uncertainty-aware fusion for scalable medical anomaly detection.
Authors: SeFi-Team
Abstract: Training image generation foundation models consumes substantial resources. Previous methods have attempted to leverage semantic guidance to accelerate the training process, yet their experiments were only conducted on simple datasets such as ImageNet, at low resolutions, and with small-scale models. In this paper, we propose SeFi-Image, a text-to-image foundation model built upon semantic-first diffusion, a novel latent diffusion modeling paradigm. We instantiate SeFi-Image at three model scales, 1B, 2B, and 5B parameters, enabling systematic study of scaling behavior and flexible deployment under varying compute budgets. Notably, our largest 5B model was trained with merely 125K A800 GPU hours, corresponding to roughly 10-20% of the training compute used by Z-Image. However, it achieves results comparable to or even superior to Qwen-Image and Z-Image. Despite this modest training compute, SeFi-Image achieves strong performance on a wide range of benchmarks, including GenEval, DPG, LongTextBench, OneIG, and CVTG-2K. Moreover, we provide DMD2-distilled few-step turbo variants for each model scale to accommodate diverse hardware constraints and latency requirements. We publicly release our code, weights and hope this work offers the community useful insights into semantic-guided diffusion modeling for T2I generation, while also providing practical and readily deployable model options.
Authors: Hooman Tavakoli Ghinani, Tatjana Legler, Martin Ruskowski
Abstract: While synthetic data generation resolves the manual labeling bottleneck in computer vision, minimizing the syn-to-real domain gap requires optimizing rendering variables. This paper presents a systematic study analyzing the impact of lighting configurations and background complexity on object detection performance. We introduce SmartSDG, an automated, reproducible pipeline built on NVIDIA Isaac Sim using Physically-Based Shading (PBS), alongside ILLUM\_INTRUCK, a new multi-object industrial benchmark dataset. Through 18 controlled experiments utilizing a state-of-the-art YOLOv12 framework, we demonstrate that complex, indirect lighting configurations paired with domain-relevant background variability significantly increase visual cue richness. Our quantitative findings show that avoiding direct specular peaks preserves crucial surface textures, mitigates the domain gap, reduces false positives, and accelerates model convergence compared to using conventional direct-light synthetic data. Ultimately, we provide actionable virtual scene design guidelines to maximize object detection robustness in industrial automation.
Authors: Srinivas Venkatanarayanan, Clement Pakkam Isaac
Abstract: Vision-language models (VLMs) are increasingly used to read maps for logistics, delivery, and accessible navigation, where the output is an actionable decision (a route, a pin, a parking choice) that must respect the road network. Yet most map benchmarks grade free text or multiple-choice answers that cannot be verified against the underlying graph. We present MapReason-OSM, a benchmark and evaluation harness for graph-verifiable mobility decisions on self-rendered OpenStreetMap panels. We render fixed-style maps for ten U.S. downtowns at two aligned zoom scales, overlay a consistent marker grammar, and pair each panel with a hidden street graph and exact oracles, yielding 6,000 instances (12,000 panels across the two zooms) over 12 routing, facility-location, and visual disambiguation tasks. Models return structured decisions that we snap back to the graph and score for validity, legality, optimality, and constraint satisfaction, plus cross-zoom consistency. Across seven VLMs, models read maps and route simply but fail at graph cost reasoning (single-facility pin placement is near chance even for frontier reasoning models), and are frequently scale-inconsistent. We release the benchmark, harness, and deterministic generator. Code and data: https://github.com/Vi-Sri/mapreason-osm
Authors: Wentao Che, Esteban Garc\'es Arias, Asim Niaz, Andreas Bender, Enrique Jim\'enez
Abstract: Learning to read cuneiform tablets is an extremely demanding task; consequently, of the roughly half million excavated tablets, only a small fraction has been analysed by Assyriologists. Computer vision offers a promising avenue for decipherment but requires large, densely annotated datasets. To address this limitation, the largest annotated cuneiform sign dataset to date is used, and a Deformable Detection Transformer (DETR)-based object detection model is evaluated under two class granularities of 173 and 106 classes. The proposed system integrates automatic tablet-side extraction, heuristic line grouping, and n-gram-based textual similarity evaluation to bridge visual sign detection and textual structure, and achieves consistent improvements of up to 28-37% over prior work on COCO-style detection metrics. At inference, the method is applied to 87,668 tablet fragments from the Electronic Babylonian Library (eBL) corpus, producing nearly 2.9 million sign detections. Although the approach operates without linguistic priors and remains sensitive to tablet damage and layout variability, it provides a scalable and interpretable foundation for corpus-wide cuneiform analysis and supports future integration with multimodal and linguistic modelling frameworks.
Authors: Hao Vo, Phu Loc Nguyen, Khoa Vo, Sieu Tran, Duc Minh Nguyen, Ngo Xuan Cuong, Nghi D. Q. Bui, Anh Nguyen, Duy Minh Ho Nguyen, Ngan Le
Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable performance on 2D visual tasks, yet enhancing their spatial intelligence for real-world applications such as Autonomous Vehicles (AV) remains an open challenge. Existing geometry-aware MLLMs typically rely on auxiliary 3D models at inference time, introducing pipeline complexity and the risk of cascading failures. In this paper, we present OmniSpace, a simple yet effective plug-and-play paradigm for geometry-aware spatial reasoning from purely 2D observations. Motivated by our finding that current MLLMs are bottlenecked by weak cross-view correspondence and depth estimation, OmniSpace introduces a Camera Pose Injector, a Multi-view Epipolar Attention module, and a 3D Geometric Distillation objective that jointly address these two limitations by transferring geometric knowledge into the model. Extensive experiments show that OmniSpace surpasses existing methods on planning benchmarks (nuScenes, Bench2Drive), risk detection (nuInstruct), language (Omnidrive), and generalization (DriveBench).
Authors: Sheng-Wei Chan, Jen-Shiun Chiang
Abstract: Degraded document image binarization is sensitive to domain shifts caused by paper aging, bleed-through, stains, shadows, and uneven illumination, and the foreground-background separation of recent learning-based methods can become unstable on unseen degradation domains. We propose DR-Mamba, a sample-conditioned detail-background suppression framework that performs automatic inference-time domain adaptation for document image binarization. Unlike test-time adaptation methods that require gradient updates or auxiliary data at inference, DR-Mamba adapts to each input document through input-dependent gates within a single forward pass, requiring no target-domain labels, no fine-tuning, and no test-time parameter updates. Instead of using Mamba-style selective scanning as a single generic feature path, DR-Mamba reinterprets it as fast-slow route modeling: a fast detail route captures local stroke structures, while a slow background route accumulates spatially persistent degradation responses. The two routes are integrated through an input-dependent subtractive gate that explicitly suppresses background interference rather than fusing features by addition or concatenation. We further add full-resolution detail-guided reconstruction and thin-stroke-aware supervision to recover fine strokes lost during downsampling. Evaluated under a leave-one-year-out protocol on DIBCO-style benchmarks, where each held-out year is treated as an unseen degradation domain, DR-Mamba shows that per-document, per-location subtractive suppression improves cross-domain robustness, with particularly strong performance on the most severely degraded held-out fold.
Authors: Chaoyue Li, Boxue Yang, Shengyao Zhou, Haoyang Wu, Rui Qian, Linfeng Zhang
Abstract: 4D dynamic scene understanding requires grounding language to a persistent worldline that binds identity, metric 3D motion, and synchronized multi-view 2D projections. Existing paradigms capture only part of this structure: large multimodal models reason over rich visual evidence but rarely preserve metric topology, while vision-language tracking remains tied to fragmented 2D or 3D outputs and local continuation. We therefore introduce \textbf{4DVLT}, a worldline-centered task for instruction-conditioned 4D dynamic scene understanding in fully observed multi-view video, and \textbf{Instruct-4D}, a benchmark with 129.4K question-answer pairs, 64.7K target entities, 851 scenes, and 9 reasoning-oriented query types. To address this setting, we present \textbf{4DTrack}, which casts instruction-conditioned tracking as graph-conditioned worldline inference through an object-centric 4D state graph, metric-guided routing, bidirectional decoding, and kinematic calibration. On Instruct-4D, 4DTrack-Qwen3.5-9B reaches 62.68 $\mathrm{TGA}_{\mathrm{Top1}}$ and surpasses the best adapted VLT baseline by 19.62 points. These results show that worldline-centered modeling improves both target grounding and recovered worldline quality. The project page is available at https://github.com/mikubaka88/4DVLT.
Authors: Jan Glaser, Ivo Bukovsky, Noriyasu Homma, Marcel Jirina
Abstract: Learning Entropy (LE) has recently been extended to image analysis through Spatial Learning Entropy Maps (SLEMs), which are two-dimensional LE distributions that highlight unusually high learning activity across an image. Unlike conventional image descriptors, SLEMs are generated by incremental, sample-wise learning of a pretrained feedforward MLP network, where local pixel neighborhoods are presented sequentially in a fixed spatial order to predict the corresponding central pixels. Consequently, the learning activity at each image location depends not only on its local structure but also on the knowledge acquired from previously processed locations. This paper introduces Learning Entropy Signatures (LES), an image descriptor derived from SLEM using the K largest LE locations. LES captures the spatial organization of learning-relevant image structures and provides a compact representation of image content based on learning weight behavior. Experimental evaluation on image classification tasks shows that a relatively small number of K largest LE locations preserve substantial discriminative information. The results indicate a close relationship between the learning of neural weights and information relevance, extending the role of Learning Entropy from time series to images and, within images, from structural point extraction to compact image representation and classification.
Authors: Francesco Di Salvo, Sebastian Doerrich, Christian Ledig
Abstract: Foundation models provide highly descriptive representations for medical images, yet their reliability degrades under distribution shifts arising from changes in patients, devices, or acquisition conditions. Reliable out-of-distribution (OOD) detection is therefore essential for safe deployment. Recent post-hoc detectors efficiently exploit frozen embeddings (\emph{e.g.}, kNN), whereas reconstruction-based OOD detection in latent feature space has seen limited adoption due to inconsistent performance. In this work, we show that the limitation of reconstruction-based methods in latent space does not stem from poor reconstruction quality, but from how reconstruction errors are scored. Standard $L_2$ residual norms collapse the anisotropic residual structure, thereby suppressing informative deviations. To address this limitation, we introduce \texttt{MaRS} (Mahalanobis Residual Scoring), a label-free OOD detector that learns an in-distribution manifold using a lightweight autoencoder and measures deviation via a Mahalanobis distance on reconstruction residuals, yielding variance-aware OOD scores. Across three imaging modalities, multiple types of distribution shift, and different model families and scales, \texttt{MaRS} outperforms established confidence-, distance-, and reconstruction-based baselines, while remaining fully post-hoc and lightweight. The code is available at https://github.com/francescodisalvo05/mars.
Authors: Irem Zeynep Alag\"oz, Nils Morbitzer, Andrea Ramazzina, Nassir Navab, Federico Tombari, Stefano Gasperini
Abstract: Several disruptive research directions have recently emerged in computer vision, including foundation models achieving previously unseen zero-shot performance in scene understanding, even interactively, and generative models that synthesize extremely realistic images. The latter have also been shown to be highly effective in scene understanding tasks thanks to their rich priors. However, for promptable segmentation, foundation models struggle with accurately segmenting an object's region, leading to false positives and over-segmentation. Notably, early attempts that leverage generative priors use prompts only during post-processing, yielding suboptimal segments because the process is agnostic to the user input. In this paper, we target these limitations with Prompt2Seg, a spatial conditioning framework for diffusion-based segmentation. Prompt2Seg augments a frozen diffusion segmentation model with a conditioning branch. Our approach takes spatial prompts, represented as 2D Gaussians or confidence maps, as explicit input signals, training the model to respond directly to user intent. Fine-tuned on a deliberately constrained set of object categories drawn from Hypersim and Virtual KITTI 2, Prompt2Seg generalizes zero-shot to a wide range of unseen object types and visual domains. We evaluate on seven datasets ranging from standard benchmarks to more challenging domains, including paintings, egocentric views, and X-ray data. Furthermore, we demonstrate that Prompt2Seg consistently outperforms the underlying diffusion segmentation backbone across all benchmarks. Our results suggest that the rich priors encoded in generative pretraining, combined with principled spatial conditioning, offer a compelling path toward broadly generalizing interactive segmentation without large-scale mask supervision.
Authors: Danial Kamali, Tanawan Premsri, Shreya Rajpal, Amir Zadeh, Chuan Li, Parisa Kordjamshidi
Abstract: Vision-Language Models (VLMs) remain unreliable when spatial reasoning requires composing relations whose meanings depend on frames of reference. Existing neuro-symbolic methods make reasoning more explicit, but often depend on brittle geometric procedures and hard decisions over noisy perception. We propose SATURN, a neuro-symbolic framework for perspective-aware compositional spatial reasoning. SATURN reconstructs an approximate 3D scene, derives soft perspective-aware spatial predicates, and composes them with a training-free Pythonic symbolic executor, separating perception from reasoning while preserving uncertainty through multi-hop inference. We also introduce 3D FORCE, a diagnostic benchmark that controls reasoning depth, view, and perspective composition across spatial arrangement grounding (SAG) and referring expression grounding (REF). On 3D FORCE, VLMs and spatially trained models degrade sharply as depth and perspective complexity increase, whereas SATURN remains stable and outperforms strong baselines. On the real-world MindCube benchmark, SATURN achieves 78.57% overall accuracy, outperforming the strongest baseline by 14 pp.
Authors: Xiao Shi, Edward P. Chandler, Chicago Y. Park, Shirin Shoushtari, Ulugbek S. Kamilov
Abstract: We propose NullFlow, a principled framework for one-step generative image reconstruction. Our key idea is to confine the generative flow to a measurement-consistent subspace. Because the flow never leaves this subspace, NullFlow needs no separate data-fidelity corrections, unlike existing solvers. NullFlow samples in a single network evaluation by learning the flow's average velocity, avoiding the step-by-step integration of traditional flow matching methods. We prove that the average velocity of this constrained flow yields a training objective whose global minimizer is a one-step posterior sampler. We show on image inpainting that NullFlow matches state-of-the-art diffusion solvers while cutting inference from hundreds of network evaluations to one.
Authors: Nikita Sharma, Pranav Sara, Karan Singla
Abstract: Frontier multimodal models can guess whether a person is lying from a testimony video. To do so, they stream that raw face and voice to a third-party model. We ask whether the heavy media is needed at all. On the Real-life Trial Deception dataset, Whissle on-device speech and vision stack extracts a compact digest: transcript, emotion, age, gender, intent distributions, a deception intent filter, fluency and rhythm, per-frame facial behaviour, and prosody. Under speaker-independent evaluation, we report three findings. A small classifier on this digest reaches AUC 0.741, matching Gemini 2.5 Pro on full video. Handing the digest to a frontier LLM reaches AUC 0.755 with Claude Opus 4.8 at 7.8X fewer input tokens, with no media leaving the device. The reported 75% accuracy is a speaker-leakage artifact. We release code and experiments.
Authors: Siddhesh Khandelwal, Bj\"orn Ommer, Leonid Sigal
Abstract: Traditional supervised methods for structured visual recognition tasks -- such as object detection, segmentation, and scene graph generation -- often produce deterministic, fixed outputs, limiting their ability to capture the inherent uncertainty in complex visual scenes. As a consequence, such point estimates are unable to capture the prediction uncertainty (or multi modality) intrinsic to these problems, often arising from natural ambiguities (e.g., ambiguity in size of partially occluded objects, local ambiguity of exact segmentation boundary, etc.) as well as noise and sparsity of training data. To address this limitation, we present Modular Diffusion Models (MDMs), a simple and novel framework that learns a distribution over structured outputs for a given input image. MDMs decompose the diffusion process into distinct, task-specific modules, each focused on capturing a different aspect of the structured information space, such as object categories, spatial locations, and inter-object relationships. This modular design allows each component to be learned independently, with seamless integration at inference without additional training. Furthermore, the modularity of MDMs enables the diffusion process to easily operate over the heterogeneous output space common in many structured learning tasks (e.g., a continuous bounding boxes and discrete class labels). Experimental results over three distinct structured tasks -- object detection, instance segmentation, and scene graph generation -- highlight the benefits of our proposed framework.
Authors: Kunwar Maheep Singh, Christian Theobalt, Rishabh Dabral
Abstract: We present Generative Relightable Avatars (GRA), a person-specific method for photorealistic free-view rendering and environment-map relighting of full-body humans. We postulate that modeling fine-grained appearance details is inherently a one-to-many problem that can benefit from a generative formulation. In contrast to fully regressive relightable avatar methods, GRA follows a hybrid approach that combines controllable, physics-grounded relighting with probabilistic refinement. Starting from a tracked animated mesh, we optimize material parameters in UV-space and render a coarse relit appearance under a target HDR environment map. Next, we refine the textures with a feed-forward model to capture pose-dependent texture dynamics and illumination effects beyond simplified reflectance assumptions. Finally, a fine-tuned video-to-video diffusion model transforms the physically grounded renderings into temporally coherent, high-detail videos while preserving 3D control, with an error-recycling strategy for generating long videos. Experimental evaluations demonstrate our method's improved perceptual quality over prior relightable avatar baselines. Project Page: https://vcai.mpi-inf.mpg.de/projects/GRA/
Authors: Keito Inoshita, Takato Ueno
Abstract: Facial expression recognition (FER) is inherently ambiguous: human annotators frequently disagree, and models deployed in real environments face distribution shift. Crucially, these two conditions demand different downstream actions, as ambiguous in-distribution faces should be reported with their ambiguity whereas out-of-distribution inputs should be rejected. However, a single uncertainty score conflates the two. In this study, uncertainty decomposition into aleatoric and epistemic components for FER is investigated, and Uncertainty-Aware Routing (UAR), an inference-time routing mechanism that exploits the separation, is introduced. Specifically, aleatoric and epistemic uncertainties are obtained from a Deep Ensemble of fully fine-tuned DINOv2 models and are each validated against an independent external signal: aleatoric against human annotator disagreement, and epistemic against distribution shift induced by image corruptions. The proposed dual-validation protocol reveals that aleatoric recovers annotator disagreement with Spearman correlation 0.66 (95% CI: 0.64-0.68), and epistemic detects corruption-induced shifts, achieving average AUROC of 0.699 at the highest corruption severity. UAR retains approximately 1.8 times more ambiguous in-distribution faces than single-uncertainty routing at a matched out-of-distribution rejection rate. A strong label-distribution-learning baseline achieves comparable disagreement recovery but cannot separate ambiguity from shift and therefore cannot route, establishing that the value of decomposition lies in the separation enabling interpretable and differentiated action selection.
Authors: Yuchuan Ding, Linfei Li, Lin Zhang, Ying Shen
Abstract: Pre-trained Vision Foundation Models (VFMs) have become central to modern computer vision due to their powerful semantic representations and strong generalization ability. However, their patchified or pooled outputs are inherently low-resolution, limiting their effectiveness in tasks requiring fine-grained, pixel-level reasoning. Existing feature upsampling approaches either degrade semantic fidelity or rely on VFM-specific retraining and heavy architectures, hindering efficiency and scalability. To address these challenges, we propose RaysUp, an ultra-lightweight, task-agnostic, and VFM-agnostic feature upsampling framework that reconstructs high-resolution feature maps at arbitrary resolutions. Unlike conventional 2D interpolation or attention-based schemes, RaysUp lifts feature reconstruction into a geometry-aware ray domain. Specifically, we introduce a Spatially Decoupled Guidance Encoder for direction-aware guidance encoding, an Any-Resolution Cross-Attention mechanism for resolution-flexible reconstruction, and a novel Ray Positional Encoding (RayPE) that injects implicit 3D geometric priors via 6D Plucker ray coordinates. Finally, a Geometry-Aware Neighborhood Attention module further ensures content-adaptive bilateral aggregation while preserving geometric consistency. Extensive experiments across diverse dense prediction tasks demonstrate that RaysUp achieves state-of-the-art performance while using only 16% of the parameters of AnyUp and delivering approximately 7x faster inference. These results highlight a substantially improved accuracy-efficiency trade-off and establish RaysUp as a practical and scalable solution for universal feature upsampling. Code is available at https://github.com/MAP-RaysUp/RaysUp.
Authors: Bo Fang, Xinyao Zhang, Yuxin Song, Hui Zhang, Hang Zhou, Antoni B. Chan
Abstract: Audio Description aims to generate concise narrations of essential visual content in audio-visual media for blind and low-vision audiences. Existing methods either rely on prompting off-the-shelf multimodal models, which often mismatch AD style, or partially optimize training-based systems with next-token prediction, which under-explores model capacity and biases generation toward generic expressions. We present READ, the first reinforcement-learning (RL) framework for training-based AD generation. READ formulates AD as sequence-level optimization with reference-matching, length, and format rewards, and further introduces a dedicated coherence reward under context-aware supervision to promote narratively coherent descriptions. Experiments on MAD-Eval, CMD-AD, and TV-AD show that READ substantially outperforms prior methods across diverse evaluation metrics. Our results highlight RL as a promising paradigm for accurate and coherent AD generation. Our codes, models, and benchmark results will be publicly available.
Authors: Soumyya Kanti Datta, Shan Jia, Siwei Lyu
Abstract: Lip-syncing deepfakes are among the most challenging forms of manipulated media because their artifacts are localized almost exclusively to the mouth region and evolve dynamically over time. Detecting such deepfakes requires precise temporal and spatial modeling of lip motion. In this paper, we propose LoCC, a novel detection framework that performs fine-grained detection and localization of lip-syncing deepfakes at both segment and frame levels. Unlike prior approaches that analyze videos holistically, our method evaluates whether each frame aligns with a counterfactual estimate generated from its temporal neighbors. Real videos exhibit strong and stable consistency, whereas lip-sync deepfakes introduce localized inconsistencies. Following a teacher-student learning paradigm, our model effectively captures these frame-level discrepancies and achieves superior performance over state-of-the-art methods on multiple benchmark lip-syncing deepfake datasets, including LAV-DF, AVDF1M, FakeAVCeleb, and KODF, and generalizes well across compression levels and datasets.
Authors: Tianbo Pan, Xingyi Yang, Shizun Wang, Xinchao Wang
Abstract: Current end-to-end multi-view 3D reconstruction methods achieve impressive results, but rely on a restrictive static assumption: the scenes is entire distractor-free with perfect cross-view geometry. This reliance on idealized inputs causes even the most advanced methods to fail in real-world settings, where transient distractors and occlusions present. To address this, we propose Visual Geometry Transformer in the Wild (VGTW), an end-to-end framework for robust reconstruction from inconsistent views. At its core, we isolate and suppress distractor-affected regions while preserving the consistent components across views. Specifically, we introduce a Distractor-aware Training (DAT) strategy that separates clean features from distractor-contaminated ones in the attention mechanism while enforcing feature consistency across images. To enable this, we train the model with an auxiliary mask prediction head, using supervision from a new dataset we collected with pixel-level distractor masks. The resulting VGTW model is a feed-forward network that directly outputs clean, distractor-free point clouds. Remarkably, it requires no additional 3D supervision, remains computationally efficient, and is compatible with existing pipelines. Extensive experiments validate our approach, demonstrating state-of-the-art performance and robust generalization in diverse, real-world scenarios.
Authors: Hu Gao, Changshuo Wang, Yulong Chen, Lizhuang Ma
Abstract: Image restoration aims to recover high-quality images from degraded observations. Recent Mamba-based image restoration models have demonstrated strong potential in modeling long-range dependencies with linear complexity. However, most existing designs still rely on a single state-evolution timescale, which limits their adaptability to spatially heterogeneous and task-dependent degradation patterns in all-in-one image restoration. In this paper, we propose Multi-$\tau$ Liquid-Mamba, an adaptive state space module that introduces input-conditioned multi-timescale liquid discretization into selective state space modeling. Instead of changing the overall selective scan pipeline, the proposed module modulates the effective discretization steps of multiple dynamical branches and adaptively fuses their responses according to degradation-aware gating weights. This design allows the model to capture both fast-varying local details and slowly evolving global structures while preserving the linear scaling property of Mamba with respect to sequence length. Importantly, Multi-$\tau$ Liquid-Mamba modulates the effective transition dynamics while preserving the original selective parameterization and hardware-efficient selective scan mechanism, making it a plug-and-play module that can be seamlessly integrated into existing Mamba-based architectures. Built upon this framework, we develop a Multi-$\tau$ Liquid-Mamba Image Restoration Network (MLMIR) for all-in-one image restoration. Extensive experiments on a wide range of restoration benchmarks demonstrate that MLMIR consistently achieves state-of-the-art performance in all-in-one image restoration while remaining highly competitive in task-aligned restoration settings.
Authors: Xu Liu, Guikun Chen, Zihao Yan, Kanzhi Wu, Wenguan Wang
Abstract: Long, continuous video streams are an increasingly critical driver of multimedia intelligence. Existing efforts often handle long videos with a sample-encode-reason approach using large models. However, they overlook a crucial deployment fact: the stream is often produced by computationally constrained devices. This forces an untenable compromise: cloud offloading unlocks strong reasoning but incurs prohibitive bandwidth overhead, while on-device processing remains limited by edge hardware capacity. Therefore, we propose CoVStream, the first edge-cloud collaborative framework for understanding long video streams. The edge node distills raw video streams into compact visual features and semantic captions for transmission to the cloud, minimizing bandwidth costs, while the cloud server integrates this data into an entity graph and global visual context, activating the heavy reasoning model only when a user query arrives. Experiments on VideoMME-Long, LVBench, and RTV-Bench show that CoVStream reduces bandwidth usage by 87.6% while retaining 99.2% of the cloud baseline accuracy on LVBench.
Authors: Shujia Li, Jianshu Hu, Haiyu Zhang, Yunpeng Jiang, Haoyuan Jin, Xinyuan Chen, Yaohui Wang, Yutong Ban
Abstract: Synthesizing realistic Human-Object Interactions (HOI) is critical for creating embodied avatars and functional virtual environments. However, current data-driven approaches primarily rely on motion capture datasets, which are expensive to scale and limited in functional diversity. Models trained with these datasets fail to generalize to unseen objects and maintain physical consistency over long horizons. In this paper, we propose a novel framework that leverages a physics simulator to overcome the data-scarcity bottleneck in HOI generation. Specifically, we propose a scalable pipeline, called \ours, which leverages policies trained with reinforcement learning in a physics simulator for task-oriented data generation and trains a generative model on the augmented dataset for generalizable HOI generation. To seamlessly utilize the synthetic data, we introduce a coarse-to-fine retargeting process that bridges the representation gap between the simplified model used in physics simulator and the standard parametric body models required for generative training. Validated through comprehensive experiments, our method demonstrates enhanced generalization to unseen objects and the capability of long-horizon generation, while exhibiting greater dynamic diversity and physical plausibility.
Authors: Sudhanshu Mishra, Jialang Xu, Jensen Ang, Evangelos B. Mazomenos, Beng Ti Ang, Yueming Jin
Abstract: Intraoperative Adverse Events (IAEs) detection is critical for improving surgical safety, with bleeding being among the most frequent events across many surgery types. Existing methods struggle to distinguish bleeding IAE from visually similar residual blood due to limited temporal reasoning. Moreover, modeling long surgical videos while preserving fine-grained temporal dynamics remains computationally challenging. We propose DBT-Bleed, a dual-branch multi-scale temporal modeling framework disentangling bleeding and normal representations using layer-wise temporal adapters for short- and long-term bleeding progression. To efficiently process long surgical videos without sacrificing fine-grained temporal information, we introduce HiRED, a Hierarchical Entropy-Driven frame selection strategy that retains temporally informative segments while removing redundancy. Experiments on the MultiBypass dataset demonstrate gains of 6.53% in F1, 5.62% in Recall and 9% in MCC values for bleeding IAE detection, consistently outperforming video-level baselines. Additionally, we evaluate cross-procedure generalization on a newly curated dataset from a different surgical procedure type, where DBT-Bleed demonstrates robust transferability by achieving gain of 6% in F1 and 8% in MCC under zero-shot setting. To support this evaluation, we introduce EndoPit-IAE, an Endonasal Pituitary Surgery dataset annotated for IAEs, representing the first IAE-annotated dataset in neurosurgery. Code will be made publicly available upon acceptance.
Authors: Dominik Kroupa, Marek Va\v{s}ko, Muh Yuzril Ihza Baharuddin, Adam Herout
Abstract: We present homographic navigation, a geometry-centric framework for guiding camera acquisition toward precise capture of planar regions. Rather than treating homography as an output, we use it as an organizing variable that unifies learning, alignment, and evaluation. From a single annotated reference image, we generate unlimited synthetic training data via homographic augmentation and train a single-shot model for joint recognition and localization of multiple artifacts (physical objects with a rectangular planar target) through sparse keypoint prediction. To address precision under limited model input resolution, we introduce a two-pass inference scheme with global detection followed by localized refinement, and a Stable Warp training strategy that significantly improves accuracy, particularly in the high-precision regime. The model also predicts confidence estimates per predicted keypoint and per the whole sample. Experimental results demonstrate that accurate planar alignment can be achieved from minimal supervision, providing a foundation for geometry-driven camera guidance and future learning from in-the-wild video data.
Authors: Zijie Meng
Abstract: Controllable video generation demands independent command of the camera and the subject, yet 2D conditioning entangles them: camera- and object-induced optical flow share the same inverse-depth (1/Z) scaling and cannot be separated from image evidence alone. We first prove that this entanglement is representational, not architectural -- the 2D camera/object split is a non-identifiable inverse problem -- and therefore reframe decoupling as a question of operator design. We resolve it at the level of the attention operator. OrthoMotion routes camera motion into a geometric channel, a norm-preserving rotation of the rotary position embedding (RoPE) phase, and subject motion into a semantic channel, a gated value injection in cross-attention. Because these sub-operators are algebraically complementary -- a rotation versus a translation of the affine action on tokens -- a lightweight decoupling regularizer provably drives their response subspaces to orthogonality, so the two controls stop interfering. To our knowledge OrthoMotion is the first method to guarantee disentanglement by construction rather than hope for it to emerge. It attains state-of-the-art camera and subject accuracy at once while minimizing cross-talk, which we quantify with a new Cross-Talk Error (CTE) metric, cutting cross-talk by more than 2.4x with no loss in fidelity and generalizing across backbones.
Authors: Toshiki Watanabe, Shintaro Ito, Natsuki Takama, Koichi Ito, Takafumi Aoki
Abstract: Structure from Motion (SfM) is essential for multi-view 3D reconstruction, however, its accuracy heavily relies on the accuracy of image matching. While the recent correspondence matching method, MASt3R, enables robust matching even under challenging conditions, it tends to generate incorrect correspondences for non-overlapping image pairs. Consequently, existing SfM methods using MASt3R, such as MASt3R-SfM, suffer from significant degradation in pose estimation accuracy as they incorporate these unreliable matches directly into optimization. To address this issue, we propose G-MASt3R-SfM, a novel SfM pipeline that enhances robustness through two key modules. First, the Graph-based View Pruning (GVP) module constructs a scene graph from matching confidence and geometrically prunes outlier views. Second, the Multi-Stage Optimization (MSO) module progressively refines camera parameters by expanding the optimization scope from local consistency to the global consistency. Experiments on the ETH3D dataset demonstrate that our method achieves state-of-the-art accuracy in both camera pose estimation and 3D reconstruction, effectively suppressing noise caused by outliers.
Authors: Zhichao Fan, Yanhang Li, Zexin Zhuang
Abstract: Forced chain-of-thought (CoT) is widely assumed to make vision-language models more reliable on video question answering. We propose a small three-probe evaluation recipe to test that assumption: paired accuracy across direct, CoT, answer-first, and no-video conditions; a counterfactual video-swap diagnostic over the CoT chains; and a four-rung visual-degradation ladder. Each probe is reported under both a strict and a permissive regex scorer, with multiplicity correction over a manuscript-declared primary family. Applied to Qwen2.5-VL on Video-MME subsets, the recipe returns a two-part finding. The CoT chains are strongly video-conditioned: swapping the input video collapses chain overlap and flips most final letters, the opposite of what a "boilerplate-chain" null would predict. Yet on the same data, forced CoT does not improve MCQ accuracy, and on the smaller 7B model it produces a small but statistically supported drop under a post-hoc primary scorer choice. We do not claim this generalizes beyond the Qwen2.5-VL / Video-MME instantiation; the raw responses and a single recomputation script will be released with the supplementary material so every number can be re-derived.
Authors: Zi-Yuan Hu, Zicong Tang, Shijia Huang, Yanyang Li, Michael R. Lyu, Liwei Wang
Abstract: Recent advancements in chain-of-thought (CoT) reasoning have shown promise in enhancing video understanding and reasoning capabilities of multimodal large language models (MLLMs). However, existing CoT-based MLLMs require labor-intensive CoT annotations and incur substantial training and inference overhead. While visual latent reasoning has emerged as a more efficient alternative, existing methods primarily focus on image tasks and heavily rely on additional supervision signals for visual latent generation (e.g., CoT traces, auxiliary images, or fine-grained annotations), limiting their scalability and transferability to video tasks. To bridge this gap, we introduce VideoLatent, a novel MLLM equipped with a latent injection module tailored for video understanding and reasoning. Specifically, VideoLatent learns to perform visual latent reasoning using a new latent self-forcing training paradigm, which comprises latent alignment and latent diversity objectives, and relies solely on standard video-question-answer triplets. Extensive experiments across 14 benchmarks demonstrate that our model consistently outperforms existing standard and latent MLLMs on general video understanding and complex video reasoning. Compared with Video-R1, our VideoLatent achieves superior computational efficiency, reducing training/inference overhead by $\sim$6$\times$/$\sim$68$\times$. Moreover, experiments demonstrate that our method has strong generalizability to different MLLM backbones and different model scales.
Authors: Jundi Wu
Abstract: Global furry conventions produce massive fursuit photographs, while manual sorting brings heavy labor costs and calls for automatic identity retrieval and clustering solutions. General multimodal models lack dedicated optimization for complex fursuit scenes, and no public benchmark dataset exists for this task. To fill this gap, we build a specialized fursuit image dataset and present a three-stage hybrid pipeline Fursee for fursuit identity retrieval and clustering. First, YOLO detects and crops high-resolution fursuit head patches to improve localization of small and overlapping targets. Second, ArcFace optimizes DINOv3 embeddings to enlarge angular separation between different identities on the feature hypersphere. Third, DBSCAN performs unsupervised clustering, with silhouette-coefficient-driven search automatically selecting optimal hyperparameters rather than fixed manual radius. Retrieval and clustering experiments verify that our pipeline outperforms mainstream multimodal models including GPT5.5, Claude Opus 4.8 and Qwen3.7-Plus on all evaluation metrics, achieving competitive performance for fursuit head retrieval and grouping.
Authors: SingGuard Team
Abstract: Vision-language models (VLMs) are increasingly deployed in consumer, medical, financial, and enterprise applications. This broad deployment expands the safety surface: risks can arise from multimodal question answering, assistant responses, and cross-modal composition, while moderation policies may vary across products, regions, and deployment stages. Most existing guardrails either rely on fixed taxonomies or target only a narrow set of interaction settings, which limits their adaptability when safety rules change at deployment time. We present \textbf{SingGuard}, a policy-adaptive multimodal guardrail model family for safety assessment in multimodal conversations. SingGuard treats the active policy as a runtime input: given natural-language rules, it checks the target content against the active policy rule by rule and predicts both the safety label and the triggered rule. To balance efficiency and interpretability, SingGuard supports fast, hybrid, and slow inference regimes along a fast-to-slow reasoning spectrum, ranging from direct safety judgments to policy-grounded deliberation. We further optimize this behavior with fast--slow decoupled reinforcement learning. We also introduce \textbf{SingGuard-Bench}, a multimodal guardrail benchmark with 56{,}340 examples spanning 80+ fine-grained risk types across multimodal QA, adversarial attack, and dynamic-rule evaluation settings, including cross-modal joint-risk cases where each modality is harmless in isolation but their composition implies unsafe intent. Across six benchmark families (35 datasets), SingGuard achieves state-of-the-art average F1 in every family. Dynamic-rule evaluation further shows improved policy-following accuracy from 0.6465 to 0.7415 under runtime policy shifts. Our code is available at https://github.com/inclusionAI/Sing-Guard.
Authors: Wenlong Cheng, Yuan Gan, Yunqiu Xu, Jiaxu Miao
Abstract: Training Latent Diffusion Models (LDMs) within Federated Learning (FL) has attracted increasing attention due to its ability to combine the powerful generative capacity of LDMs with the privacy-preserving properties of FL. However, FL requires sharing the global model with multiple participants, which risks unauthorized model distribution or resale by malicious clients. While an intuitive approach is to adopt existing VAE-based watermarking techniques for LDMs in FL, this strategy falls short in addressing such threats due to two fundamental challenges: (1) Existing methods support ownership verification but lack the ability to trace model leakage to a specific malicious client; (2) VAE-based watermarks are vulnerable, as they can be removed simply by replacing the decoder with a clean counterpart. In this paper, we propose FedOT, the first framework for ownership verification and leakage tracing in federated LDMs. Specifically, to address the first challenge, we design a chunked watermark, where the first part is for ownership verification, and the second part is used for client identification. Furthermore, to overcome the second challenge and secure the model against VAE replacement attack, we introduce Latent Vector Transformation (LVT), which strengthens the connection between the VAE and U-Net latent spaces by modifying the original latent distribution of the VAE. Consequently, any attempt to replace the VAE for watermark removal leads to significant image quality degradation, making the LDM model unusable. Extensive experiments demonstrate that FedOT achieves superior performance in both ownership verification and traceability. Project page: https://spyzixuan.github.io/FedOT/.
Authors: Yuanshuo Tan, Kezhe Zhu, Xiujie Sun, Chunping Liang, Shuoyang Zhu, Chenquan Xu, Licheng Zhong, Huiming Pan, Yinri Jin, Chang Liu, Bo Xiao, Shenglong Le, Bryndan W. Lindsey, Peter B. Shull
Abstract: Quantitative measurement of the golf swing is critical for evaluating technique and enabling individualized feedback. However, existing methods are impractical to use on the golf course: optical motion capture is laboratory-bound, camera-based methods require impractical camera placement, and multi-sensor inertial measurement unit (IMU) systems require multi-segment setup and calibration. We thus propose a single wrist-worn IMU approach for estimating full-body joint angles during golf swings. The proposed Wrist-IMU Temporal Kinematic Network (WIT-KinNet) leverages modality-specific IMU embeddings and temporal kinematic encoding to learn wrist-to-body motion dependencies and estimate full-body joint angles during golf swings. Thirty-six golfers spanning beginner and skilled players, performed full, half, and quarter swings using seven club types: driver, 3-wood, 5-hybrid, 5-iron, 7-iron, 9-iron, and sand wedge. The proposed WIT-KinNet was evaluated under subject-wise cross-validation using synchronized smartwatch IMU data and ground-truth kinematics derived from an optical motion capture system. The proposed approach achieved a mean absolute error of 8.11 $\pm$ 1.84$^\circ$ across full-body joint angles. High temporal correlation was observed for pelvic rotation and upper torso rotation (r = 0.98 and 0.97, respectively), with X-factor and S-factor also showing strong correlation (r = 0.96 and 0.96). Linear mixed-effects models of the error revealed that swing amplitude, skill level, and club type all significantly affected measurement differences (p $<$ 0.05). The results establish the first single wrist-worn IMU approach for estimating full-body golf swing kinematics, enabling practical swing analysis during real gameplay.
Authors: Aaditya Baranwal, Md Jahid Hasan, Shruti Vyas
Abstract: Optical microscopy enables rapid, label-free imaging of live bacteria and is the standard instrument for species identification across clinical, environmental, and industrial microbiology. Yet field samples are routinely polymicrobial and may contain organisms that were never seen during system training, and no computer-vision benchmark tests multi-label species identification from phase-contrast microscopy (PCM) of such mixtures. We introduce Phase-contrast Optical bEnchmark for Bacterial Identification ($\textbf{PHOEBI}$), a wet-lab-prepared dataset of $120{,}000$ PCM images covering $40$ combinations of six rod-shaped species, paired with a leave-combinations-out (LCO) evaluation protocol that holds out entire species combinations to mirror the practical scenario of a model trained on catalogued mixtures that must generalise to unseen ones. On LCO, every gradient-trained per-image aggregator we test drops $0.39$ to $0.57$ F1 from the in-distribution to the held-out split, a systematic open-world recognition failure in the aggregator, not the visual representation. A linear probe of thirteen different encoders over the same features spreads only about six percentage points of F1 across general-purpose and biomedical pretraining objectives, confirming the representation is sound. We propose three lightweight $\textit{anchor-based}$ decoders that capture per-species presence geometrically over a shared frozen tile-feature pool, scoring $\textit{higher}$ on held-out combinations than on in-distribution validation.
Authors: Quanyue Song, Yishan He, Yanfei Zhang, Shihao Cheng, Zhixiang He, Zhizhi Guo, Chi Zhang, Xuelong Li, Caigui Jiang
Abstract: Recent diffusion-based models have enabled realistic audio-driven avatar generation in real-time streaming. However, existing approaches struggle to maintain visual temporal consistency and fail to explicitly perceive user intent in complex interactive streaming scenarios. To address these challenges, we propose InteractiveAvatar, a real-time infinite-streaming video generation framework that supports visually consistent avatar video generation and intent-aware interactions. With autoregressive distillation, InteractiveAvatar achieves real-time str-eaming generation of human avatars over arbitrarily long durations. For visual consistency, we introduce a Long-Short Visual Memory (LSVM) mechanism that flexibly compresses historical visual information into compact tokens, preserving both short-range coherence and long-term consistency. To generate avatars with speeches and actions aligned with user intent, we propose a Reasoning-Reaction Module (RRM), which incorporates a State-Cycling strategy and a Cache-Switching mechanism. Extensive experimental results over diverse scenarios demonstrate that our method achieves state-of-the-art visual consistency in long-duration generation, while enabling complex user-avatar interaction in real time.
Authors: Zisheng Chen, Yuping Qiu, Jianhua Han, Tao Tang, Xiuwei Chen, Likui Zhang, Ying-Cong Chen, Hang Xu, Xiaodan Liang
Abstract: Recent Vision-Language-Action (VLA) models have advanced end-to-end autonomous driving by incorporating reasoning for better interpretability and planning quality. However, most existing approaches directly generate the final trajectory without explicitly examining its future consequences, which limits their reliability in complex and dynamic environments. To address this limitation, we propose IRR-Drive (Intend, Reflect, Refine), an adaptive multimodal reflection framework for autonomous driving. Specifically, to tightly couple high-level reasoning with physical constraints, IRR-Drive first generates a preliminary textual intention and anticipates potential interactions by predicting future semantic bird's-eye view (BEV) representations. This dual-modality (Text + BEV) reflection space explicitly models anticipated scene evolution, enabling the model to rigorously self-correct and refine its initial intent before generating the final trajectory. Furthermore, to balance planning performance and computational efficiency, we construct reflection-oriented training data and design an adaptive reflection reward, enabling the model to adaptively select its reasoning mode according to scene complexity. Instead of using reasoning primarily as an auxiliary interpretation, IRR-Drive directly integrates an adaptive reflection mechanism into the planning framework, enabling grounded, decision-aware trajectory correction that is driven by scene complexity. Our method achieves state-of-the-art performance on the NAVSIM benchmark in both PDMS and EPDMS. Extensive experiments demonstrate the effectiveness of our multimodal reflection framework and validate the efficacy of the proposed adaptive reflection strategy.
Authors: Yu Cao, Ziquan Liu, Zhensong Zhang, Jiankang Deng, Shaogang Gong, Jifei Song
Abstract: Maintaining physical consistency in video generators and world models increasingly relies on vision-language models (VLMs) as automated judges that provide reward signals, ranking decisions, and data-filtering criteria. Yet VLMs differ substantially in training data and architecture, encoding physical phenomena through distinct internal representations. A single global evaluation schema therefore gives every VLM the same axes of competence, regardless of what each can actually perceive. We propose JudgeFit, an iterative refinement procedure that discovers a per-VLM evaluation taxonomy. An initial taxonomy is constructed by prompting the target VLM to enumerate physics errors on a small set of videos and clustering the resulting descriptions. The taxonomy is then refined through a diagnostic step: we calibrate the VLM's per-dimension scores to human physical-commonsense ratings, diagnose which dimensions it scores unreliably or redundantly, and prompt an LLM to repair them, iterating until convergence. We further instantiate this procedure as a benchmark and apply it to 16 VLMs spanning eight model families. The refined taxonomy outperforms the global-schema baseline on held-out videos for every VLM tested, with a mean relative improvement of approximately 32%. Beyond aggregate accuracy, the per-VLM profiles expose model-specific blind spots that overall rankings cannot anticipate, with reliability patterns differing markedly across model families.
Authors: Quang-Khai Le, Cong-Long Nguyen, Minh-Triet Tran, Trung-Nghia Le
Abstract: Text-to-image generation has seen rapid advancements, especially with the development of generative models. However, challenges remain in achieving high-quality, contextually accurate image outputs that faithfully match the provided textual descriptions, especially in artistic generation. In this paper, we present a simple yet efficient retrieval augmented generation framework, namely MythraGen, for text-to-artistic image generation by integrating an art retrieval mechanism with LoRA-based model fine-tuning. Our method extracts features from a large-scale art dataset, optimizing the generation process by combining artist-specific styles and content. Particularly, retrieved images from an external art database that have the highest similarity to the query prompt are used to finetune Stable Diffusion using LoRA for desired art generation. Experimental results and user studies on the WikiArt dataset show that our proposed method can generate artworks that closely match the user's input, significantly outperforming existing solutions.
Authors: Dooseop Choi, Kyounghwan An, Kyoung-Wook Min
Abstract: In this paper, we present a framework dubbed \textbf{BEV-Denoise} that estimates and removes intrinsic noise from learned Bird's-Eye-View (BEV) features to achieve accurate BEV semantic segmentation. Inspired by the noise estimation capability of Denoising Diffusion Probabilistic Models (DDPM), we design a UNet-based noise estimation module that learns to estimate the noise from the learned BEV features. The estimated noise is then subtracted from the BEV features and fed to BEV map decoders for the final prediction results. To facilitate supervision for the noise estimation module, we follow a sequential learning paradigm called Task Decomposition (TD) where a pre-trained BEV map autoencoder is employed to train a view transformation (VT) encoder. We share three key insights learned from our intensive experiments that are critical for improved performance. We apply our framework to four existing models, encompassing the three major VT paradigms. Experimental results on a large-scale real-world dataset, nuScenes, demonstrate the effectiveness of our framework.
Authors: Minh-Loi Nguyen, Long-Bao Nguyen, Van-Hieu Huynh, Minh-Triet Tran, Trung-Nghia Le
Abstract: Deep neural networks have witnessed remarkable advancements in recent years and have become integral to various applications. However, alongside these developments, training and deployment of neural network models on embedding and edge devices face significant challenges due to limited memory and computational resources. These problems can be addressed with deep neural network compression, which involves a trade-off between model size and performance. In this paper, we propose a novel method for model compression through two phases. First, we utilize model compression techniques, such as pruning and quantization, to significantly reduce the model size. Then, we use Mixture of Experts to route the previously compressed models to enhance performance while maintaining a balance in inference efficiency. MoEs consist of multiple expert models (i.e., compressed models) that are moderately sized and deliver stable performance. Experimental results on several benchmark datasets show that our method successfully compresses CNN models which achieves substantial reductions in FLOPs and parameters with a negligible accuracy drop.
Authors: Sylwia Majchrowska, Philip Teare
Abstract: Self-supervised learning (SSL) is increasingly used in medical imaging to reduce annotation requirements, but representation quality is often judged using a single downstream evaluation setting. For dense clinical tasks, this can confound representation quality with the capacity of the downstream model used to recover task-relevant information. We present a systematic evaluation of self-supervised representations for left-ventricular segmentation and ejection fraction (EF) estimation from apical four-chamber echocardiography on EchoNet-Dynamic. Rather than relying on a single downstream probe, we compare a hierarchy of extraction strategies with increasing expressivity: heuristic extraction without mask-supervised training, frozen linear probes, frozen lightweight decoder probes, and partial fine-tuning. We apply this framework to two complementary representation families: generic frozen self-DIstillation with NO labels (DINOv3) features and a task-adapted dense self-supervised representation, Bootstrap Your Own Segmentation (BYOS). In both families, heuristic extraction substantially understated what was recoverable from the frozen representation. For DINOv3, performance improved from Dice 0.684 and EF mean absolute error (MAE) 13.01 under heuristic extraction to Dice 0.906 and EF MAE 9.65 with a frozen lightweight decoder, approaching a supervised U-Net baseline (Dice 0.915, EF MAE 9.72). For BYOS, performance improved from Dice 0.687 and EF MAE 17.83 under heuristic extraction to Dice 0.902 and EF MAE 8.74 with a frozen lightweight decoder. These results show that conclusions about self-supervised representation quality in dense echocardiographic analysis depend strongly on the downstream extraction strategy used for evaluation. We therefore argue that multi-strategy evaluation is an important methodological consideration for SSL in dense medical image analysis.
Authors: Wangding Xia, Ye Du, Jiashi Lin, Meng Wang, Danli Shi, Shujun Wang
Abstract: Large-scale pretrained foundation models have revolutionized general medical screening, but often falter on rare diseases because such conditions are underrepresented in real-world clinical datasets. While retrieval-augmented diagnosis attempts to mitigate this, conventional static methods frequently succumb to the hubness problem, retrieving visually similar but semantically incorrect common diseases. To address this, we propose Evo-RAD, a self-evolving agentic framework that transforms evidence acquisition into a dynamic decision-making task. We formulate retrieval as a Markov Decision Process (MDP) where a graphbased agent observes the reference set state and executes actions to purge discordant evidence (DELETE), acquire pathologically consistent samples (INSERT), or conclude the evolution (TERMINATE). Optimized via Group Relative Policy Optimization (GRPO) with a homogeneityaware reward, the agent learns to maximize the diagnostic homogeneity of the support reference set. Experiments on retinal disease benchmarks show that Evo-RAD substantially improves rare-disease diagnosis, outperforming retinal foundation models by +21.04%, while also surpassing retrieval-based and parameter-efficient fine-tuning methods by +3.56%. Code is available at https://github.com/SDH-Lab/Evo-RAD.
Authors: Yubo Zhou, Jianghao Wu, Ping Ye, Shaoting Zhang, Guotai Wang
Abstract: Concept segmentation models like Segment Anything Model 3 (SAM3) show strong generalization on natural images, yet their performance degrades in medical imaging due to the domain gap caused by different imaging principles and styles. Test-Time Adaptation (TTA) is essential for improving the testing performance by updating the model on the fly without annotations. However, existing vision-language TTA methods are mainly driven by image-level uncertainty minimization, which does not necessarily reflect region-level semantic correctness in medical segmentation. Moreover, they often lack mechanisms to maintain stability in continual one-pass adaptation, leading to limited performance when reliable dense supervision is missing for segmentation. To address these issues, we propose Concept Alignment Contrast and LongShort Prompt Memory for Test-Time Adaptation (CM-TTA) of SAM3 for medical images. First, for a test sample with multiple augmentations, we introduce a novel Concept Alignment Contrast (CAC) metric, which leverages textual-visual semantic consistency to robustly evaluate prediction quality to select the best augmented view as the supervision. Second, to balance rapid and stable adaptation, we design a Long-Short Prompt Memory (LSPM) module. The short memory dynamically fuses recent prompts based on CAC scores for agile local adaptation, while the long memory maintains a stable global prompt to generate enhanced pseudo-labels. Finally, a Densely Supervised Prompt Update (DSPU) strategy is proposed to optimize the prompt embeddings with enhanced pseudo labels as dense supervision. Extensive experiments on prostate and skin lesion segmentation demonstrate that our CM-TTA framework significantly outperforms existing methods for TTA of SAM3.
Authors: Bahar Moharrer, Susanna Cifani, Marco Raoul Marini, Luigi Cinque, Maria De Marsico
Abstract: This work studies subject recognition from Leap Motion Controller 2 (LMC2) hand landmark data under a subject-level unknown-identity identification protocol on the Multi View Leap2 Hand Pose (ML2HP) dataset. Using only the landmark modality, we retain the original geometric representation and enrich it with fingertip-to-palm distances and palm-normalized inter-finger angular descriptors. Evaluation is performed under a Leave-One-Subject-Out (LOSO) protocol in which, for each outer fold, one subject is excluded from the enrolled set and treated as unknown at test time. To avoid tuning on the true outer unknown subject, the unknown-rejection threshold is selected in an inner validation step by temporarily withholding one enrolled subject from the inner gallery and using it only for threshold estimation. We compare a tree ensemble baseline with two neural alternatives: a learned embedding baseline based on centroid matching and cosine-similarity-based rejection, and an MLP+OpenMax model, which represents a more established open-set recognition approach. Under this evaluation setup, Extra Trees remains the strongest overall method, indicating that the main challenge on this benchmark is not enrolled-subject discrimination alone, but robust score separation between known and unknown probes. The results support the feasibility of compact, interpretable landmark-based descriptors for contactless hand-based unknown-subject rejection and identification on a small-cohort dataset.
Authors: Yu Zhan, Guangcheng Chen, Hanjing Ye, Zhiqin Cheng, Zanjia Tong, Wenjun Xu, Hong Zhang
Abstract: Single-view mesh reconstruction predicts object meshes and spatial layouts from a single observation, making it attractive for fast robot spatial reasoning and real-to-sim digital twins. However, robot-mounted cameras naturally rotate during manipulation and navigation, while learned single-view reconstruction models often rely on view-dependent priors and may generalize poorly to out-of-distribution camera rotations. Such rotations can introduce 3D inconsistencies, incorrect layouts, and violations of physical constraints, but this failure mode remains under-evaluated. We introduce an evaluation protocol with controlled axis-wise roll, pitch, and yaw sweeps to trace errors in monocular depth estimation (MDE), canonical object meshes, camera-space layout, and physical plausibility within a representative SAM3D-style pipeline. On the Aria Digital Twin dataset and a real Franka wrist-camera sequence, camera rotations induce MDE distortion, layout drift, and collision penetration, while canonical mesh predictions remain relatively stable. A two-stage SAM3D+FoundationPose pipeline is more robust than one-stage feed-forward layout prediction, and our Gravity-Aware Refinement reduces one-stage pairwise ICP-based layout-orientation error by 47.1$\%$. Our evaluation reveals that current single-view mesh reconstruction methods generalize poorly to robot camera rotation, and suggests that explicit gravity cues are important for reliable robotic single-view mesh reconstruction.
Authors: Yuting Li, Weihang Fang, Haoyuan Gao, Linghe Kong, Yexin Li, Lichao Sun, Weiran Huang
Abstract: The rapid deployment of Vision-Language Models (VLMs) in dynamic environments necessitates the ability to learn continuously without forgetting. However, traditional continual learning (CL) settings often rely on white-box paradigms, which is increasingly invalidated by the shift toward cloud-hosted models. In this paper, we introduce Black-CL, a more realistic benchmark for VLMs that enforces three primary real-world challenges: weight and architecture inaccessibility, constrained computation, and task-agnostic inference. The learner can query only output embeddings or logits, with no gradient flow through or structural modification of the backbone. Current CL methodologies, which rely on backbone backpropagation or complex parameter expansion, are fundamentally incompatible with these constraints. Under this setting, we propose BETA, a simple yet effective baseline built on the key insight that solely optimizing textual prototypes can navigate the complexities of CL. BETA integrates three core components: Semantic Projection Accumulation (SPA) for incremental knowledge acquisition, Latent Distribution Replay (LDR) for anchoring the embedding space against catastrophic forgetting, and Test-Time Prototype Adaptation (TTPA) for dynamic, instance-aware boundary refinement. Extensive experiments across ten diverse datasets and various backbones demonstrate that BETA significantly outperforms existing black-box tuners. Remarkably, with only 0.05 M trainable parameters, a 180--3000$\times$ reduction compared to competitive methods, BETA achieves performance on par with or even exceeding white-box CL methods. We believe Black-CL and BETA provide a foundational framework for future advancements in continual learning and accelerates the transition of continual learning from academia to real-world systems.
Authors: Yuhua Luo, Junsheng Zhang, Mengyin Liu, Xincheng Lin, Ming Yan, Zhudi Chen, Chenglu Wen, Lan Xu, Siqi Shen, Cheng Wang
Abstract: Human motion follows a temporal hierarchical structure, transitioning from low-frequency global trajectories to high-frequency details. Inspired by the success of multi-level autoregressive models in computer vision, we propose MotionMAR, a coarse-to-fine framework for motion reconstruction from sparse observations. It first estimates the global trajectory of human motion and then gradually refines the temporal details. This architecture consists of four integrated components. The Temporal Multi-scale Tokenization (TMT) VQ-VAE encodes the data at multiple temporal resolutions, separating semantic motion from minor jitters. The Motion Autoregressive Network (MAN) operates in this latent space, predicting motion across scales. It first establishes the global structure through coarse indices and then generates finer indices to recover specific details. Meanwhile, the Scale-Aware Control (SAC) module integrates sparse tracking data to ensure the generated output aligns with actual observations. The Motion Refinement Network (MRN) subsequently smooths consecutive poses and eliminates quantization artifacts. Experiments show that MotionMAR achieves state-of-the-art accuracy on the AMASS dataset, providing a reliable and structure-aware approach for motion reconstruction. The source code is publicly available at http://www.lidarhumanmotion.net/motionmar/.
Authors: Hussain Alasmawi, Numan Saeed, Soha Said, Mohammad Yaqub
Abstract: Preterm birth (PTB) prediction can enable targeted surveillance and timely intervention, yet most ultrasound-based models use a single selected transvaginal ultrasound (TVUS) frame per patient despite routine exams acquiring multiple cervical images. We formulate PTB prediction as a multiple instance learning (MIL) problem, representing each patient as a variable-sized bag of TVUS images with a single outcome label. To move beyond standard MIL aggregators that collapse a bag into a point estimate, we propose a Gaussian Mixture Model (GMM) pooling, which summarizes all images in a bag into a fixed-length representation by modeling their feature distribution. This design captures intra-patient variability. We evaluate the method on a private clinical cohort and on a public lymph node metastasis benchmark. For PTB prediction, GMM pooling improves over the instance-based model PR-AUC from 0.44 to 0.56. On the lymph node benchmark, it achieves state-of-the-art performance with 0.91 F1-score and 0.89 ROC-AUC for classification and 0.18 MAE for regression. The code is publicly available at https://github.com/HussainAlasmawi/GMM_Pooling.
Authors: Ruiliang Zhou, Xuecheng Wu, Kang He, Guangyun Han, Bin Liu, Qinqin Chen, Wende Xu, Qingjie Zhao, Chengru Song
Abstract: While Diffusion Transformers (DiTs) have revolutionized high-fidelity video generation, their reliance on 3D full attention creates a quadratic computational bottleneck. Existing sparse methods face a dilemma: dynamic pruning suffers from prohibitive runtime overhead and memory fragmentation, while static heuristics fail to capture fine-grained dependencies. In this work, we propose ScalingAttention, a training-free framework grounded in a key inductive bias: while individual activations are input-dependent, the high-mass attention regions for each head rapidly converge to a stable, prompt-agnostic Intrinsic Sparse Topology. This topology is weight-encoded, scale-invariant, and efficient to extract. ScalingAttention decouples topology discovery from sparsity control via: (1) WEST (Weight-Encoded Sparse Topology), which extracts a robust block-sparse prior mask offline to eliminate runtime search; (2) FAST (Fidelity-Aware Sensitivity Tuning), which adaptively tunes head-wise sparsity based on diffusion fidelity requirements. To ensure practical acceleration, we co-design a hardware-aligned bit-wise block-sparse kernel. Experiments on Wan2.1 show up to 1.90X end-to-end speedup with superior fidelity, establishing a new Pareto frontier over state-of-the-art baselines.
Authors: Tiange Zhang, Rongqun Lin, Haocheng Tang, Xiandong Meng, Weijia Jiang, Zhimeng Huang, Siwei Ma
Abstract: Although state-of-the-art neural video codecs (NVCs) have achieved remarkable performance, they suffer from limited generalization when encountering complex motion patterns unseen during training. To bridge this domain gap without the expensive cost of online fine-tuning, we propose a Training-Free Scale-Driven Online Flow Refinement (SOFR) method. Serving as a plug-and-play module, SOFR integrates motion information from coarse and fine scales and dynamically fuses them according to warping accuracy, effectively rectifying motion estimation errors with negligible computational overhead. Furthermore, we design a rate-aware strategy that selects different dynamic fusion strategies according to bitrate modes, and employs a reliability check based on warping error to ensure robustness. Extensive experiments on the USTC-TD dataset verify the effectiveness and generalization of SOFR across various NVC frameworks, including DCVC-SDD, DCVC-FM, and EHVC. Notably, it brings an average of 2.84% and 4.05% bitrate savings in terms of PSNR and MS-SSIM, respectively, to DCVC-FM with negligible coding time increase. Our code is available at https://github.com/SunnyMass/SOFR.
Authors: Xiaoyu Xu, Jian Zou, Sheyang Tang, Zhihua Wang, Jing Liao, Kede Ma
Abstract: Feed-forward Gaussian splatting (FFGS) facilitates real-time novel view synthesis, yet current methods often remain tied to view-dependent predictions. As more input views are added, they may accumulate noisy or redundant evidence instead of converging to a stable scene representation. In this paper, we introduce CanonicalGS, a feed-forward pipeline that maps cluttered multi-view observations into a stable, scene-centric representation. CanonicalGS first extracts view-centric evidence from depth, semantic features, and uncertainty estimates, and then aggregates this evidence in a canonical latent world using uncertainty-aware fusion. By emphasizing reliable observations while suppressing uncertain or redundant ones, CanonicalGS produces representations that scale more effectively for novel view synthesis and transfer to downstream visual perception tasks. Experiments show up to a $2.5$ dB improvement in peak signal-to-noise ratio for synthesizing novel views and an $11\%$ gain in semantic segmentation accuracy.
Authors: Sen Li, Haichao Cui, Changhao Yin, Chendong Shao, Yaqi Wang, Xinhua Tang, Fenggui Lu
Abstract: Real-time weld-pool perception is critical for closed-loop control in laser wire-feed welding, where sensing, computation, and actuator response introduce unavoidable delay. This paper presents a physics-guided spatiotemporal state space network for lookahead weld-pool segmentation. The model uses historical coaxial grayscale images, welding process parameters, and aligned wire-state electrical signals to predict the future semantic layout of three physically meaningful regions: keyhole, wire, and molten pool. It combines a visual encoder, process- and sensor-conditioned feature normalization, patch-level temporal state space modeling, horizon-conditioned latent prediction, dense future feature prediction, and a motion-aware mask decoder. Auxiliary signed-distance-function supervision, temporal consistency, feature distillation, and fine-grained keyhole losses further constrain the predicted geometry and local motion. Experiments on a 43-sequence laser welding dataset show that the proposed WeldMamba reaches 74.63\% mIoU at a 500 ms lookahead. Ablation studies further show that temporal history, patch-level state space modeling, and keyhole motion awareness are the main contributors to robust future segmentation.
Authors: Tania Aguirre, Luis Rold\~ao, Moussab Bennehar, Nathan Piasco, Dzmitry Tsishkou, Simone Rossi, Pietro Michiardi
Abstract: Reconstructing dynamic urban scenes remains challenging due to the unbounded nature of driving environments and the presence of multiple dynamic objects. Currently, potentially faster sparse voxel methods are mainly designed for static scenarios. On the other hand, dynamic approaches based on 3D Gaussian Splatting, despite their high-fidelity, are often time-consuming for driving scenarios and exhibit uncontrollable memory growth in large scenes. To address these limitations, we present DrivingVoxels, a compositional sparse voxel rendering framework for dynamic driving scenes. Our method jointly rasterizes sparse voxels from multiple independent octrees within a single rendering pass. Each rigid dynamic object is represented by an octree defined in its local coordinate frame, while a separate static octree models the stationary background. DrivingVoxels adopts a fully explicit, neural-free representation together with a LiDAR-guided structural initialization that efficiently captures scene geometry. We evaluate our framework on the PandaSet benchmark, demonstrating that DrivingVoxels performs on par on perceptual metrics and better on structural metrics for NVS and reconstruction while requiring shorter training times than previous 3DGS-base methods to an efficient optimization workflow anchored by a strong LiDAR prior.
Authors: Hongxiang Li, Hongxu Chen, Chenyang Zhu, Xiaoshuang Huang, Jiayin Cai, Xiaolong Jiang, Yao Hu, Long Chen
Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable success in visual understanding but remain constrained in visual generation due to the fundamental feature discrepancy between semantic perception and pixel-level reconstruction. Bridging this gap requires overcoming two core challenges: endowing semantic encoders with high-fidelity reconstruction capabilities, and effectively aligning generative models with semantic spaces without relying on external teachers. To this end, we propose a novel unified multimodal framework featuring \textbf{S}emantic-\textbf{P}ixel self-alignment and \textbf{A}daptive \textbf{R}outing (\textbf{SPAR}). First, to reconcile semantic perception with pixel-level reconstruction, we introduce an asymmetric dual-stream unified tokenizer. A lightweight semantic stream anchors discriminative features, while a Transformer-augmented pixel stream recovers fine-grained visual details into a unified compact latent space. Second, to eliminate external dependencies, we propose a self-aligned generation paradigm that natively leverages this optimized tokenizer as an internal alignment teacher for the diffusion model. Furthermore, to facilitate flexible multimodal interaction within this unified space, we introduce Dynamic Token Routing, which enables each token to adaptively aggregate multi-layer MLLM features based on its distinct semantic demands. Extensive experiments demonstrate that SPAR establishes the state-of-the-art for unified architectures, achieving exceptional generation and reconstruction quality while preserving foundational visual understanding capabilities.
Authors: Kang Yang, Tianci Bu, Peng Wang, Deying Li, Wen Jie, Yongcai Wang
Abstract: Collaborative perception serves as a pivotal solution to enhance the perception capability of individual agents in autonomous driving, where a core challenge lies in seeking reliable evidence to quantify and weight the contribution of each participating agent. Existing methods typically rely on a confidence map, which is co-trained with the detection head, but it is inherently correlated with the detection results and thus fails to provide unbiased physical evidence. Furthermore, how to deeply integrate evidence into the cooperative fusion process remains an open question. To address these issues, this paper first proposes an uncertainty map, a physically grounded and unambiguous metric for evaluating perception quality. This map is directly supervised by real-time sensor signals, i.e., LiDAR point density, ensuring decoupling from detection noise and thereby providing physical scenario-aware evidence for weighting agent contribution. Based on this map, we develop the Uncertainty-Enhanced Collaborative Perception (UECP) framework, centered on the Uncertainty-Aware Pyramid Fusion (UAPF) module. UAPF uses a coarse-to-fine strategy, with two key components: Uncertainty-Weighted Downsampling (UWD) for high-fidelity feature preservation, and Uncertainty-Guided Residual Fusion (UGRF) to reinforce ego features, suppressing noise and ensuring robust fusion. Extensive experiments on real-world datasets show UECP outperforms state-of-the-art methods in effectiveness and robustness by embedding the uncertainty map into fusion. Code will be publicly available.
Authors: Youyang Yin, Huanhuan Liu, YY, Qunyi Xie, Chaorun Liu, Shiqi Yang, Shaohua Wang, Zhanlong Liu, Hao Zou, Jinyue Chen, Shu Wei, Jingjing Wu, Mingxin Huang, Zhen Wu, Guibin Wang, Tengyu Du, Lei Jia
Abstract: Recently, end-to-end OCR models, exemplified by DeepSeek OCR, have once again thrust OCR into the spotlight. A widely held view is that employing a large language model (LLM) as the decoder allows the model to leverage the prior distribution of language, leading to improved OCR performance. However, the downside is equally evident: as the output sequence lengthens, the accumulated KV cache drives up memory consumption and progressively slows down generation. This stands in stark contrast to humans, who exhibit no such decline in efficiency during long-horizon copying tasks. In this technical report, we propose Unlimited OCR, a model designed to emulate human parsing working memory. Taking DeepSeek OCR as the baseline, we replace all attention layers in the decoder with our proposed Reference Sliding Window Attention (R-SWA), which reduces attention computation costs while maintaining a constant KV cache throughout the entire decoding process. By combining the high compression rate of DeepSeek OCR's encoder with our constant KV cache design, Unlimited OCR can transcribe dozens of pages of documents in a single forward pass under a standard maximum length of 32K. More importantly, R-SWA is a general-purpose parsing attention mechanism - beyond OCR, it is equally applicable to tasks such as ASR, translation, etc. Codes and model weights are publicly available at http://github.com/baidu/Unlimited-OCR.
Authors: Rapha\"el Del\'ecluse, Hazem Wannous, Laurent Grisoni, Laurent Guimas
Abstract: Pedestrian trajectory prediction requires modeling temporal dynamics, multimodal cues, and social interactions in crowded environments. Existing methods often address these factors separately or entangle them in costly attention blocks, limiting scalability, flexibility, and interpretability. We propose a three-step hierarchical Transformer that explicitly separates temporal encoding, multimodal fusion, and scene-level interaction reasoning. Lightweight GRU summaries enable efficient cross-modal attention, while social attention over time--agent tokens captures inter-pedestrian influences at manageable cost. Experiments on JTA, JRDB, and the Pedestrians and Cyclists in Road Traffic dataset show state-of-the-art performance on real-world datasets (JRDB, Urban) and competitive results on JTA. Ablation and qualitative analyses confirm the contribution of each stage and the model's ability to anticipate complex behaviors such as early turning.
Authors: Weile Guo, Shenghong He, Danying Mo, Chengdong Xu, Xuexun Liu, Chao Yu
Abstract: Motion instruction generation in cross-video comparison aims to produce corrective feedback that describes the differences between a query and a reference motion. However, existing models often generate instructions that exhibit motion hallucinations, failing to reflect actual kinematic differences between paired videos. To systematically investigate these hallucinations, we introduce MotionHalluc, a dedicated benchmark for evaluating motion hallucinations in paired-video comparison. MotionHalluc comprises 1540 fine-grained questions over 553 video pairs, evaluating hallucinations along three core dimensions: (1)directional hallucination, (2)attributional hallucination, and (3)temporal hallucination. Extensive evaluations of state-of-the-art large multimodal models demonstrate high susceptibility to these hallucinations. Furthermore, we provide Perceive-Parse-Verify (PPV) as a training-free measurements extraction and verification baseline that converts candidate instructions into executable measurement queries and supplies kinematic measurements at inference time. Our results show that this simple measurements injection yields an average 10.6% performance gain across models, suggesting that motion reasoning with explicit quantitative measurements is a key factor in reducing hallucinations in cross-video comparison. Our code and dataset will be made publicly available upon acceptance.
Authors: Chuangxin Zhao, Canran Xiao, Siyuan Ma, Mengyao Lyu, Yanbiao Ma, Jun Xia, Guiguang Ding, Yang Liu
Abstract: Multimodal large language models (MLLMs) are increasingly required to adapt to non-stationary streams of visual domains, question types, and user instructions, yet continual fine-tuning often causes severe forgetting of previously acquired multimodal skills. Existing continual vision-language methods mainly preserve outputs, replay data or pseudo-data, regularize embedding geometry, or allocate task-specific parameters, but they provide limited control over how internal cross-modal attention patterns supporting old skills drift during adaptation. We propose Attention-Spectrum Regularization (ASR), a replay-free continual learning framework that preserves skill-conditioned structures of cross-modal attention. ASR treats cross-attention maps as two-dimensional signals, summarizes their scale and directional properties into compact spectral statistics, and stores only skill-wise prototype distributions instead of replaying past image-question pairs, generated pseudo-examples, or old-stage teacher snapshots. In later stages, a phase-invariant spectral regularizer constrains harmful drift of these prototypes while allowing instance-level attention to adapt to new tasks. We provide theoretical analysis showing that skill-conditioned spectral drift controls forgetting under a spectral sufficiency assumption, and that Fourier power spectra are stable to spatial translations and bounded perturbations. Experiments on continual VQA and multimodal instruction-tuning benchmarks, including VQA v2, VQACL, CLT-VQA, CoIN, and UCIT, show that ASR consistently improves final performance and reduces forgetting over strong replay-, regularization-, and adapter-based baselines. Preserving skill-level attention structure is an effective and lightweight mechanism for continual MLLMs. Code is available at https://github.com/Creative-zcx/attention-spectrum-replay
URLs: https://github.com/Creative-zcx/attention-spectrum-replay
Authors: KunHo Heo, Seungjae kim, Wongyu Lee, SuYeon Kim, MyeongAh Cho
Abstract: Few-shot object detection aims to detect novel object categories from only a few labeled examples, avoiding costly large-scale annotation. Recent prototype-based similarity learning approaches enable training-free adaptation by matching query features with class prototypes. However, they suffer from two fundamental limitations: (i) class confusion arising from inter-class similarity margin collapse, and (ii) insufficient visual cues for precise localization, as similarity scores capture only class-level semantic affinity while providing limited spatial information. To address these issues, we introduce two complementary components. Text-Anchored Semantic Mask (TSMa) leverages class-level text features as semantic anchors to identify semantically aligned channels through channel-wise interaction between visual and text features. By suppressing style-induced spurious responses and emphasizing class-intrinsic signals, TSMa enlarges inter-class similarity margins and mitigates class confusion. We further propose Stage-Aligned Hierarchical Autoregressive Regression (SHARe), which reformulates localization as a hierarchical autoregressive process that progressively refines bounding boxes across multiple stages. SHARe leverages the layer-wise characteristics of ViT representations by aligning feature abstraction levels with regression stages: deeper layers guide early coarse localization, while shallower layers rich in edge and texture cues refine spatial details in later stages. Experiments on COCO demonstrate a new state of the art, outperforming the previous best by +10.1 nAP, with extensive analysis validating each component. The code is available at https://github.com/VisualScienceLab-KHU/ReSet.
Authors: Xirou Zhou, Zijing Xu, Yibo Qu, Qi Zhang, Xiaowan Hu, Xinyang Li
Abstract: The quantum nature of light determines the inherent Poisson stochasticity of photon detection, which is ubiquitous in photography, microscopy, and astronomy. However, our controlled numerical studies reveal that the signal-dependency, heteroscedasticity, and statistical asymmetry of Poisson-mixed noise make it challenging for existing denoisers to learn. In contrast, i.i.d. Gaussian noise, with its statistical independence and symmetric distribution, is easier to model for networks. To address this gap, we propose Poisson2Gaussian (P2G), a noise Gaussianization method that explicitly converts complex real-world noise to i.i.d. Gaussian noise via probability density matching beyond low-order moments. We also design an unbiased denoising framework that synergizes P2G with downstream denoisers, ensuring convergence to the underlying signal without requiring paired clean data or explicit noise parameters. Extensive experiments demonstrate that P2G consistently achieves state-of-the-art performance across diverse datasets. In challenging scenarios where noise strongly deviates from Gaussian statistics, our method improves the PSNR by up to 0.75 dB. Notably, P2G is architecture-agnostic and can provide universal improvements for various denoisers. The source code will be publicly available.
Authors: Aur\'elien Brun, Jan Skaloud
Abstract: ALS boresight calibration has relied for two decades on dedicated flight patterns over structured scenes containing planar surfaces of varied aspect and slope. While reliable, this approach imposes constraints on the scene content and operations, which limits its applicability to boresight recovery within routine mapping missions. We present a practical approach that substantially relaxes these requirements by replacing plane-based constraints with scene-agnostic point-to-point correspondences extracted automatically from overlapping ALS strips. Two complementary formulations are proposed to estimate boresight with laser vector observations: (i) a simpler parametric adjustment utilizing INS/GNSS trajectory; (ii) a rigorous formulation treating GNSS and raw inertial data within an existing factor-graph, i.e. a dynamic network, where boresight is added as an additional parameter. Both formulations are evaluated across four operational ALS flights equipped with five inertial systems, covering a wide range of flight altitudes, overlap geometries, terrain types and inertial sensor classes. The analysis draws a clear boundary between the legacy plane-based conditioning that falls short outside the calibration scenario and the proposed formulations, which either recover or absorb boresight effects under conventional mapping geometry. Among them, the lightweight formulation is sufficient for boresight recovery using tactical and navigation grade inertial sensors, while the general factor-graph approach is clearly superior when the inertial sensor errors are less observable within an optimal smoother. This supports the hypothesis that, for INS/GNSS trajectory of sufficient quality, the boresight calibration can be performed without particular scene prerequisites during routine mapping operations using a minimum of 3-4 overlapping strips, with either proposed formulation...
Authors: Zhan Peng, Jie Ma, Huiqiang Sun, Chong Gao, Zhijie Xue, Zhiyu Pan, Zhiguo Cao, Jun Liang, Jing Li
Abstract: Video world models hold promise for simulating interactive environments, yet maintaining consistent long-term memory across complex camera trajectories remains a critical challenge. Existing methods typically rely on computationally expensive context scaling or rigid heuristic retrieval mechanisms, which lacks generalization to varying camera trajectories and environments. In this paper, we propose Compression and Retrieval (CaR), an attention-driven implicit memory retrieval mechanism to overcome these limitations. By injecting viewpoint information via positional encoding, our method performs flexible memory retrieval through attention computation. To efficiently process extended contexts with minimal computational overhead, we further introduce a lightweight context compression network. Furthermore, we construct SceneFly, a large-scale synthetic dataset featuring realistic camera trajectories and frame-level annotations to train and evaluate long-horizon video world models. Extensive experiments demonstrate that our approach achieves state-of-the-art results on established benchmarks and exhibits strong generalization to open-domain scenes.
Authors: Boyan Wang, Yongxi Huang, Wenjing Li, Tianrui Hui, Shaofei Huang, Nan Pu, Zhun Zhong
Abstract: This report presents our solution for the ICRA 2026 GOOSE 2D Fine-Grained Semantic Segmentation Challenge, which requires parsing unstructured outdoor scenes from four camera platforms into 56 fine-grained categories. Our approach pairs foundation vision encoders (including DINOv3, SigLIP2, and InternImage) with a Mask2Former decoder, and trains them with a strong recipe including long training schedules, exponential moving average, a larger crop size, and multi-scale plus flip test-time augmentation. The three encoders, chosen for their complementary pretraining objectives, are combined into a pretraining-diverse ensemble through per-class validation-IoU weighting. Evaluated on the official GOOSE test set, our submission achieves 75.40% composite mIoU and wins the second place of the challenge. Our study further shows that the encoder's pretraining recipe, rather than its parameter count or the decoder design, is the dominant factor for accuracy on this benchmark.
Authors: Aman Kumar Pandey, Anil Singh Parihar
Abstract: Low-light human action recognition remains a challenging problem due to poor illumination, amplified noise, motion ambiguity, and diverse real-world scenes. Existing low-light datasets often lack sufficient action diversity, capture realism, or balanced class distribution, limiting the development of robust models. To address this, we introduce LUMINA-26: Low-Light Understanding for Modeling and Interpreting Night-time Actions, comprising 6,784 clips across 26 action classes, recorded from 22 subjects across 20 indoor and outdoor locations under naturally occurring low-light conditions. We also propose Illumi-Net: An Illumination-Adaptive Mixture-of-Experts Network, which leverages video-level illumination cues to guide adaptive enhancement and transformer-based spatio-temporal feature extraction, with expert-conditioned decision fusion. Our method surpasses previous state-of-the-art performance on ELLAR (Top-1: 55.13%, Top-5: 78.87%) and establishes a strong baseline on LUMINA-26 (Top-1: 75.95%, Top-5: 93.58%), offering a practical benchmark for future low-light action recognition research.
Authors: Xiaobin Hu, Haoyang He, Bo Yin, Yu He, Lei Xie, Jiangning Zhang, Yu-Gang Jiang, Shuicheng Yan
Abstract: While recent advancements in anomaly detection have demonstrated the efficacy of CNN- and Transformer-based approaches, these architectures face inherent limitations: CNNs struggle to capture long-range dependencies, whereas Transformers suffer from quadratic computational complexity. Consequently, Mamba-based architectures have attracted considerable attention, as they successfully combine superior long-range dependency modeling with linear computational complexity. By critically rethinking the structural evolution across the Mamba lineage 1-3 series, this paper proposes MambaADv2, a framework tailored for multi-class unsupervised anomaly detection. MambaADv2 comprises a pre-trained encoder and a Mamba-inspired decoder, equipped with Duality-enhanced State Space (DSS) modules across multiple scales. The proposed DSS module effectively models both global dependencies and local representations by integrating parallel-cascaded Hybrid State Space (HSS) blocks and frequency-enhanced convolution operations. The structure of the Hybrid State Space (HSS) block is tailored by following the SSD-based Mamba lineage and incorporating Mamba3-style position-aware state-space modeling, leveraging the dual computational paths of linear recurrence and parallel matrix formulation to model local continuity and global contextual comparison, thereby better serving the core anomaly detection objective of precisely reconstructing normal representations while magnifying anomalous deviations. Additionally, we propose a semantics-adaptive progressive scanning strategy that decays scanning complexity along the feature pyramid.
Authors: Alex Costanzino, Pierluigi Zama Ramirez, Giuseppe Lisanti, Luigi Di Stefano
Abstract: Implicit Neural Representations (INRs) have been proven successful in encoding continuous signals through coordinate-based networks, yet facing a spectral dilemma: periodic activations capture fine details but act as all-pass filters that memorise noise, while spatially compact activations regularise effectively but suffer from low-frequency bias. Existing attempts to resolve this trade-off introduce computational overhead or tuning frailty. We propose to model each neuron's activation as the steady-state response of a sinusoidally-forced damped harmonic oscillator, whose amplitude naturally governs the network's spectral selectivity during training. By jointly optimising the oscillator parameters alongside the network weights, our method adapts to the target signal's spectral content without explicit regularisation. Initialised in the stopband, the network exhibits a coarse-to-fine learning curriculum that progressively expands its spectral gate, capturing low-frequency structures first and high-frequency details only when justified by the reconstruction objective. Comprehensive experiments show that our approach consistently achieves state-of-the-art or competitive results against established INRs, while requiring no task-specific tuning of any hyperparameters.
Authors: Amir Ebrahimzadeh, Nazila Esmaeili, Michael Ghadimi, Jannis Hagenah
Abstract: Background: Laparoscopic camera navigation (LCN) is a critical skill, yet its current assessment typically relies on manual rating systems which are time-consuming and difficult to scale. Automated feedback could significantly enhance surgical training by providing immediate, standardized metrics. This study aims to define, clinically evaluate the relevance, and establish the technical readiness of a set of approaches for LCN assessment. Methods: We developed a detailed taxonomy of 14 key aspects of camera navigation, categorized into Framing & Composition, Visibility & Clarity, Orientation & Stability, Motion & Dynamics, and Safety & Awareness. For each aspect, we assessed the technological readiness of automated measurement based on the current state of the art (SoTA) in computer vision (CV). To establish clinical relevance, we designed a survey for practicing laparoscopic surgeons to rate the importance of each aspect on a 5-point Likert scale and to select the five most critical skills. Results: 23 surgeons participated in the survey. Foundational aspects like Field of View, Focus and Centering were rated as most important by surgeons. We present a "Clinical Importance vs. CV Technological Readiness" matrix, identifying high-priority targets for development--aspects that are both clinically crucial and technologically ready to measure. Conclusion: This work establishes a foundational framework for quantifying LCN skills. By aligning surgeon priorities with CV capabilities, we provide a clear roadmap for automatic skill assessment. This foundation enables the development of AI-driven assistance tools that can accelerate the learning curve for surgical assistants and potentially improve surgical safety and efficiency.
Authors: Jaehyuk Jang, Minseok Seo. Seungju Cho, Kangwook Ko, Changick Kim
Abstract: Vision-language models (VLMs) achieve strong zero-shot recognition, but they remain highly vulnerable to adversarial perturbations. Recent test-time adaptations improve robustness without retraining, but they do not directly adapt the corrupted visual representation itself. Prompt-based methods adapt the learnable text prompts, while input-space methods optimize pixels or padding at test time. These approaches can improve predictions, but they do so through an indirect and expensive optimization path. We propose Test-time Visual Subspace Steering (T-VSS), a lightweight defense that performs test-time adaptation directly in the visual feature space. T-VSS first builds a sample-specific low-rank subspace from multi-view feature residuals anchored at the attacked image. It then learns a shared feature correction within this subspace using reliability-weighted entropy minimization. By constraining adaptation to a compact visual geometry, T-VSS steers attacked features toward more stable and discriminative predictions while avoiding noisy full-space updates. Experiments on fine-grained, ImageNet, and ImageNet-OOD benchmarks show that T-VSS improves adversarial robustness while maintaining competitive clean accuracy and better efficiency than prior test-time adaptations.
Authors: Haq Nawaz Malik, Faizan Iqbal, Nahfid Nissar
Abstract: Optical Character Recognition (OCR) for low-resource languages is often constrained by the lack of annotated training data and the complexity of script-specific rendering. Kashmiri, written primarily in the Perso-Arabic Nastaliq script, presents additional challenges due to contextual glyph shaping, dense ligatures, and orthographic variability. We introduce Koshur Pixel, the first large-scale synthetic OCR dataset for Kashmiri, comprising 613,078 image-text pairs generated from the KS-PRET-5M corpus using the SynthOCR-Gen framework. The dataset spans multiple fonts and textual granularities, ranging from individual words to full-page documents, and incorporates more than 25 augmentation strategies that emulate real-world document degradations. Koshur Pixel provides a scalable and cost-effective alternative to manual annotation, establishing a foundational resource for training OCR systems, digitizing Kashmiri textual heritage, and advancing language technologies for a severely under-resourced language.
Authors: Qi Li, Yuliang Huang, Shaheer U. Saeed, Qianye Yang, Vasilis Stavrinides, Zachary M. C. Baum, Dean C. Barratt, J. Alison Noble, Tom Vercauteren, Yipeng Hu
Abstract: Deep learning-based medical image segmentation models are trained using annotations that exhibit systematic bias and variability across raters. While probabilistic multi-rater approaches can emulate annotator-specific delineations, annotator characteristics are typically encoded implicitly in deep latent feature space, making direct analysis of their influence on predictive distributions less straightforward. We propose a logit-space probabilistic segmentation framework based on stochastic variational Gaussian Process that explicitly decomposes predictions into an image-dependent reference logit distribution and annotator specific perturbations parameterised by bias and variance. This formulation enables more explicit analysis on how intra- and inter-rater variability propagate to predictive distributions. We evaluate the method on a multi-annotator medical image dataset, which shows that explicitly modelling annotator specific perturbations improves uncertainty calibration while maintaining comparable segmentation accuracy, compared with state-of-the-art multi-rater probabilistic segmentation method. The learned bias and variance parameters quantitatively reflect annotator-specific behaviour. Furthermore, controlled perturbation experiments over bias and variance demonstrate how changes in annotator parameters systematically influence predictive performance. The code used in this paper is made publicly available at https://github.com/QiLi111/GPS-Var.
Authors: Yiming Li, Yihan Yang, Yuguang Chu, Yuanhui Hu, Si-Yuan Cao, Xiaohan Zhang, Xiaokai Bai, Zhe Wu, Hui-Liang Shen
Abstract: Remote photoplethysmography (rPPG) estimates the blood volume pulse (BVP) signal from facial videos, enabling contact-free health monitoring. Conventional clip-wise approaches, which use video clips as input, require capturing over one hundred frames before inference, thus introducing several seconds of delay and hindering real-time use. Meanwhile, frame-wise approaches struggle to capture long-range temporal and periodic features of physiological rhythms, and therefore lead to reduced estimation accuracy. To overcome these issues, we propose StreamPPG, a unified architecture that enables low-latency frame-wise physiological signal estimation while achieving competitive accuracy compared with clip-wise approaches. StreamPPG is trained under a consistent privileged learning (CPL) strategy, which leverages ground-truth rPPG signals as privileged information to enhance the model's representation capability. Extensive experiments demonstrate that StreamPPG achieves state-of-the-art accuracy across multiple datasets while maintaining real-time throughput on edge devices.
Authors: Iris Dominguez-Catena, Daniel Paternain, Mikel Galar
Abstract: Large-scale image-text datasets, such as LAION-5B, are foundational to modern AI systems, yet their vast scale and uncurated nature raise significant concerns about demographic and stereotypical biases. This study presents a comprehensive analysis of the demographic composition and representational, stereotypical, and intersectional biases in LAION-2B-en and LAION-2B-multi, the two main components of the LAION-5B dataset. Using state-of-the-art models -- FairFace, DeepFace, and Emo-AffectNet -- we analyze faces detected in the dataset to identify biases across age, gender, race, and expressed emotion. Our findings reveal substantial overrepresentation of young adults (20--39), White individuals, and males, alongside consistent underrepresentation of minority racial groups and middle-aged or older women across both dataset components. We also observe stereotypical associations between demographic attributes and emotions, such as ``Anger'' being predominantly linked to males and ``Happiness'' to females, pointing to systemic imbalances in the data. The consistency of these patterns across two demographic models and both components of LAION-5B demonstrates that these biases are deeply embedded in one of the most widely-used training datasets. Given the scale at which LAION-5B is used to train generative models, these demographic imbalances could shape the behavior and outputs of numerous downstream AI systems.
Authors: Zhangyuan Yu, Wanran Sun, Guangjing Yang, Xiaohu Wu, Qicheng Lao
Abstract: Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in multimodal reasoning. However, prevailing reinforcement learning (RL) paradigms lack explicit counterfactual enhancement and causal learning mechanisms. This fundamental deficiency results in severe grounding failures, manifesting as a tendency to ignore visual evidence in favor of language priors or exhibiting hallucination drift during long chain-of-thought reasoning. To address this root cause, we propose CounterFactual Policy Optimization (CFPO), a novel framework that enforces causal consistency between visual perception and textual reasoning. CFPO introduces a cross-modal counterfactual enhancement mechanism, which regularizes the policy by maximizing the discrepancy between the model's predictions and those from a counterfactual state where critical visual cues are suppressed. This approach seamlessly integrates with standard algorithms like GRPO and DAPO without requiring external reward models or additional supervision. Extensive experiments demonstrate that CFPO significantly improves reasoning fidelity, achieving consistent gains of 3.17%-6.25% over standard RL baselines and 1.32%-2.13% over the state-of-the-art perception-aware method (PAPO). Code is available at https://github.com/Raven-July/CFPO.
Authors: Vikram Sandu, Mayurdeep Pathak, Rajiv Soundararajan
Abstract: Despite modeling temporal motion, dynamic 3D Gaussian Splatting (3DGS) methods still inherit a static densification strategy that is ill-suited for dynamic scenes. This neglect of temporal behavior leads to under-reconstructed and blurry dynamic regions, as short-lived Gaussians receive sparse supervision and fail to densify effectively. We propose a Visibility-Aware Densification (VAD) framework that integrates temporal visibility into the densification process, ensuring that Gaussians are refined based on their actual temporal presence. A Temporally-Adaptive Thresholding (TAT) mechanism further adjusts each Gaussian's densification threshold according to its temporal lifespan, promoting balanced refinement of both static and dynamic regions. Finally, a Temporal Offset Warping (TOW) design enhances deformation capacity around temporal centers, extending the lifespan of highly dynamic Gaussians and facilitating more effective densification. Our approach achieves substantial improvements in the visual quality of dynamic regions, outperforming existing methods across three dynamic multi-view benchmark datasets. Moreover, the proposed VAD module generalizes across diverse dynamic 3DGS methods, consistently improving dynamic reconstruction as a plug-and-play component.
Authors: Feifei Bian, Zhimin Zheng, Wei Deng, Daiguo Zhou, Jian Luan
Abstract: Recent years have witnessed remarkable progress in image generation and editing, particularly regarding instruction following and visual fidelity. However, when handling ambiguous intentions, logical reasoning, and Out-of-Distribution (OOD) knowledge, existing image models often yield sub-optimal results due to a lack of deep reasoning capabilities and real-time external information. Although emerging unified understanding-and-generation models attempt to bridge this gap, they remain constrained by their intrinsic parameter scales and static knowledge gaps. Inspired by agentic paradigms, we propose RS-Gen: a plug-and-play, training-free, multi-stage image agentic framework. RS-Gen innovatively introduces a "Questioning-and-Solving" closed-loop mechanism to accurately identify logical issues and knowledge gaps, autonomously planning actions to bridge information deficits and execute deep logical reasoning. Extensive experiments demonstrate that RS-Gen significantly expands the capability boundaries of foundational image generation and editing models. Specifically, on the WISE Verified and RISEBench benchmarks, RS-Gen yields substantial absolute performance gains of 0.313 for Qwen-Image and 19.70 for Qwen-Image-Edit-2511, respectively, successfully elevating both to the state-of-the-art (SOTA) level among open-source models.
Authors: Zixu Li, jianjun Qian, Hang Shao, Lei Luo, Jian Yang
Abstract: Remote Photoplethysmography (rPPG) enables contactless pulse estimation from facial videos, serving as a vital tool for health monitoring. However, current deep learning methods often struggle under complex disturbances, particularly varying illumination, facial expressions, and unconstrained head movements. In such scenarios, subtle physiological signals are easily dominated by external interference, making the recovered rPPG waveform unstable and unreliable. One important reason is that most existing methods directly model the rPPG signal in a unified manner, where different signal components are coupled during reconstruction. This makes it difficult to preserve weak pulse-related variations when strong disturbance-induced changes are present. To address this challenge, we propose PhysFlow, a frequency-decoupled dual-field rectified flow framework tailored for robust rPPG estimation. Specifically, the ground-truth rPPG signal is decomposed into trend and amplitude components, which are used as separate supervisory targets. Based on the extracted facial features, PhysFlow learns two component-specific conditional velocity fields to model the two components separately. This design reduces mutual interference between different components and improves the robustness of rPPG reconstruction under complex disturbances. Moreover, the rectified flow formulation enables efficient waveform reconstruction with only a few ordinary differential equation (ODE) integration steps. Extensive experiments on multiple benchmark datasets demonstrate that PhysFlow outperforms state-of-the-art methods in both heart-rate estimation and rPPG waveform reconstruction across diverse challenging scenarios.
Authors: Rapha\"el Del\'ecluse, Hazem Wannous, Laurent Guimas
Abstract: Person re-identification (Re-ID) is a crucial task in surveillance and human behavior analysis, often used in public spaces such as transport hubs. Traditional RGB-based Re-ID methods raise privacy concerns and are highly sensitive to lighting variations and occlusion. In this paper, we propose a novel Re-ID approach that leverages depth images, which inherently obscures facial and other identifiable features, making it a privacy-preserving solution. Our method addresses the association problem between multiple views of individuals by applying the Hungarian algorithm, optimizing the matching process through minimization of the global cost across the distance matrix. We further enhance the approach by introducing temporal sequences of frames as input to a Transformer encoder architecture, which exploits both RGB and depth modalities. This architecture captures dynamic movement patterns, improving feature extraction and re-identification accuracy. Additionally, we employ batch hard triplet loss to enhance discriminative feature learning by focusing on the hardest samples. We evaluate both depth-only and RGB-D models on several top-view datasets, including TVPR2, GODPR, and BIWI RGBD-ID. Our results demonstrate that depth-only re-identification can achieve competitive performance compared to state-of-the-art methods, as measured by standard metrics such as Cumulative Matching Characteristics (CMC) and Mean Average Precision (mAP), while prioritizing privacy preservation.
Authors: Kai Zeng, Moran Li, Zhengwei Wang, Yingchen Yu, Yiheng Lin, Ruichuan An, Ming Lu, Qi She, Wentao Zhang
Abstract: Visual text editing aims to precisely modify text in images and videos while preserving stylistic consistency and visual realism. Despite significant advances in the image domain, video text editing remains largely unexplored: it is a localized task demanding stroke-level precision within small text regions, which compounds the challenges of cross-frame accuracy, temporal coherence, and stylistic fidelity. We introduce SteerVTE, a unified framework that \underline{\textbf{steer}}s a frozen video diffusion model to perform precise \underline{\textbf{V}}ideo \underline{\textbf{T}}ext \underline{\textbf{E}}diting through style and glyph control. Built on a frozen diffusion transformer, SteerVTE attaches a lightweight text context adapter with two complementary modules: a style encoder capturing the original text's visual attributes, and dual-granularity glyph encoders encoding the target text at both the line and character levels. To overcome the inherently weak text rendering priors of video foundation models, we further propose a glyph-aware spatial-focal loss and a three-stage progressive training curriculum that scales from image to video data. To support large-scale training, we also develop an automatic synthesis pipeline and construct SteerVTE-1M, a dataset of one million triplets spanning diverse scenes, fonts, and stylistic effects. Extensive experiments demonstrate that SteerVTE substantially outperforms existing video editing baselines across text accuracy, style consistency, and temporal coherence.
Authors: Felix Tristram, Stefano Gasperini, Benjamin Killeen, Marcel Walch, Christian Benz, Nassir Navab, Ghazal Ghazaei
Abstract: The increasing maturity of embodied AI platforms has driven a growing interest in procedural video representation learning to support intelligent assistance systems for complex, multi-step tasks. Leveraging large-scale latent predictive training, video foundation models capture video dynamics, enabling downstream tasks such as activity understanding, spatiotemporal localization, and predictive control. However, procedural videos include actions with long-range dependencies that these models do not support, due to the quadratic complexity of self-attention. Distinct actions, for example, may be visually similar despite appearing at different points in the procedure, such as turning the stove on versus off. Here, we propose a backbone-agnostic approach that learns long-duration video representations by reducing the problem to a dense, frame-aligned action space and predicting pooled masked latent vectors. This approach allows our Procedural Joint Embedding Predictive Architecture (P-JEPA) to ingest videos over 30 minutes long, enabling effective long-form understanding of procedural steps. We evaluate P-JEPA using features extracted with VJEPA2.1, TSM, and I3D over the EgoExo4D, EgoProceL, and Assembly101 datasets, finding that it consistently improves linear separability, streaming inference, and temporal action segmentation performance, achieving state-of-the-art results on EgoExo4D fine-grained action classification while using an order of magnitude fewer parameters than LLM-based methods and running in real time.
Authors: Yujin Choi, Jaehong Yoon
Abstract: Flow matching has recently emerged as a strong paradigm for state-of-the-art text-to-image (T2I) generation, enabling high-quality generation with a small number of sampling steps. As these models are increasingly integrated into real-world applications, ensuring safe and non-sensitive content generation has become a critical requirement. However, adapting safety and concept removal methods to this new generation framework remains an open challenge. Specifically, prior methods largely rely on iterative trajectory steering across a number of denoising steps or on CLIP-centric prompt embedding manipulation. These design assumptions pose fundamental bottlenecks for safety in flow matching-based T2I generation, where limited sampling steps constrain iterative correction and modern context-aware text encoders diminish the effectiveness of embedding-level interventions. In this paper, we propose VESFlow, a training-free safety method tailored to flow matching with extremely few sampling steps. Leveraging the fact that flow matching models learn the marginal velocity, we directly edit the velocity field via a safe-conditional posterior. VESFlow steers the trajectory toward safe outputs while leaving the conditioning prompt unchanged. Building on the observation that VESFlow leaves outputs unchanged under benign prompts, we further introduce a risk score-based filtering that bypasses velocity editing to reduce computational cost while preserving benign prompt generation. Based on this filtering, we propose VESFlow+, a stronger variant of VESFlow that not only edits the velocity toward the safe direction, but also pushes it away from the unsafe direction. Experimental results show that VESFlow+ removes the target concept, reducing the attack success rate by NudeNet to 6.3% on Ring-A-Bell and 6.8% on MMA-Diffusion on the 4-step MeanFlow model, while preserving fidelity on benign prompts.
Authors: Feifei Wang, Shiyuan Yang, Xiaoyu Li, Jing Liao
Abstract: As instruction-based editing models and multimodal large language models advance, diverse image editing tasks have become feasible. However, achieving precise and consistent geometric image editing, such as translating, scaling, and rotating in 3D space, remains a major challenge. In this work, we introduce BoxCtrl, a 3D-aware visual prompting framework. Unlike text-only or coarse 2D-guided approaches, our method introduces informative RGB 3D bounding boxes projected onto 2D images as visual prompts. The three orthogonal faces of each box are painted with distinct RGB colors, simultaneously encoding position, size, and orientation to provide a compact, intuitive in-context visual example. The key to BoxCtrl's success lies in these well-designed bounding boxes, which decouple geometric control from appearance control. This enables the model to learn consistent correspondences between faces of the same color in the latent space, leading to a precise understanding of geometric intentions and accurate editing results. We introduce a two-stage training paradigm: Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL). To address paired data scarcity, we construct a large-scale synthetic dataset for SFT, equipping the model with fundamental editing capabilities. To bridge the synthetic-to-real domain gap, we incorporate an online RL stage leveraging unpaired real-world data. Guided by a reward function evaluating geometric accuracy and visual fidelity, our SFT-RL strategy significantly enhances geometric precision while maintaining photorealistic quality. Extensive experiments demonstrate that BoxCtrl achieves state-of-the-art performance across translation, rotation, scaling, and composite editing tasks.
Authors: Nermeen Abou Baker, Paul Szabo-M\"uller, Uwe Handmann
Abstract: Sorting a huge stream of waste accurately within a short period can be done with the support of digitalization, particularly Artificial Intelligence, instead of traditional methods. The overlap of Artificial Intelligence and Circular Economy can flourish many services in the environmental technology domain, in particular smart ewaste recycling, resulting in enabling circular smart cities. We analyse the growing need for automated ewaste recycling as an essential requirement to cope with the fast growing ewaste stream and we shed the light on the impact of Artificial Intelligence in supporting the recycling process through smart classification of devices, where the smartphone is our case study. Our study applies transfer learning as a special technique of Artificial Intelligence by finetuning the output layers of AlexNet as a pretrained model and perform the implementation on a small size dataset that contains 12 classes from 6 smartphone brands. We evaluate the performance of our model by tuning the learning rate, choosing the best optimizer, and augmenting the original dataset to avoid overfitting. We found that the optimizer of Stochastic Gradient Descent with Momentum and 3e-4 as a learning rate brings almost 98% model accuracy with generalization. Our study supports automated ewaste recycling in decreasing the error rate of ewaste sorting and investigates the advantages of applying transfer learning as the best scenario to overcome the rising challenges.
Authors: Mingyu Mei, Li Zhang, Zibo Dai, Han Sun, Xinyue Zhao, Huiliang Shen, Zaixing He
Abstract: 6D pose estimation is a key task in computer vision and embodied AI, widely used in robotic manipulation, augmented reality, etc. Existing methods directly regress in a high-dimensional continuous space, facing two key challenges in category-level pose estimation: limited accuracy due to noise and local optima, and inefficient search over an infinite space that hinders real-time performance. This paper proposes Flow6D, a hierarchical flow matching framework with a two-stage discrete latent space localization-continuous pose regression strategy. Rotation and translation parameters are first discretized into bins, with a discrete flow matching model locking the latent space around the true pose to reduce search complexity. Then, by sampling in the latent space, a continuous flow matching model predicts local pose residuals to optimize the estimate and regress to an accurate pose. The framework also naturally extends to articulated objects, outperforming state-of-the-art methods on synthetic and real datasets with real-time inference at 70 FPS. Project website: https://flow6d.github.io/.
Authors: Yuqiang Huang, Yuxi Wang, Junyu Dong, Zhaoxiang Zhang
Abstract: Underwater 4D reconstruction remains challenging due to the coupling between degraded light transport in participating media and dynamic water variations. Most existing Methods are developed under in-air assumptions and do not explicitly account for underwater absorption and backscatter. Additionally, near-static assumptions make these approaches sensitive to drifting particles and dynamic distractors , leading to unstable geometry and inconsistent cross-view results. To address these issues, we propose a generative framework for underwater 4D reconstruction, named Ocean4D, which is built on two complementary components. Specifically, 4D-GCC constructs 4D geometrically consistent conditioning with improved cross-frame coverage, while the Medium-Aware Block performs implicit medium-aware denoising in the latent diffusion process to stabilize underwater appearance under absorption and scattering. Given a monocular video and target cameras, our method generates videos along the target trajectories while preserving global structure and cross-view consistency. Extensive experiments on both dynamic and static underwater benchmarks demonstrate state-of-the-art performance on underwater reconstruction.
Authors: Hengji Zhou, Lingxuan Huang, Jian Wang, Bing Zhou, Si Wu, Lianghao Xia, Chao Huang
Abstract: Video editing has become essential in digital media creation, yet existing automated systems are restricted to short segment processing and domain-specific tasks. They face two critical limitations: i) inability to handle diverse video comprehension and editing operations, and ii) lack of long-video understanding for coherent narrative creation. We propose VideoAgent, an all-in-one agentic framework addressing these challenges through two key innovations. First, we develop automated video shot creation with shot planning agents for coherent narratives and cross-modal retrieval for aligned visual content. Second, we design a multi-agent orchestration framework integrating over thirty specialized editing agents. Intent parsing filters relevant tools while textual-gradient graph optimization assembles complex editing pipelines. Extensive experiments on our newly-proposed VideoEdit benchmark and public datasets demonstrate VideoAgent's superiority over existing multimodal LLMs and agentic systems. VideoAgent achieves 87-95% orchestration success rates while reducing API costs by 60%. Human evaluation across six video categories shows VideoAgent produces professional-quality content approaching human-level performance, with ratings only 4% below human-created videos. We release our code at https://github.com/HKUDS/VideoAgent.
Authors: Cheng Cui, Tingquan Gao, Xueqing Wang, Changda Zhou, Hongen Liu, Ting Sun, Yubo Zhang, Zelun Zhang, Jiaxuan Liu, Manhui Lin, Yue Zhang, Suyin Liang, Yiqing Xiang, Yi Liu
Abstract: Accurate document layout analysis remains a critical bottleneck for document parsing systems, due to the intricate coupling among heterogeneous document layout elements, geometric distortions (\eg, paper warping and bending, perspective variations), and reading order within diverse layout structures. Existing approaches typically rely on fragmented multi-stage pipelines or computationally heavy generative Transformer architectures, leading to error propagation and limited efficiency. In this paper, we present RT-DocLayout, a highly efficient end-to-end framework for document layout analysis, designed as a front-end for document parsing tasks. The proposed model unifies classification, detection, pixel-level segmentation, and reading order prediction for layout elements within a single 33M-parameter architecture. Built upon the RT-DETR, our key contribution is a unified multi-task formulation within a single query-based decoder that simultaneously classifies, regresses bounding box, generates masks, and constructs relationship to reason reading order. By jointly learning geometric and structural representations, RT-DocLayout introduces multi-task optimization that substantially improves robustness under real-world document distortions. Extensive experiments on public benchmarks demonstrate state-of-the-art performance in document layout analysis while maintaining real-time inference speed(132.1 FPS). When coupled with downstream OCR engines, RT-DocLayout significantly improves full-document reconstruction quality, providing a scalable and practical foundation for real-world document intelligence systems.
Authors: Tom Hodemon, Mohamed Chaouch, Aboubacar Tuo, Angelique Loesch
Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable success in Visual Question Answering (VQA), yet their "black-box" nature hinders deployment in critical domains. Grounded Visual Reasoning (GVR) approaches attempt to improve interpretability by explicitly couple textual rationales with visual grounding information, which are typically textual coordinates. This mechanism lacks a learnable semantic link to the visual features, often resulting in a semantic-spatial gap where the model hallucinates coordinates that do not correspond to image evidences. In this work, we introduce Composer, a MLLM that leverages a novel visual grounding mechanism based on learned proxy-tokens to promote faithful interpretability. These discrete symbolic pointers explicitly index the image latent space, allowing the model to manipulate visual regions as addressable, semantically manipulable sets. To rigorously validate our novel grounding mechanism, we constructed ComposerGCoT, a dataset synthesized to enable holistic assessment of reasoning consistency and grounding accuracy. Experimental results indicate that Composer achieves performance parity with its coordinate-based counterpart in final answer accuracy, while improving visual grounding accuracy by +9.0 points. By demonstrating that discrete proxy-tokens capture spatial semantics more effectively than typical textual coordinates, we establish that visual grounding mechanisms with learnable semantic links represent a promising path toward trustworthy and reliable MLLMs.
Authors: Tim G. Zhou, Anthony Fuller, Geoff Pleiss, Evan Shelhamer
Abstract: Machine learning models for remote sensing are trained and deployed on a static set of modalities. However, as we equip newer satellites with novel sensors and retire old ones, practitioners may wish to deploy an existing model on a substitution, superset, or subset of modalities with minimal retraining given data availability or practical computational constraints. We study the setting of updating existing models to changing modalities and identify three main scenarios: Modality Transfer (substitution), Addition (superset), and Peeking (subset). We propose DeluluNet, an architecture with modular components for all three changing modality scenarios. DeluluNet is trained end-to-end, learning a multi-modal model from a unimodal teacher and unlabeled multimodal data via modality hallucination--predicting missing modality representations from those that are present. As a result, DeluluNet can keep predicting even when input modalities change, providing a practical alternative to re-labeling and re-training in a changing world.
Authors: Hiroaki Aizawa
Abstract: Medical image segmentation is a fundamental task for medical image processing and computer-assisted intervention, yet data imbalance and small lesion detection pose significant challenges. Dice Loss, which measures the overlap between predicted and ground truth regions, is widely used to mitigate these issues. To further emphasize its properties, we propose Polynomial Dice Loss, a polynomial extension of Dice Loss. Specifically, by leveraging the geometric characteristics of Dice Loss and formulating the loss function as a polynomial representation via Taylor expansion, we enable the adjustment of the contribution of higher-order components to the loss function. In our experiments, we evaluate the proposed method against loss functions derived from conventional Dice and Tversky coefficients. Experimental results and further analysis show that the polynomial formulation provides a simple way to control the loss shape and achieves competitive performance across multiple segmentation settings.
Authors: Amaury Wei, Ismail Nejjar, Olga Fink
Abstract: Unsupervised video object tracking aims to decompose dynamic scenes into persistent, object-centric entities without manual annotations. Many recent approaches rely on slot-based representations, where a fixed set of latent variables ("slots") represent individual objects across frames. To preserve object identity, these models enforce temporal consistency on slot embeddings. However, when appearance and pose are entangled, this consistency objective conflicts with object motion and viewpoint changes. As a result, slots tend to lock onto static regions (e.g., background) to satisfy the consistency objective, while foreground objects become fragmented across multiple slots or frequently swap identities. To address these limitations, we propose STAITUS, a unified framework that explicitly disentangles each slot into appearance and geometric pose (position/scale). Leveraging this disentanglement, STAITUS enforces within-frame spatial separation and applies temporal alignment only in appearance space, yielding sharper masks and more persistent identities under motion, occlusion, and object entry/exit. Furthermore, to mitigate over-segmentation, we introduce an adaptive gating mechanism that dynamically adjusts the number of active slots to match scene complexity. Extensive experiments on synthetic and real-world benchmarks demonstrate that STAITUS substantially outperforms state-of-the-art baselines in segmentation quality and tracking stability.
Authors: Zesong Yang, Yuanhang Lei, Liyuan Cui, Yihang Chen, Jiaer Huang, Boming Zhao, Peter Yichen Chen, Hujun Bao, Zhaopeng Cui
Abstract: Recent advances integrate physically grounded Newtonian dynamics with neural rendering frameworks, narrowing the gap between photorealistic scene reconstruction and physics-based animation. However, existing approaches focus on mechanically driven dynamics while neglecting temperature, a fundamental yet invisible physical factor underlying phenomena such as melting, solidification, and other thermomechanical processes. In this paper, we propose MeGAS, a novel framework that incorporates thermomechanical phase-change dynamics into 3D Gaussian Splatting (3DGS). Specifically, we propose a new thermomechanical dynamic Gaussian Splatting representation that augments 3DGS with temperature attributes and employs a heat advection-diffusion solver with MPM dynamics incorporating phase transitions, enabling physically plausible and visually realistic synthesis of thermophysical phenomena. Furthermore, a new topology-adaptive Gaussian rendering strategy is proposed to mitigate cracking and floaters under extreme deformation. Extensive experiments demonstrate that MeGAS produces physically consistent thermomechanical behavior while maintaining high-fidelity photorealistic rendering, advancing toward physics-integrated world models.
Authors: Wei Li, Jingyang Zhang, Guoan Wang, Junzhi Ning, Yang Chen, Guang Yang, Lixu Gu
Abstract: Universal segmentation models exhibit significant potential for diverse tasks involving different imaging modalities and segmentation objectives. Task-Incremental Learning provides a privacy-preserving approach to continually evolve a universal model on tasks from sequentially-arriving medical departments. However, training the model solely on the incoming task induces forgetting on past tasks, since consecutive tasks exhibit concurrent shifts in image appearance and segmentation objective. To address this problem, we propose a novel Coupled Comprehensive Generative Replay (C^2GR) framework that simultaneously synthesizes image-mask pairs of previous tasks to mitigate forgetting under concurrent appearance and objective shifts. This requires preserving image-mask correspondence for structure-realistic generation and bridging asynchronous optimization of the generator and segmentor for segmentation-oriented generation. Specifically, we propose a Bayesian Joint Diffusion (BJD) method that formulates the correspondence as conditional distributions optimized via conditional denoising. Furthermore, we develop a Relation-aware Unified Prompt Synchronization (RUPS) scheme to simultaneously modulate the generator and segmentor via a shared task-relation-aware prompt for synchronizing their optimization. Experiments on 20 tasks spanning diverse modalities and objectives demonstrate that C^2GR exhibits only a 2.44% drop in overall performance compared to joint training with all task data, effectively alleviating forgetting from the concurrent shifts. Our code will be made publicly available at https://github.com/mar-cry/C2GR.
Authors: Qin Lei, Jiang Zhong, Xin Xiao, Yuming Yang, Hao Wu
Abstract: Curvilinear object segmentation, including vessels and cracks, is challenging due to extreme spatial sparsity and topological fragility, where small local errors can cause severe structural disconnections. Meanwhile, modern segmentation pipelines increasingly rely on strong but hard-to-modify foundation encoders whose heavy downsampling limits fine structural recovery. Motivated by this, we focus on the post-encoder stage and study two recurring and actionable failure modes: a reconstruction bottleneck in high-resolution feature restoration and a decision bottleneck in binarization. We present PEPA, a lightweight Post-Encoder Plug-in Adapter for 2D curvilinear segmentation pipelines with accessible decoder/head features and target, query, or class descriptors. PEPA couples (i) Target-Conditioned Snake Upsampling (TCSU), which uses target-conditioned continuous snake-like sampling to better recover thin and tortuous structures during upsampling, and (ii) Target-Adaptive Differentiable Thresholding (TADT), which predicts target-specific thresholds and optimizes a soft-threshold surrogate with explicit safeguards against trivial bias shifting. Under this post-encoder interface, PEPA can be attached to both prompt-based decoders and conventional dense predictors. Experiments on five medical and industrial benchmarks show that adding PEPA to frozen-encoder baselines yields consistent improvements, with gains in topological connectivity (clDice) typically exceeding those in region overlap (IoU), indicating improved structural continuity. With only $\sim$0.26M additional parameters, PEPA offers a practical post-encoder enhancement for structure-centric segmentation.
Authors: Zhenyu Yi, Zhiyun Song, Yusong Sun, Zelin Liu, Manman Fei, Zhenhao Li, Jiaxuan Zhao, Xu Han, Lichi Zhang
Abstract: Automated diagnosis of 3D brain CT scans is essential for critical care, yet it remains challenging due to the heavy reliance on manual annotations and the limited semantic understanding of conventional models. While 2D foundation vision-language models (VLMs) have shown remarkable generalization, effectively transferring their representational power to 3D volumes remains an open problem. In this paper, we propose Brain-Adapter, a novel dual-stream multiple instance learning (MIL) framework that leverages pre-trained 2D biomedical VLMs and raw diagnostic reports for robust scan-level multi-label classification. Specifically, we introduce a Text-Conditioned Attention (TCA) mechanism, utilizing raw diagnostic sentences as semantic queries to dynamically align visual cues with specific disease concepts. Concurrently, a parallel visual MIL stream captures global scan characteristics, supervised by structured labels extracted via a Large Language Model (LLM). To ensure representation coherence, a consistency constraint enforces synergy between the two streams. During inference, an Uncertainty-Aware Refinement (UAR) module dynamically calibrates and fuses these dual-stream predictions to resolve ambiguous cases. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art 3D models and standard MIL approaches. By eliminating the reliance on dense annotations, Brain-Adapter provides a highly scalable and clinically viable solution for 3D acute intracranial pathology analysis.
Authors: Yohann Perron, Guillaume Astruc, Nicolas Gonthier, Clement Mallet, Loic Landrieu
Abstract: Vision Transformers (ViT) dominate computer vision. However, their reliance on rigid patch projectors hinders transfer to Earth Observation (EO), where input modalities, scales, and resolutions vary widely. We introduce UniverSat, a ViT-style backbone built around a Universal Patch Encoder that maps patches from arbitrary spatial, spectral, and temporal resolutions, and from both optical and non-optical sensors, into a shared embedding space with a shared set of weights. This enables training a single model on heterogeneous multimodal corpora via self-supervision, yielding robust, sensor-agnostic spatial features. We validate this approach with strong results across classification and segmentation on standard EO benchmarks from GeoBench, PANGEABench, and SpectralEarth. Our code and models are available at https://github.com/gastruc/UniverSat.
Authors: Jan-Niklas Dihlmann, Andreas Engelhardt, Simon Donne, Hendrik P. A. Lensch, Mark Boss
Abstract: Text and image conditioned 3D models now generate convincing assets, but they still offer little direct control over the space an object should occupy or avoid. In authoring, this spatial intent is often known before generation starts. A chair should fit a seating envelope, a prop should leave clearance for motion, or a part should expose a contact surface. Prompts and image views are poor carriers for such constraints, requiring the need for an explicit control interface. We present Arbor, a trainable attachment for text conditioned latent 3D generation. Arbor introduces constraint meshes as a native 3D control interface. The interface uses hull regions where geometry should exist, avoidance regions that should remain empty, and touch regions the object should contact. Unlike completion or whole object scaffold control, these meshes are not target evidence. They are local typed requirements and can include regions where no surface should appear. Arbor keeps this signal as geometry by converting constraint meshes into tokens and learning a routed attachment inside a frozen denoiser. Each latent region can therefore receive the part of the constraint that matters for its spatial location. We evaluate Arbor on automatic and artist curated control benchmarks with hull, avoidance, and touch constraints, and compare the metric trends to a user preference study. Even without dedicated compliance losses, Arbor improves constraint obedience while preserving object quality and variation under fixed constraints.
Authors: Merveilles Agbeti-Messan, Pierrick Tranouez, St\'ephane Nicolas, Cl\'ement Chatelain, Thierry Paquet
Abstract: End-to-end OCR increasingly relies on autoregressive sequence models, where the quadratic cost of Transformer attention limits efficient transcription of long, paragraph-level text. State-Space Models (SSMs) such as Mamba offer linear-time decoding and have recently been shown to match Transformer accuracy on printed historical lines, but their behavior as sequences grow from short lines to full paragraphs, and their generalization to handwriting, remain poorly understood. We study how a Mamba-based OCR recognizer scales from lines to paragraphs. We first conduct a systematic exploration of its four core hyperparameters (decoder depth, state dimension, expansion factor, and connector depth) on synthetic paragraphs from 100 to 1,000 characters, identifying the recurrent state dimension and the expansion factor as the dominant levers for long-sequence accuracy. We then compare the recognizer against a Transformer baseline trained under an identical protocol. On clean synthetic paragraphs, both models stay below 1% CER at every length while the SSM runs 1.4 to 4.5 times faster, the speedup growing with sequence length. On real handwriting, however, the SSM lags clearly behind: it reaches 8.2% CER on IAM lines and 10.0% on IAM paragraphs, against 4.2% and 3.5% for the Transformer baseline. Through controlled experiments we show that a substantial part of this gap stems from data scarcity rather than from an intrinsic architectural limit: the autoregressive SSM decoder is markedly data-hungry on long sequences. Our study clarifies when SSMs are a practical choice for large-scale document transcription and when they are not.
Authors: Tongkun Guan, Haocheng Wang, Wei Shen, Xiaokang Yang
Abstract: Visual document retrieval requires rapidly locating relevant pages from large multi-modal corpora in response to user queries. While recent methods powered by Multi-modal Large Language Models (MLLMs) show competitive accuracy, they suffer from prohibitive computational costs by applying intensive MLLM encoding to every single page. Meanwhile, we observe that user queries are typically keyword-anchored, containing semantically rich words that are expected to appear directly in the visible text of relevant pages, offering an efficient cue for quickly narrowing down candidate pages. Building on this insight, we propose LightSTAR, an efficient framework that decomposes visual document retrieval into: 1) LLM-free Visual Selection, which utilizes content-grounded query encoding to focus on informative words and employs LLM-free visual embeddings to produce a high-recall candidate set; and 2) Vision-adaptive Semantic Refinement, which further performs fine-grained semantic matching exclusively on these top candidates via adaptive region-wise feature fusion to effectively combine textual and layout cues, optimized through a hardness-aware contrastive objective. Experimental results demonstrate that LightSTAR achieves state-of-the-art retrieval accuracy while reducing end-to-end latency by several-fold, offering a highly practical solution to the accuracy-efficiency trade-off in visual document retrieval. Code is available at https://github.com/bokufa/LightSTAR.
Authors: Suraj Prasai, Kangning Cui, Rongkun Zhu, Sarra Alqahtani, Ying Zhang, Victor Paul Pauca, Miles R. Silman, Fan Yang
Abstract: Forest imagery analysis often involves multiple tightly coupled vision tasks, which must be performed under substantial variation in geographic regions, sensors, and acquisition conditions. However, practitioners often lack a unified tool that is geospatial-native, cloud-optimized, and ML-integrated for end-to-end workflows spanning annotation, prediction, visualization, and downstream analysis at scale. We present AwakeForest, an interactive end-to-end platform designed for large-scale forest imagery that integrates model-assisted inference, automatic annotation, and human-in-the-loop refinement within a single workflow. Our platform supports plug-and-play integration of pretrained models and enables scalable interaction with forest imagery ranging from standard aerial scenes to large orthomosaics that can span several gigabytes to hundreds of gigabytes. AwakeForest produces analysis-ready outputs that can be directly used for downstream analysis and to support iterative model and annotation updates on new scenes. We demonstrate the system on the PALMS dataset and illustrate how AwakeForest supports an end-to-end workflow for practical forest management and analysis.
Authors: Jiho Choi, Seonho Lee, Seojeong Park, Hyunjung Shim
Abstract: Multi-view 3D Visual Question Answering (MV3D-VQA) requires integrating partial observations into a coherent 3D scene representation and selecting informative viewpoints for multi-step spatial reasoning. However, current multimodal LLMs are typically trained with sparse, answer-level supervision, which often yields inconsistent cross-view reasoning and brittle view selection. We present DR-MV3D (Dense Reward for MV3D-VQA), a map-grounded learning framework that provides dense, verifiable rewards to supervise the reasoning process. Our approach decomposes MV3D-VQA into (i) allocentric global map construction, (ii) question-conditioned view-trajectory planning, and (iii) egocentric grounding for answer prediction. To make intermediate steps learnable without manual annotations, we introduce two rewards: a global consistency reward that aligns the predicted map with geometry-consistent pseudo targets from frozen 3D vision foundation models (e.g., VGGT + SAM3), and a local trajectory reward that supervises ordered viewpoint selection. We optimize the full pipeline with trajectory-level policy optimization (GRPO). Experiments on MindCube, VSI-Bench, and BLINK (MV) show that DR-MV3D consistently improves over strong multi-image baselines, supporting the effectiveness of process-level dense supervision for multi-view 3D reasoning.
Authors: Mohamed Nagy, Naoufel Werghi, Jorge Dias, Majid Khonji
Abstract: The tracking-by-detection paradigm in multi-object tracking (MOT) typically relies on static appearance descriptors to complement motion estimation. However, these descriptors are frame-independent, limiting their robustness as visual cues. Since such descriptors are often obtained from computationally intensive pretrained backbones, real-time MOT systems frequently abandon appearance cues altogether and rely solely on motion prediction and geometric association. In this work, we introduce Polycepta, an object-centric appearance state estimation framework that reformulates appearance modeling as a recursive estimation problem rather than a frame-wise matching task. Polycepta constructs and continuously updates an independent appearance state for each tracked object, enabling future appearance representations to be estimated from accumulated observations. Polycepta is encouraged to learn the appearance-state construction of object-specific representations rather than memorize them through a proposed learning strategy, enabling appearance estimation for unseen classes. A key property of Polycepta is that the quality of appearance estimation improves as object states evolve during inference. While conventional appearance descriptors remain static or degrade over time, Polycepta progressively refines appearance estimates as additional observations are accumulated. Extensive experiments on KITTI, the Waymo Open Dataset, and MOT17 demonstrate consistent reductions in identity switches and improvements in tracking performance when integrated into the tracking-by-detection pipelines. Polycepta operates at 90.57 Hz and delivers state-of-the-art performance on the KITTI benchmark when integrated into the RobMOT framework, achieving a MOTA of 92.27\%.
Authors: Hongkai Zheng, Ta-Ying Cheng, Benjamin Klein, Yisong Yue, Zhuoning Yuan
Abstract: Video diffusion models have enabled remarkable progress in video generation and editing. However, content preservation remains a core challenge: existing methods regenerate every pixel and often alter elements that should remain unchanged, such as characters or background scenes. We introduce Vera, a layered diffusion framework for content-preserving video editing. Instead of regenerating the entire video, Vera generates an edit layer along with an alpha matte for compositing with the source video, separating creative editing from content preservation by design. To encourage coherent composition with the source video, we extend the text-to-video DiT into a Mixture-of-Transformers (MoT) architecture, with separate DiTs for each layer that interact through joint self-attention. To support the training of Vera, we further construct a high-quality layered dataset with accurate alpha mattes, diverse scenes and dynamics, and visual effects. Across our quantitative benchmark and human preference study, Vera outperforms leading open-source video editing models in content preservation while remaining competitive in edit quality, using 486K frames of layered training data.
Authors: Andrei Liviu Nicolicioiu, Sarvjeet Singh Ghotra, Morgane M. Moss, Aaron Courville
Abstract: The availability of large amounts of clean data is paramount to training neural networks. However, at large scales, manual oversight is impractical, resulting in sizeable datasets that can be very noisy. Attempts to mitigate this obstacle to producing performant vision-language models have so far involved heuristics, curated reference datasets, and using pre-trained models. Here we propose a novel, bootstrapped method in which a CLIP model is trained on an evolving, self-selected dataset. This evolving dataset constitutes a balance of filtered, highly probable clean samples as well as diverse samples from the entire distribution. Our proposed Self-Filtering method iterates between training the model and selecting a subsequently improved data mixture. Training on vision-language datasets filtered by the proposed approach improves downstream performance without the need for additional data or pre-trained models.
Authors: Nathan Senyard, Salem Hamdani, Astrid Zhang, Derek Wang, Evan Shelhamer, Mathias L\'ecuyer, Jos\'ephine Gantois
Abstract: We propose Hedgementation: a new benchmark to evaluate machine learning models for hedgerow mapping from remote sensing data at country scale and 10m$^2$ spatial resolution. We combine and harmonize multiple remote sensing data products and ground truth labels sourced from a hedgerow inventory in France. We measure the ability of three baseline models to generalize across spatial distance, and across climatic zones, a more explicitly challenging task. Our benchmark tests both supervised and self-supervised learning approaches for remote sensing, applied to tracking fine-scale features of high agricultural importance. The code to reproduce the benchmark and baselines results is available at https://github.com/hedgementation/hedgementation.
Authors: Hongli Xu, Jiaqi Hu, Junwen Huang, Boyang Zhong, Peter KT Yu, Nassir Navab, Benjamin Busam, Slobodan Ilic
Abstract: Estimating the 6D pose of unseen objects is a fundamental yet challenging problem for open-world robotics and embodied perception. Model-based methods are accurate but depend on CAD assets or heavy onboarding, while most model-free approaches are still limited to pairwise single-anchor matching and thus fail under occlusion and large viewpoint changes with low query-reference overlap. Therefore, we present PANY, a unified model-free framework that seamlessly supports both RGB and RGB-D inputs, operates on one or sparse pose-free reference views, and generalizes effectively to novel objects. Built on a multi-view transformer geometry backbone, PANY moves beyond pairwise matching by learning view-consistent geometry and cross-view alignment cues that remain stable under wide baselines and limited overlap. When additional unposed assist views are available, PANY aggregates them via pose-graph canonical registration to increase geometric coverage and reinforce the final pose. Extensive experiments show that PANY achieves state-of-the-art performance across multiple benchmarks, substantially outperforming existing model-free methods, improving pose accuracy by +12% on YCB-V and over +20% on LM-O. Furthermore, PANY consistently performs well under both single-reference and sparse-reference settings, demonstrating strong robustness in real-world environments.
Authors: Diego E. Farchione, Ramzi Idoughi, Peter Wonka
Abstract: Accurate volume and surface area estimation is critical for diverse applications, from marine ecology to medical diagnostics. However, existing methods often suffer from high computational costs and poor performance with sparse and noisy data. We propose a fully feed-forward framework that regresses scale-normalized volume and surface area and their associated uncertainties directly from multi-view images. By fusing 3D point cloud reconstructions with view-aligned 2D features through a graph-based decoder, our model bypasses iterative optimization, ensuring exceptional scalability and rapid inference. Experimental results demonstrate that our approach outperforms state-of-the-art methods, particularly when operating with a low number of input images. Validated across coral monitoring, dietary analysis, and anthropometry, our proposed framework provides a robust, adaptable solution for quantitative shape analysis. This architecture provides a high-speed, scalable alternative for precise geometric estimation from visual data, maintaining high performance even in resource-constrained or sparse-view scenarios.
Authors: Kaizhen Tan, Hanzhe Hong, Siru Tao
Abstract: Text-to-image models can generate visually plausible city streets, but whether their outputs correspond to a requested road segment rather than a generic city prior remains unclear. We introduce GeoFidelity-Bench, a reference-panel benchmark for segment-conditioned geographic fidelity in street-view generation. It contains 7,117 curated Mapillary images covering 109 named OpenStreetMap road segments in 25 cities across six continents. For each generated panel, the benchmark ranks the target reference panel against panels from the nearest segment in the same city, other segments in the same city, and segments from other cities, making local discrimination rather than absolute target similarity the primary test. We evaluate six open-weight text-to-image generators under city-only, street-and-neighborhood, and GPS-augmented prompts. Adding street and neighborhood names is associated with an increase of 5.5 percentage points in top-1 retrieval accuracy over city-only prompts, with a 95% confidence interval from 3.4 to 7.7 percentage points. However, the similarity margin between the target and the nearest segment in the same city remains near zero, indicating that local names improve broad local plausibility more than exact segment identity. Prompts that keep the city fixed but use incorrect street or neighborhood names further show that only part of the gain depends on the correct local names, while appending raw GPS coordinates as ordinary text yields no statistically clear additional benefit. Held-out real-image queries successfully recover segment identity, showing that the curated references contain usable segment-level signal. GeoFidelity-Bench thus reveals a persistent gap between city- or neighborhood-plausible street-view generation and faithful generation for a specific road segment.
Authors: Sai Kumar Dwivedi, Federica Bogo, Bu\u{g}ra Tekin, Chenhongyi Yang, Nadine Bertsch, Tomas Hodan, Michael J. Black, Dimitrios Tzionas, Shreyas Hampali
Abstract: Generating human-object interactions (HOI) is central to character animation, robotics, AR/VR, and embodied AI. Recent HOI generation methods synthesize motion from text, object geometry, and sparse waypoints, controlling action semantics and object trajectories. However, these signals underspecify interaction: the same prompt and trajectory can produce different grasps, approach directions, body poses, object poses, contacts, and body-object layouts. We address this ambiguity with a reference image as a visual specification of the desired interaction snapshot. However, a single global image representation conflates distinct cues and conditions all frames on identical visual evidence. We therefore introduce IMAGIN-4D, a diffusion-based HOI generator that decomposes image conditioning spatio-temporally. For spatial conditioning, IMAGIN-4D extracts supervised interaction-state tokens for body pose, object pose, body-object contact, and spatial relationships at the depicted frame. For temporal conditioning, it computes frame-aware tokens by querying image patches per generated frame, allowing sequence segments to attend to different visual cues from the same image. To balance image, text, and waypoint cues, IMAGIN-4D uses role-aware conditioning: text, waypoints, and interaction-state tokens use separate AdaLN streams, while frame-aware visual tokens cross-attend with motion tokens. Since HOI motion datasets lack paired images, we build a synthetic motion-to-image rendering pipeline from FullBodyManipulation (FBM) and introduce an image-adherence metric to evaluate whether generated motions match the reference snapshot. Experiments on FBM and BEHAVE show that IMAGIN-4D improves fine-grained interaction control over single-token and uniformly image-conditioned baselines while preserving waypoint-following and motion quality. Code and models will be released at https://imagin4d.github.io.
Authors: Cong Han, Xiaohan Lan, Haibo Qiu, Yujie Zhong
Abstract: Following the paradigm shift initiated by OpenAI o3, interleaved reasoning with code to enhance multimodal large language models (MLLMs) has become a pivotal research frontier. The existing literature focuses primarily on tool-use within vision-perception tasks. However, such approaches typically rely on predefined heuristics for visual manipulation and are inherently incapable of addressing numerical computation problems due to their exclusive focus on visual operations. This paper empowers MLLMs with adaptive interleaved reasoning capabilities through extended reinforcement learning training on code-augmented complex numerical computation tasks. To this end, we propose a comprehensive three-component solution consisting of: a two-stage cold-start data construction pipeline, data filtering strategies for RL dataset curation, and an adaptive tool-invocation strategy leveraging a group-constrained reward function for interleaved reasoning trajectories. Extensive experiments demonstrate that after Reinforcement Learning training with the group-constrained reward function, performance improves by an average of 6.1 percentage points (pp) on evaluation benchmarks. Specifically, the accuracy for interleaved reasoning samples increases by 9.9 pp, and the overall success rate of tool-use exceeds 95%. Our data and code are available at: https://github.com/CongHan0808/AIR.git.
Authors: Sara Dorfman, Maya Vishnevsky, Omer Dahary, Or Patashnik, Daniel Cohen-Or
Abstract: Modern text-to-image models excel in visual fidelity and prompt adherence. However, this strict adherence comes at the cost of diversity: generated samples tend to collapse into a single visual interpretation. Existing methods to improve diversity produce outputs driven by incidental variations rather than meaningful design choices. This motivates a new variant of the diversity task where structure is enforced on the generated samples. We introduce a method for controlled diversity that enables Semantic Browsing, where users can navigate structured image galleries and experience creative exploration through a systematic traversal of meaningful, interpretable axes of variation. Achieving this level of semantic control requires a deep understanding of the scene. We exploit the fact that recent text-to-image models are trained on elaborated captions, effectively decoupling semantic decision-making from pixel generation. This enables a paradigm shift: instead of relying on stochastic variation within the text-to-image model, we induce diversity directly at the text level. By leveraging rich textual representations, we allow a Vision Language Model (VLM) to operate on the full scene context. To overcome the generic outputs typical of standard VLMs, we employ an agentic workflow that explicitly enforces structured variation attuned to the original prompt. We demonstrate that our method produces diverse and navigable design spaces where every variation corresponds to a specific, user-understandable semantic decision.
Authors: Rishubh Parihar, Ayush Raina, R. Venkatesh Babu, Or Patashnik
Abstract: Reference-based diffusion models enable highly controllable image generation by leveraging elements from input images to guide prompt-driven synthesis. However, these models are computationally expensive in runtime, and their cost scales severely with the number of input references. While the efficiency of diffusion models has been extensively studied in the context of prompt-driven generation, it remains largely under-explored in the realm of reference-based models. This setting presents unique challenges not addressed by methods focusing solely on generation. In particular, the wasteful representation of references as dense token grids offers significant opportunities for improvement. In this work, we present Sparse Context, a method for constructing sparse reference representations by retaining only a reduced subset of reference tokens. We observe that even without modifying the model, dropping a significant portion of reference tokens at inference time largely preserves its generation capabilities. To fully realize this potential, we fine-tune the model with random token dropping at varying ratios, encouraging robustness to partial reference representations. Crucially, this training strategy decouples the model from any specific token selection rule, allowing flexible control at inference time. At inference time, instead of random dropping, we apply task-aware token selection strategies that prioritize the most informative regions of the reference images, adapting the token budget to the input and task requirements. Extensive experiments show our method achieves a 4x increase in inference speed for multi-reference generation and an 2x for single reference generation. Importantly, this efficiency is achieved without compromising visual quality across both spatially-aligned editing and subject-driven generation.
Authors: Yehonathan Litman, Xiaoxuan Ma, Manan Shah, Nicolas Ugrinovic, Kris Kitani, Fernando De la Torre, Shubham Tulsiani
Abstract: Reconstructing dynamic non-rigid objects from monocular video requires integrating visual cues from direct observations with data-driven priors over geometry and appearance. Prior approaches either learn to directly predict 4D representations from visual input or initialize a 3D representation that is subsequently deformed and refined based on video evidence. However, the former are constrained by the scarcity of 4D training data, while the latter leverage priors only for the initial reconstruction and rely solely on video supervision thereafter; neither handles complex in-the-wild scenarios with large deformations and occlusions well. We present Lift4D, a test-time optimization framework that addresses both limitations. First, we adapt an existing single-view 3D reconstruction model to yield temporally consistent per-frame predictions via causal latent conditioning, providing a coherent initialization for a deformable 3D Gaussian Splatting representation. We then ``sculpt'' this representation to match the input video through an occlusion-aware optimization that faithfully recovers visible surface details while completing unobserved regions using a view-conditioned diffusion prior. We demonstrate that Lift4D clearly improves over prior 4D reconstruction methods, particularly on challenging in-the-wild sequences with severe occlusions and non-rigid motion.
Authors: Tai Hyoung Rhee, Dong-Guw Lee, Ayoung Kim
Abstract: Thermal infrared (TIR) imaging has been a popular choice for field robotics due to its robust perception capability under low light visual degradation, but it suffers from severe stochastic and fixed-pattern noise that breaks downstream estimation. This noise is intensified indoors due to low thermal contrast and uniform temperature distributions, contributing to the relative lack of indoor TIR deployments. Existing TIR denoising methods exhibit a poor accuracy-efficiency tradeoff, either too slow for online deployment required in robotics or insufficiently robust to severe degradation, while typically being trained on synthetic noise. Addressing these problems, we propose TIDY, a lightweight wavelet-domain denoiser trained on real clean-noisy TIR data. By reformulating TIR denoising in the wavelet domain, TIDY explicitly disentangles noise from structural content, enabling targeted suppression with reduced spatial complexity, significantly improving inference speed over prior methods (~34Hz). TIDY introduces two new metrics, Wavelet Entropy and Wavelet Directional Stripe Index, as complementary loss terms to explicitly suppress stochastic noise and stripe artifacts. Across severe indoor corruption and zero-shot settings, TIDY improves robustness and yields consistent gains in downstream robotics tasks including thermal inertial odometry and monocular depth estimation. Code and dataset is available at: https://github.com/williamrheeth/TIDY
Authors: Md Zabirul Islam, Md Motaleb Hossen Manik, Ge Wang
Abstract: Generative text-to-video systems can produce visually fluent educational clips, but they rarely encode the pedagogical content knowledge (PCK) needed for effective instruction, including prerequisite-aware sequencing, learner-adaptive depth, and sustained cognitive engagement. We present CourseBlueprint, a course-grounded pipeline for adaptive pedagogical video generation. Given a topic and learner persona, the system generates a structured teaching blueprint in a single forward pass over an undergraduate biomedical-imaging corpus (BMED 2300; twenty-three lectures, 1,116 slides). Instead of ad-hoc prompt chaining, the pipeline uses typed intermediate representations with validation: a scaffolding module builds a stage-labeled prerequisite concept graph with deterministic cycle removal, an adaptive controller assigns per-concept style specifications, and an engagement generator produces narration following a fixed hook->retrieval->core->analogy->forward contract. A deterministic slide-image override further grounds the rendered video by reusing instructor slides whenever retrieval confidence is high. We also release a reusable benchmark corpus and an evaluation harness combining repeated LLM-judge scoring with regex-grounded objective metrics. In a five-topic ablation, removing the engagement contract reduces the engagement score from 5.00 to 1.20, the adaptive score from 4.80 to 3.40, Flesch readability from 38.0 to 19.8, and analogy and retrieval-prompt counts to near zero. The slide-image override converts a 0/9 corpus-grounding failure into 9/10 successful slide matches on the same topic. These results show that pedagogical video quality depends less on surface fluency than on explicit, typed instructional contracts that make scaffolding, adaptation, engagement, and grounding auditable.
Authors: Mushtari Sadia, Zhenning Yang, Umme Habiba Lamia, Nishat Shawrin, Ang Chen, Amrita Roy Chowdhury
Abstract: Electrical circuit diagram QA tasks require complex mathematical reasoning, which remains challenging for multimodal LLMs. We present SPARC, a multi-agent system that answers questions over circuit diagrams by grounding reasoning in executable physics-based simulations. SPARC uses LLM agents to synthesize, execute, and analyze simulation programs, improving accuracy and reliability by design. It achieves 83% accuracy, with up to a 58% absolute improvement over baselines, while enabling systematic error diagnosis.
Authors: Matin Fallahi, Patricia Arias-Cabarcos, Thorsten Strufe
Abstract: A central challenge in EEG authentication is that models are typically tied to the acquisition settings in which they are trained. In particular, variations in headset hardware, channel layout, and signal duration create heterogeneous recordings that existing models are not designed to handle, causing each new headset or dataset to be treated as a separate model-development problem. This fragmentation limits multi-dataset learning, hinders knowledge transfer, and reduces model reusability. To address this limitation, we present NeuroShield, a reusable foundation model for EEG authentication that learns identity-discriminative embeddings from variable-channel and variable-length EEG recordings through a dual-stage transformer architecture. We pretrain NeuroShield on three public EEG datasets comprising 15{,}762 subjects and 28{,}116 sessions, and evaluate transfer on two unseen downstream datasets. Our evaluations show that, after fine-tuning, NeuroShield reduces equal error rate by 0.44--8.06 percentage points relative to the state of the art. NeuroShield further generalizes to segments longer than those seen during training and operates across channel layouts not encountered during pretraining. These results establish NeuroShield as a reusable and adaptable EEG identity encoder across heterogeneous recording settings. We release NeuroShield as open source to support reproducibility and community adoption.
Authors: Jiabo Ma, Cheng Jin, Yihui Wang, Hao Jiang, Ling Liang, Yingxue Xu, Junlin Hou, Zhengrui Guo, Zhengyu Zhang, Yifei Xia, Hongyi Wang, Fengtao Zhou, Zhe Xu, Huajun Zhou, Jiarui Ouyang, Qian Zeng, On Ki Tang, Eunhyang Park, Carolyn Glass, Ronald Cheong Kin Chan, Li Liang, Hao Chen
Abstract: Computational pathology has advanced rapidly with the emergence of foundation models, yet widespread adoption remains limited by substantial technical complexity and programming requirements. Here we present PathLab, an autonomous agentic framework that translates natural-language research objectives into executable and validated computational pathology workflows through the structured composition of domain-specific skills and tools. By organizing workflow generation around reusable methodological modules, including data preprocessing, model development, evaluation and interpretation, PathLab enables studies to be specified at the level of scientific intent rather than implementation details. We evaluated PathLab across 12 public datasets spanning four representative task families: region-of-interest classification, whole-slide image classification, segmentation and survival prediction. Across all task categories, PathLab achieved non-inferior performance relative to expert implementations, while consistently enforcing semantic validity of user prompts and proactively rejecting incompatible workflow specifications prior to execution. In controlled user studies, PathLab substantially reduced the time required to generate executable analytical pipelines and enabled domain experts without programming experience to independently design, execute and evaluate computational pathology studies. Together, these results establish PathLab as a reliable interface between biomedical intent and computational execution, enabling computational pathology studies to be designed at the level of scientific questions rather than programming expertise. By lowering technical barriers to advanced AI methodologies, PathLab provides a foundation for the broader democratization of computational pathology.
Authors: Yuxin Jiang, Chang Yu, Yunuo Chen, Xiang Feng, Yin Yang, Nishank Gite, Chenfanfu Jiang
Abstract: Video-world-model policies learn action-relevant representations by predicting future observations. However, they condition on only a short observation window, which renders long-horizon manipulation non-Markovian when the correct action depends on earlier events that are no longer visible. We present MemoryVAM, an episodic memory mechanism for video-world-model policies. We employ a Recap-Cue (RC) module, in which a Perceiver-based Recap Compressor maps per-frame CLIP embeddings into compact memory tokens, and a lightweight Cue Gate estimates task completion from memory and language. These tokens are injected into both the video backbone and the action decoder, aligning policy imagination with episode progress and conditioning actions on history. Our model trains the memory module with video prediction, a delta-reconstruction auxiliary loss, and episode-boundary supervision, requiring no per-frame progress labels. The same mechanism applies to UNet and Diffusion Transformer (DiT) backbones by changing only the cross-attention injection interface. On LIBERO-Mem, our model improves average success from 5% to 42.5%. On real robots, it achieves 78.3% success on counting tasks, 80.0% on spatial recall, and 75.0% on sequential tracking. Project page: https://MemoryVAM.github.io/
Authors: Colten Reissmann, Hugo Garrido-Lestache Belinchon
Abstract: Grayscale images are commonly found in historical photography restoration, medical imaging, and artistic media. However, automatically applying color to these images remains a significant challenge in computer vision because many plausible colorizations can correspond to the same grayscale input. In this work, we quantify the effect of text conditioning on pixel-level and perceptual metrics for grayscale-to-color image models. Specifically, we compare two architectures, a U-Net and Stable Diffusion 1.5, each tested with and without CLIP text conditioning while holding all other variables constant. Our results show that text conditioning improves PSNR by 5.6%, SSIM by 1.2%, and colorfulness by 36.6%, while reducing LPIPS by 7.6% in the U-Net tier. In the Stable Diffusion tier, text conditioning improves PSNR by 5.8%, SSIM by 1.5%, and colorfulness by 0.6%, while reducing LPIPS by 11.3%. These results indicate that text conditioning provides consistent, measurable improvements to colorization quality across both architecture scales.
Authors: Qiuhong Shen, Shihua Zhang, Yue Liao, Qi Li, Zhenxiong Tan, Shizun Wang, Shuicheng Yan, Xinchao Wang
Abstract: World Action Models (WAMs) are embodied predictive-action models that make a forecast of the future available to action. Recent WAMs repurpose large video generation models, and a parallel line relies on language or vision-language backbones without a video-generation core. This rapid expansion has blurred the boundary among broad world models, video generation models, action-grounded video world models, Vision-Language-Action policies, and WAMs. This survey gives the field a common account. It first clarifies these boundaries, then organizes existing works through two complementary views. The first view asks what each method is required to generate, spanning rendered futures, latent futures, and video-generation-free action reasoning. The second view decomposes each method by predictive substrate, backbone, action coupling, and deployment regime. This anatomy supports a unified discussion of interactability, causality, persistence, physical plausibility, and generalization, followed by data, evaluation, and open challenges. Across these axes, a consistent design pattern emerges: WAMs are not simply video generators with action heads, but predictive-action methods whose design choices trade representational richness against compute, memory, latency, and action-label cost. The field is moving toward methods that generate less of the future while preserving what control requires. The survey homepage is available at https://world-action-models.github.io/.
Authors: Austin T. Wang, Dongchen Yang, Angel X. Chang
Abstract: Developing robust models for 3D visual grounding (3DVG), the localization of entities in a 3D scene described in natural language, is important for enabling agents to correspond spatial language with objects in the physical world. However, the lack of diverse descriptions at scale prevents models from generalizing beyond simple linguistic patterns. Recent such attempts lack diversity in the constraint types and language used to ground objects. Captioning methods cannot precisely contrast objects, which is important for visual grounding. We therefore propose ViGiL3D++, a scalable, scene-agnostic method that generates diverse visual grounding queries by combining constraint sampling in scene graphs with the language generation of LLMs. We show that it has greater diversity over existing scaled datasets and improves model performance over several 3DVG benchmarks but also illuminates outstanding limitations of VLMs.
Authors: Yinhuan Huang, Hao Cao, Pu chen, Wenqi Guo, Zhijin Qin
Abstract: Diffusion-based image compression methods, leveraging powerful generative priors, have demonstrated remarkable perceptual quality at ultra-low bitrates. However, adapting modern generative models to image compression often relies on carefully engineered conditioning or auxiliary branches, together with substantial retraining, and these costs grow as the models scale. This motivates an open question: Can stronger generative priors be integrated into compression through a simpler, more extensible design? To answer this, we propose FlowCodec, a streamlined framework that plugs pretrained large-scale text-to-image priors (e.g., Qwen-image-2512 and FLUX.1-dev) into ultra-low-bitrate codecs. FlowCodec decomposes the pipeline into two decoupled stages: (1) Latent Compression, which maps clean latents to bitrate-constrained noisy latents; and (2) Latent Transport, which leverages the pretrained prior to refine the noisy latents toward the clean ones in a single step. Notably, FlowCodec requires neither additional conditioning signals nor auxiliary networks. Furthermore, with lightweight adaptation, it can flexibly support multiple bitrates while keeping the number of trainable parameters below 0.54% of the generative backbone. Experiments show that FlowCodec preserves high visual quality at bitrates below 0.05 bits per pixel. The Qwen-image variant significantly outperforms existing methods in terms of LPIPS and DISTS, while both variants deliver higher PSNR and clearly faster encoding than existing one-step diffusion-based methods, with the FLUX variant also maintaining competitive decoding speed.
Authors: Jiancheng Zhao, Xiang Ji, Yifan Zhan, Zunian Wan, Yinqiang Zheng
Abstract: Image compression for machines calls for a unified codec that serves multiple downstream vision tasks. Existing approaches either adopt task-specific end-to-end designs, raising parameter and deployment overhead, or rely on transfer-based adaptations that remain externally attached and heuristic task design. A key limitation shared by both lines of work is their largely static computation pattern, which applies similar transformations across tokens despite the fact that different image regions exhibit markedly different semantic importance and complexity for machine perception. We propose MoECodec, a token-aware image compression framework that supports multiple downstream tasks within a single model. MoECodec replaces the FFN layers in transformer-based compression model token-wise Mixture-of-Experts (MoE), enabling dynamic, token-level computation conditioned on the input content and task objective. To make MoE effective in compression model, we introduce a stable routing strategy that combines expert-choice routing with spatial total variation regularization to encourage spatially coherent assignments, and we propose a lightweight expert architecture, Group Shuffle MLP (GShMLP), to control parameter growth. Extensive experiments show consistent improvement against baselines on both conventional image reconstruction and machine tasks.
Authors: Zhiling Chen, David Gorsich, Matthew P. Castanier, Yang Zhang, Jiong Tang, Farhad Imani
Abstract: Robotic inspection relies on accurate sensing to acquire high-fidelity geometric measurements for defect detection and metrology. While prior work has focused on robot motion and viewpoint planning, how to configure sensing parameters remains largely underexplored, despite their decisive impact on measurement quality. We propose SenseHD, a robotic sensing system that formulates scanner configuration as an instruction-conditioned sensing decision. Instead of predicting precise parameter values, SenseHD treats sensing parameters as discrete sensing actions and selects stable sensing regimes through hyperdimensional associative memory. Experiments on a real robotic inspection platform demonstrate that SenseHD robustly selects appropriate sensing configurations and significantly improves inspection reliability, while remaining lightweight and efficient compared to baseline methods.
Authors: Sang-Hun Han, Min-Gyu Park, Jisu Shin, Seunghyun Shin, Jin-Hwi Park, Hae-Gon Jeon
Abstract: 3D human avatars have shown impressive visual fidelity driven by pose-conditioned models, yet they still lack the physical ability required for interactions with each other and environments. Although recent studies have made various attempts to incorporate physical characteristics into 3D avatars, they only exhibit limited physical deformations, often leading to constrained interaction behaviors. To resolve this issue, we present PIAvatar, a framework to simultaneously enable physically aware interactions between avatar-avatar and avatar-environment, and a non-rigid deformable human body simulation. In this work, our key insight is to decouple kinematic velocity from deformation gradient. When external forces act on avatars, the kinematic velocity induces stress which hinders the avatar's ability to achieve a desired pose. In addition, we integrate a skeletal framework within the avatar. It allows estimating its poses and real-time tracking in a closed form, even during non-rigid physical interactions. Our approach is implemented within a conventional Material Point Method framework to ensure physically consistent dynamics. We lastly evaluate the method on both human-object and human-human interaction scenarios to assess its behavior under diverse interaction settings.
Authors: Dayun Ju, Chanyoung Kim, Sunyoung Jung, Hyo-Jung Jung, Chena Lee, Younjung Park, Seong Jae Hwang
Abstract: Segmenting the temporomandibular joint (TMJ) disc from MRI is essential for accurate diagnosis of internal derangement, yet it remains unreliable in practice due to its small size, low contrast, and morphological variability. Existing methods, primarily adapted from general segmentation architectures, often produce fragmented or anatomically inconsistent masks, leading to unstable measurements of disc position and shape for downstream diagnosis. To address these challenges, we propose TISC, a TMJ disc segmentation framework that integrates semantic anchoring with clinical metadata-guided boundary refinement. The framework first establishes robust disc localization in the foundation model feature space via a Prototypical Semantic Anchoring (PSA) module that aggregates adjacent-slice MedDINOv3 features and derives a prototype-driven similarity map. It then performs targeted boundary refinement through a Clinical-Metadata Point Refinement (C-MPR) module, with point-wise predictions modulated by Mouth Open Limitation (MOL), a clinical indicator associated with disc displacement without reduction. On a large-scale cohort of 2,488 PD MRI volumes from 1,300 patients, our method achieves up to a 4.96 Dice improvement over strong baselines across diverse architectures, delivering more anatomically coherent and clinically reliable TMJ disc segmentation.
Authors: Dafna K. Matsegora, Stephen M. Watt
Abstract: We present an iterative algorithm to compute an arc-length parameterized spline interpolating a set of points. This differs from other methods where the computed spline either does not interpolate the original points or the parameterization is not the arc-length of the returned curves. Our method is applicable in any dimension $D \ge 2$, and we illustrate it with numerical results for plane curves.
Authors: Tian Dong, Yan Meng, Shaofeng Li, Guoxing Chen, Yuling Chen, Zhen Liu, Haojin Zhu, Hao Chen
Abstract: Training datasets have tremendous proprietary value and are vulnerable to unauthorized copying. Existing defenses mainly focus on tracking individual data points, but pay little attention to the threat of dataset regeneration. Through a measurement study of public tumor datasets, we identify substantial real-world partial-dataset replication, raising concerns about potential license noncompliance. To counter the challenge of tracking previously unknown adversarial regeneration, our key insight is that regeneration that preserves model utility inevitably preserves measurable signals across multiple feature scales. We categorize these dataset features into sample-, set-, and distribution-level features and design four similarity metrics to accurately identify regeneration. Based on these metrics, we develop DIPBox, which to our knowledge is the first testing framework that tracks regeneration suspects via multi-scale similarity testing across a spectrum of defender access settings, from limited to full information. We further provide a learning-theoretic analysis that justifies these multi-scale metrics and formalizes an inherent utility--divergence trade-off, implying fundamental limits on evasive regeneration. Extensive experiments on 16 vision and text base datasets, 320 regenerated datasets, and 590 derived models validate that DIPBox outperforms previous solutions while characterizing its robustness and limits under three adaptive attacks.
Authors: Edward Beng Wai Tan, Siew-Kei Lam, Dongshuo Zhang
Abstract: Recent 3DGS-SLAM systems enable real-time operation by leveraging conventional feature matching or ICP-based tracking, thereby avoiding the heavy dense photometric optimization used in earlier approaches. However, feature matching remains prone to failure in textureless environments, while ICP-based tracking struggles in structureless or geometrically degenerate scenes due to ill-conditioned optimization. To address this issue, we propose Spectral GS-SLAM, an efficient yet robust tracking framework that integrates ICP with complementary feature-based constraints. Our method mitigates numerical instability by adaptively compensating under-constrained directions in degenerate scenarios, without interfering with the shared Gaussian representation used for mapping. We further introduce a Gaussian-aware planarity weighting mechanism that exploits the intrinsic covariance structure of 3D Gaussians to characterize scene geometry and guide information fusion. Extensive evaluations on challenging TUM RGB-D sequences demonstrate that Spectral GS-SLAM achieves real-time performance (40.14 FPS) while maintaining consistent tracking in both structureless and featureless environments. The proposed method preserves trajectory integrity in degenerate scenes while maintaining competitive performance in non-adverse conditions.
Authors: Yi Wang, Ziyu Zhan, Yuran Wang, Hao Wang, Qiang Liu, Zuoqiang Shi, Lingyun Qiu, Xing Fu
Abstract: Imaging objects hidden outside the direct line of sight expands the effective field of view and is critical for applications such as autonomous driving and robotic perception. Despite impressive progress in time-of-flight (ToF)-based non-line-of-sight (NLOS) imaging, real-world deployment remains challenging because practical measurements are often collected over spatially limited, arbitrarily shaped relay regions-conditions that violate the planar-wall and dense-sampling assumptions made by most existing methods. To address these limitations, we propose a LOS-guided NLOS imaging pipeline that imposes no geometric assumptions on the relay surface and naturally supports both confocal and non-confocal configurations. Our method represents the hidden scene using 3D Gaussian primitives and couples them with an efficient, differentiable transient rendering model, enabling end-to-end optimization directly from measured transients. We validate our approach on real-world measurements from both a public dataset and a custom-built capture system. Across settings, our method achieves state-of-the-art reconstruction fidelity under spatially limited, sparsely sampled conditions, and significantly outperforms existing methods on complex, arbitrary relay surface geometries.
Authors: Florian Seligmann, Emiliyan Gospodinov, Enes Ulas Dincer, Gerhard Neumann
Abstract: Vision-language-action models (VLAs) achieve state-of-the-art performance on many robotic manipulation tasks, yet they can still behave unpredictably in out-of-distribution scenarios. Runtime failure detection is therefore essential for the safe real-world deployment of VLAs. However, existing task failure detectors require computationally expensive action sampling, are based on architectural assumptions that limit their applicability to VLAs, or need access to failure rollouts. We propose VLA-FAIL, a lightweight and broadly applicable failure detection framework for VLAs that combines two novel failure detectors with minimal overhead, without requiring failure data. The first, last-layer Mahalanobis distance (LLMD), detects out-of-distribution states by measuring token-wise deviations in last-layer features relative to the training data. The second, action chunk consistency (ACC), exploits the temporal overlap induced by receding-horizon control and detects failures when consecutive action chunks become inconsistent. To capture the trade-off between detection accuracy and detection latency, we introduce AUCPDT, a threshold-independent metric that jointly evaluates precision, recall, and detection time. Through extensive real-world and simulation experiments, we demonstrate that LLMD and ACC capture complementary failure modes whose combination enables reliable and early failure detection across diverse tasks, frequently outperforming significantly more expensive baseline methods.
Authors: Hanzhi Chen, Anran Zhang, Simon Schaefer, Kejia Chen, Shi Chen, Daniel Cremers, Oier Mees, Stefan Leutenegger
Abstract: A central question in robot learning is how to acquire skills from the kinds of data that humans learn from: passive observation, embodied practice, and the experience of failure. Human videos provide the first of these in abundance, and prior work has shown they can initialize useful policies. Far less clear is whether they can support the second and third: whether priors extracted from human videos can ground a robot's own attempts well enough to evaluate them, correct them, and improve from them. In this work, we show that human videos can be used to learn embodiment-agnostic action, dynamics, and value representations that transfer across robot embodiments, providing the predictive foundation required for robots to autonomously improve from their own rollouts and failures. We introduce Dynamics-Guided Action Correction (DGAC), a training-free approach that leverages these adapted models to repair failed states: each failure becomes a query for which the learned models propose and rank corrective actions, turning failures into supervision for the next policy update. Across seven real-world manipulation tasks spanning both a mobile manipulator and a static manipulator arm, our approach improves success rates from 40% to 81% across multiple policy backbones, demonstrating cross-embodiment robot self-improvement from human-video priors. These results show that human priors and robot failures can be combined to enable scalable autonomous policy improvement. Project page: https://ethz-mrl.github.io/robot-self-improvement-website/.
URLs: https://ethz-mrl.github.io/robot-self-improvement-website/.
Authors: Sampath Rapuri, Jeremy Ko, Benjamin D. Killeen, Russell H. Taylor, Mathias Unberath
Abstract: The ability to synthesize realistic X-ray images has catalyzed the development of AI models for X-ray image-guided procedures, which otherwise suffer from a lack of available annotated data. Prior work has demonstrated the effectiveness of mechanistic simulation of digitally reconstructed radiographs (DRRs) as a training data source for a myriad of tasks, including segmentation and anatomical landmark detection, with comparable or superior performance to real data training. However, mechanistic DRR synthesis still relies on the availability of annotated high-resolution anatomical models. Deriving these from CT images of real patients or specimens imposes an undesirable bottleneck on data quantity and variability. In this work, we explore two methods for synthesizing training data: (1) a 3D conditional latent diffusion model that generates CT volumes to use as inputs for mechanistic DRR generation without real, 3D anatomical models, and (2) a view-conditioned 2D diffusion model that produces synthetic X-rays. In controlled experiments, we demonstrate that synthetic 2D diffusion-based X-rays can be used to train an anatomical landmark detection model that generalized to real X-ray images with performance rivaling that of a model trained on real X-ray images. Thus, we provide preliminary evidence that synthetic, 2D diffusion-based training data can substitute for real X-ray data, identifying a promising avenue towards generating large, diverse datasets for training robust AI models in interventional X-ray imaging.
Authors: Ling Chen, Ruinan Jin, Jun Luo, Hanliang Chen, Quirin Strotzer, Rongkai Yan, Yuan Xue, Luciano Prevedello, Dufan Wu
Abstract: Automated radiology report generation (RRG) has gained increasing attention because it can reduce the heavy workload of clinical report writing. However, most existing methods mainly optimize for natural language generation (NLG) metrics that focus on language fluency, while providing little control over clinically important factors such as precision and recall. As consequence, generated reports may be fluent but not well aligned with different clinical needs. To address this challenge, we propose a reinforcement learning framework for precision recall controllable RRG, where a control parameter explicitly adjusts the trade-off between clinical precision and recall during inference. This design allows the model to flexibly generate reports according to different clinical requirements. To ensure clinical correctness, we introduce a clinical reward into the training objective, which helps improve clinical efficacy (CE) beyond standard language-based optimization. In addition, we apply a group-relative training strategy that normalizes rewards within each training group, reducing reward variance and improving training stability. Extensive experiments on the MIMIC-CXR dataset show that our method consistently outperforms state-of-the-art approaches in both NLG and CE evaluation metrics, while providing reliable control over the CE precision recall trade-off.
Authors: Yitao Jiang, Roy Xing, Luyang Zhao, Brian Plancher, Muhao Chen, Devin Balkcom
Abstract: Vision--Language--Action (VLA) controllers are often built by extending vision--language models (VLMs) with action supervision, relying on multimodal backbones with large data and compute requirements. We demonstrate that a text-only large language model (LLM) can be adapted into a VLA-style controller when visual observations are rendered into a text input using an ASCII representation. This ASCII-as-vision interface enables existing training and deployment stacks for LLMs to efficiently condition on visual state, follow natural-language instructions, and produce constrained, executable actions. We fine-tune and compare multiple LLMs and VLMs across model families and scales, using both expert demonstrations from a planning-based teacher, as well as DAgger for iterative improvement. In a 2D manipulation benchmark, in both simulation and on a physical manipulator, the resulting controllers can identify task-relevant entities and plan feasible action sequences. Our results suggest that ASCII rendering can serve as a lightweight, interpretable modality bridge from images to text, complementing conventional VLA pipelines, and opening directions for VLA research with text-only backbones.
Authors: Nikolaos Tsagkas, Andreas Sochopoulos, Chris Xiaoxuan Lu, Oisin Mac Aodha, Alexandros Kouris
Abstract: Deploying generalist robotic agents in the real world requires transferable skills. Specifically, a policy trained to clone a behavior from object-specific demonstrations must generalize beyond that object, otherwise data collection requirements become intractable. Recently, fine-tuning of pre-trained billion-parameter Vision-Language Models (VLMs), initially on large-scale robot datasets and then on fewer scenario-specific demonstrations, has emerged as the predominant paradigm for designing Vision-Language-Action (VLA) models. While these policies achieve state-of-the-art manipulation performance in-distribution, they remain brittle to minor spatial, semantic, and task variations. In this work, we address the inability of current models to decouple the declarative (i.e., concepts and entity semantics) from the procedural knowledge (i.e., how to do something) encoded in their parameters, which is a fundamental bottleneck for zero-shot skill transfer to novel objects. To address this, we propose w$^{2}$VLA, a new VLA model with restructured information flow. Rather than feeding all multimodal tokens from the VLM encoder into a large, opaque transformer-based action expert, our approach modulates the robot state sequence with visual, spatial, and skill information in a compositional and interpretable manner. Unlike popular, state-of-the-art VLAs, we show that our modular approach successfully decouples knowledge representations, enabling robust behavior cloning and unprecedented zero-shot skill transfer capabilities across dissimilar, unseen objects.
Authors: Trishna Saikia, Anup Kumar Gupta, Puneet Gupta, Pasi Liljeberg
Abstract: Respiratory rate is a vital indicator of pulmonary and cardiovascular health, yet conventional methods for estimating respiratory rate are often intrusive due to their contact-based nature. Remote photoplethysmography offers a promising non-contact alternative and has been widely used for heart rate estimation; however, its potential for respiratory rate estimation remains underexplored. Existing methods typically adapt green and chrominance-based projections originally designed for heart rate estimation, which only partially capture respiratory dynamics. Most prior work focuses on the Eulerian representation with fixed or empirically selected RGB projections. To address these gaps, we propose a skin-tone-aware dynamic RGB signal projection that captures respiratory information. To mitigate the sensitivity of the Lagrangian representation to non-respiratory motion, we introduce a denoising network for motion-based remote photoplethysmography signals. We further design a phase-independent contrastive loss that enables Eulerian and Lagrangian representations to collaboratively learn respiratory rate information. We also introduce RR-rPPG, a respiratory-rate facial video dataset with Indian demographic representation. We evaluate the method on RR-rPPG and the publicly available COHFACE dataset, where it consistently outperforms comparison methods and achieves up to a 42.1% reduction in mean absolute error across the evaluated settings. The proposed framework demonstrates the effectiveness of jointly leveraging skin-tone-aware Eulerian and denoised Lagrangian representations for contactless respiratory rate estimation from facial videos. In addition, RR-rPPG contributes a diverse benchmark resource for future research in remote respiratory monitoring. The code and dataset will be made publicly available upon paper acceptance.
Authors: Nan Ming, Yeqiang Qian, Chunxiang Wang, Ming Yang
Abstract: Robust obstacle segmentation is essential for the safety of intelligent robots, where LiDAR-based perception systems play a fundamental role in the robot-environment interaction. While extensive LiDAR-based approaches have demonstrated high performance on common obstacles in urban scenarios, their results on tiny obstacles such as curbs, gravel, and potholes remain unsatisfactory due to the significant similarity between tiny obstacles and inherent road undulations. Moreover, their segmentation accuracy even deteriorates sharply when the LiDAR scans suffer from degradation in challenging off-road scenes. To overcome these bottlenecks, we propose LOGOS, a LiDAR-only unified tiny obstacle segmentation system, which models the road surface as a continuous mixture of 2D Gaussian primitives and distinguishes tiny obstacles via high-presicion elevation estimation. Unlike existing Gaussian splatting methods that rely on iterative RGB training, LOGOS is a backpropagation-free LiDAR-only approach. It directly estimates Gaussian parameters via a freespace-aware initialization by incrementally pruning non-road primitives using smoothness constraints. Subsequently, pointwise signed distances are computed via a novel normal-aware elevation splatting function, ensuring robustness to both flat and sloped terrains. We evaluate LOGOS on a highly heterogeneous benchmark of point cloud frames collected from urban mobility scenarios and mining haulage off-road environments. These data are practically acquired using different LiDAR sensors and exhibit large variations in point density, terrain roughness, and obstacle types. Experiments on the road and off-road scenes demonstrate that LOGOS significantly outperforms other state-of-the-art methods, particularly in degraded point cloud regions and challenging off-road scenarios, while maintaining real-time efficiency.
Authors: Wooseung Kim, Sung-Hong Park
Abstract: Functional magnetic resonance imaging (fMRI) utilizes echo-planar imaging (EPI) to capture blood-oxygen-level-dependent (BOLD) signals with high temporal resolution. However, EPI is inherently sensitive to magnetic field inhomogeneities, resulting in susceptibility-induced geometric distortions along the phase-encoding (PE) direction. To correct these distortions, conventional approaches rely on additional calibration scans, such as field maps or reverse PE acquisitions, which are not always available in practice. To overcome this limitation, we propose SACRED, a calibration scan-free susceptibility distortion correction framework that corrects geometric distortions via image translation-based registration using only a routinely acquired anatomical T1-weighted (T1w) image and a unidirectional PE BOLD image. SACRED employs an invertible neural network as the image translation backbone to bridge the contrast gap between BOLD and T1w images while enforcing structural consistency through a modality independent neighborhood descriptor. This design enables the use of a mono-contrast similarity objective to train the registration network in an unsupervised manner without requiring distortion-corrected BOLD images. In addition, we incorporate test-time adaptation (TTA) to further enhance performance on out-of-distribution (OOD) data at inference time. SACRED was evaluated on one in-distribution (ID) dataset and two OOD datasets, and was compared with representative fMRI distortion correction methods. The results demonstrate that SACRED significantly outperforms competing methods on both ID and OOD datasets, exhibiting robustness to scanner and population shifts, partly enabled by TTA. The code will be made publicly available upon acceptance.
Authors: Efe Il{\i}cak, Baris Imre, Chlo\'e Najac, Ruben van den Broek, Beatrice Lena, Andrew Webb, Marius Staring
Abstract: Deep unrolled networks (DUNs) integrate physical forward models with learned regularization in cascaded network architectures, achieving exceptional performance in inverse problems while maintaining interpretability. While most DUNs operate in the object domain (e.g., image space), recent variants explored representation spaces for improved information flow. However, these methods rely on heuristic methods for data consistency (DC), sacrificing fidelity with measurements. In this work, we introduce DUNE (Deep Unrolled Networks in rEpresentation space), a framework that maintains exact adherence to physical measurements while operating in learned representation spaces. By deriving the DC gradient via the chain rule and implementing it through the Vector-Jacobian Product (VJP), we enable exact backpropagation of measurement residuals into the representation space. This formulation supports diverse architectural backbones, including pre-trained encoders to guide the iterative process. We assess DUNE against state-of-the-art baselines on accelerated MRI reconstruction tasks, demonstrating that exact VJP-based gradients yield superior reconstruction quality and structural fidelity across both single-channel portable low-field and multi-channel clinical high-field MRI acquisitions. The code will be available upon publication at https://github.com/EfeIlicak/DUNE.
Authors: Lorenzo Catania, Dario Allegra
Abstract: Implicit Neural Representations (INRs) have recently emerged as a promising paradigm for image compression, offering a fundamentally different approach from traditional and learned codecs. Nevertheless, INR-based methods for image compression suffer from long encoding times and a consistent performance gap in classic quality metrics such as PSNR. In this work, we explore the potential of purely INR-based compression methods and we propose PaaF (Picture as a Function), a novel INR-based image codec that introduces improved architectural design, adaptive quantization, and an efficient entropy coding scheme. These components are designed to enhance rate-distortion performance while preserving the simplicity and parallelizability of INR-based decoding. Experimental results demonstrate consistent improvements over existing INR-based methods in both quantitative metrics and perceptual quality. These findings highlight the potential of INR-based approaches and contribute to narrowing the gap between functional representations and more established compression paradigms.
Authors: San Dinh, Zichao Wendy Di, Matt Menickelly
Abstract: In X-ray tomography, reconstruction quality generally improves with larger numbers of projections. However, more projections increase experiment costs, acquisition time and the radiation dose imparted to the sample. One mitigation to these trade-offs is to adopt a sequential design of experiments, in which each subsequent measurement is determined as a function of previously acquired data in order to maximize information gain. In practice, a widely used heuristic to maximize information is to align beams with the edges of the sample. A key challenge, however, is that the true sample is unknown, so identifying edge-aligned beams typically requires reconstructing the sample based on available measurements. This work proposes a novel sequential design method that identifies edge-aligned measurements directly from the sinogram, bypassing any reconstruction, thereby improving computational efficiency and reducing the experimental design's susceptibility to reconstruction errors. Our method dynamically selects the next set of measurement beams by maximizing an acquisition function that balances exploration and exploitation over the domain of all possible measurements, improving reconstruction quality while reducing measurement redundancy.
Authors: Nandika Goyal, Glen Uehara, Andreas Spanias
Abstract: Histopathologic cancer detection is challenging due to tissue variability, staining differences, and subtle visual distinctions between disease classes. We propose two quantum algorithms for this task: a configurable dual-gradient CSWAP circuit (DG-CSWAP) that computes multi-directional edge responses in a single execution via per-pixel local Ry encoding, and a hardware-efficient destructive swap circuit (DG-DST) natively matched to quantum processing unit (QPU) gate sets at substantially lower circuit complexity. We prove algebraic equivalence between DG-CSWAP and DG-DST, enabling a two-circuit QPU validation strategy. A three-stage NISQ mitigation pipeline, including readout error correction, bias subtraction, and slope regression, reduces single-pixel hardware MSE by ~8x. Validated on five quantum processors via Amazon Braket, the method achieves inter-platform Pearson r ~ 0.93-0.94 across all local-simulator pairs. Compared to a prior Quantum Fourier Transform (QFT) based amplitude-encoding baseline requiring 12-qubit global state preparation and a three-model ensemble (85.55% on PatchCamelyon), the proposed method uses shot-based measurements, executes on real quantum hardware, and achieves 79.80% accuracy with a single ResNet-50. A Lite configuration delivers a 17x preprocessing speedup at a 2.59% accuracy cost. To the best of our knowledge, this is the first quantum hardware implementation study with noise mitigation for histopathologic image classification.
Authors: Xiaoyang Liu, Shangzhe Wu, Kai Han
Abstract: 3D Gaussian Splatting (3DGS) has achieved state-of-the-art photorealistic rendering, but the representation gap prevents these assets from being physically interactive. Production-grade physics engines do not understand the 3DGS representation, while prior physics-for-3DGS methods are monolithic silos. These prior works are fundamentally limited, demonstrating only object-centric physics in isolated environments, such as on an ideal plane. They are incapable of interacting with complex static collision geometry or heterogeneous assets. We propose a novel framework that, for the first time, bridges this gap by enabling 3DGS assets to participate in scene-level, heterogeneous, multi-solver physical simulations. Our core contribution is a Representation Abstraction Framework that translates all diverse assets, including 3DGS, virtual meshes, and fluids, into a unified physical particle set. This abstraction is key to enabling complex behaviors, such as the non-rigid deformation of 3DGS assets, within a unified physics pipeline. This particle set, along with the static scene collision boundaries derived from scene capture, is processed within a solver-agnostic physics kernel. The physical results are then mapped back to drive each asset's specific visual reconstruction. This architecture unlocks capabilities impossible with prior art. We demonstrate complex, two-way interactions between deformable 3DGS assets, standard CG assets such as fluids and meshes, and large-scale captured static environments, showcasing realistic coupled phenomena that were previously unattainable.
Authors: Chu-Hsuan Lin, Alberto Mario Ceballos-Arroyo, Jisoo Kim, Shrikanth M. Yadav, Huaizu Jiang, Lei Qin, Geoffrey S. Young
Abstract: In this work, we present SemanticVessel, a dataset for fine-grained brain vessel segmentation in computed tomography angiography scans. Based on the detailed contrast provided by dynamic 4D-CTA scans, we generate segmentation traces for arteries and veins. We then use intensity-guided region growing to obtain segmentations of the majority of vascular territories in the human brain, which are refined and annotated with 20 unique arterial classes by an expert radiologist. Unlike existing datasets, where minor arteries are discarded as background content, we merge these minor arteries into a generic arterial class. Due to the multiple-phase acquisition of dynamic 4D-CTA, labels for a single phase can be re-used for other phases in the same series, greatly increasing the size of our dataset with no additional annotation cost. The results show that models trained with the additional generic artery class produce better fine-grained segmentations across the board. We will make our code, annotation GUI, and model weights available to the scientific community. Code, weights, and data will be made available on https://github.com/alceballosa/robust-vessel-segmentation
URLs: https://github.com/alceballosa/robust-vessel-segmentation
Authors: Yashom Dighe, Karthik Dantu
Abstract: Point-cloud goals provide a direct way to specify dexterous in-hand reorientation: instead of defining an object-specific pose frame or estimating 6D pose at test time, the policy is given the desired 3D geometry of the object. Yet raw point-cloud goal conditioning is poorly conditioned for policy learning. Current and goal clouds are unordered, independently sampled, and often visibility-dependent, so their discrepancy entangles object rotation with permutation, resampling, and unstable correspondence structure. For this reason, prior point-cloud manipulation methods typically add structure outside the representation itself, such as explicit pose or relative-pose inputs, dense flow features, or distillation from privileged teachers. We close this gap by learning a rotation-aware point-cloud embedding whose Euclidean latent distance is calibrated to the SO(3) geodesic error between object orientations. The resulting representation turns current-goal comparison into a smooth control signal, allowing a model-free RL policy to act from current and goal point-cloud embeddings, proprioception, and centroid metadata, without object pose, relative pose, dense flow, or teacher-action supervision. In in-hand reorientation experiments, this interface matches privileged-state and distillation-based baselines while avoiding brittle test-time computation of structured pose or flow inputs. These results suggest that point-cloud goals become practical for this task when the representation, rather than an external module, encodes the task-relevant geometry of rotation. We also show evidence that generic visual point-cloud pretraining is insufficient for such a current-goal comparison because it discards the task-relevant state and preserves only shape features.
Authors: Vishal Pandey, Rishav Tewari, Ruzina Haque Laskar
Abstract: Crop recommendation systems in precision agriculture have long suffered from a fundamental modality gap: visual soil characterization and chemical nutrient profiling are typically treated as independent inference problems, with fusion often reduced to late-stage feature concatenation. AgroSense~2.0 addresses this limitation through three architectural advances. First, we introduce continental-scale geospatial integration via a seven-band soil raster (\texttt{india\_soil\_7bands.tif}) spanning India, encoding Nitrogen, pH, SOC, Clay, Sand, Silt, and Bulk Density as $32\times32$ spatial patches, a modality entirely absent from prior work. Second, we replace naive feature concatenation with a cross-modal Transformer fusion module, where tabular nutrient features attend over image representations via multi-head attention, enabling richer inter-modal dependency modeling than shallow fusion. Third, we adopt a multi-task objective jointly optimizing soil classification and crop recommendation through a shared backbone, improving generalization via complementary cross-task signal. To enhance interpretability, we apply TreeSHAP to the tabular branch, revealing crop-conditioned nutrient sensitivity: humidity and rainfall emerge as the most influential features globally, while crop-specific profiles diverge meaningfully rainfall dominates rice, nitrogen and potassium dominate maize, and humidity and nitrogen dominate coffee. These explanations provide transparency into model decisions and surface both agronomically consistent patterns and dataset-specific divergences worth further study. Together, these contributions establish AgroSense~2.0 as a more principled, interpretable, and geospatially grounded framework for precision agriculture.
Authors: Haoran Zhu, Youcheng Cai, Huangsheng Du, Jingyang Meng, Ligang Liu
Abstract: 3D Gaussian Splatting (3DGS) has emerged as a promising method for high-quality, real-time 3D reconstruction. To associate 3DGS with mesh representations, existing methods primarily focus on 3DGS-to-mesh reconstruction from multi-view images. In contrast, the problem of converting a mesh into 3DGS has received comparatively less attention. Instead of relying on heuristic strategies that bind 3D Gaussians to the mesh, we propose a novel white-box 3DGS construction framework, termed Mesh2GS, which generates 3DGS directly from mesh geometry based on plenoptic sampling theory, achieving Nyquist-level performance for high-quality global illumination rendering. Firstly, we propose a plenoptic sampling guided 3DGS construction strategy that theoretically derives the minimum sampling rate of the sampled views and the distribution of 3D Gaussians. Second, we propose a novel 3DGS update procedure with albedo--shading decomposition for efficient global-illumination capture. Finally, we introduce a neural illumination enhancement module to handle non-Lambertian effects. Experimental results demonstrate that our method surpasses state-of-the-art baselines and is practically effective for both real-time shared rendering and non-Lambertian effects capturing specular highlights. The project code will be released upon acceptance.
Authors: Jingjing Jiang, Atsumoto Ohashi, Ryuichiro Higashinaka
Abstract: Full-duplex spoken dialogue models, such as Moshi, enable natural, low-latency voice conversations. However, they remain limited to the audio modality, lacking the facial expressions that are integral to human communication. We present Moshi-Face, the first full-duplex dialogue model that jointly processes the user's audio and facial input while simultaneously generating speech and facial motion. We first construct a vector-quantized variational autoencoder (VQ-VAE) as a face codec that encodes 3D head meshes extracted from facial videos into compact discrete tokens, referred to as face tokens, and conversely reconstructs 3D meshes from these tokens. We then extend Moshi with a Face Transformer module that generates face tokens non-autoregressively, enabling Moshi-Face to produce synchronized audio and face tokens in real time. Experiments show that Moshi-Face achieves audiovisual alignment at low latency while preserving the dialogue quality of the original audio-only model.
Authors: Alexandre Levy, Ernest Valveny Llobet, Antonio Manuel L\'opez
Abstract: Autonomous vehicles (AVs) face driving scenarios ranging from routine traffic to rare events. To assess safety it is crucial to reproduce these scenarios in a controllable, repeatable, and scalable manner, with simulation playing a key role. This paper introduces D-V2S, a novel framework that automatically generates simulatable driving scenarios from driving videos. D-V2S operates in two stages: a Driving Record Analyzer (DRA) uses a vision language model (VLM) with our designed prompt to produce natural-language descriptions from input videos, capturing road layouts and dynamic traffic interactions; subsequently, a Scenario Generator (SG) uses a large language model (LLM) and our conditioning context to translate these descriptions into executable scenarios. Using simulations, we show that D-V2S generates scenarios where 90% of the relevant semantic elements of the videos are present. We also provide qualitative results demonstrating D-V2S's capability to transform real-world driving videos into simulatable scenarios. Moreover, we provide both semantic and human driven ablative analyses of D-V2S's modules. In particular, we show how the VLM choice matters for DRA, and how our SG achieves a 75% preference rate over other state-of-the-art methods.
Authors: Zekun Xu
Abstract: Reinforcement learning with verifiable rewards (RLVR) is increasingly applied to large vision-language models (LVLMs), yet outcome-only optimization can drive a model to stop attending to the video and instead exploit linguistic priors -- a failure we call a visual shortcut. While the existence of such perception bypass is by now documented, how it forms, whether it can be undone, and when intervention still helps remain open. We treat the strength of a grounding penalty, lambda, as a control knob and characterize the formation-reversal dynamics of visual shortcuts along the training time axis. On a held-out, out-of-distribution diagnostic set, we find: (i) a sharp onset -- shortcut reliance emerges abruptly over a narrow window of optimization steps and is robust across random seeds; (ii) a monotone dose-response -- increasing lambda progressively suppresses the shortcut, and at an intermediate dose the trajectory first forms and then reverses the shortcut, exposing a hysteresis-like asymmetry between acquiring and removing it; and (iii) a critical intervention window -- applying the penalty before onset arrests shortcut formation, whereas the same penalty applied after consolidation is markedly less effective. Together these results recast visual-shortcut collapse not as a binary defect but as a controllable, time-dependent, and asymmetric process, with direct implications for when and how strongly to regularize multimodal RLVR.
Authors: Pietro Belligoli, Nikita Makarov, Sayedali Shetab Boushehri, Fabian Schmich, Raul Rodriguez-Esteban, Michael Menden
Abstract: Precision medicine in ophthalmology requires accurate longitudinal predictions, but the fragmented nature of multimodal clinical data remains a barrier to forecasting. We introduce OphthaDT, an LLM-based digital twin for ophthalmology that serializes longitudinal patient histories from 3,220 patients across four Phase III clinical trials into structured narratives to forecast best corrected visual acuity (BCVA). In benchmarks spanning up to 100 weeks, OphthaDT demonstrated the lowest prediction error in neovascular age-related macular degeneration (nAMD), achieving an average mean absolute error (MAE) reduction of 6.0% compared to all baselines. In diabetic macular edema (DME), OphthaDT demonstrated competitive performance against all baselines while outperforming Random Forest and XGBoost by an average MAE reduction of 2.6% and 6.9%, respectively. Results reveal that OphthaDT's predictive advantage scales with trajectory complexity: whereas linear models remain effective for the more stable treatment responses of DME, OphthaDT's capacity is better suited for capturing the high longitudinal variability of nAMD. Finally, OphthaDT handles irregular sampling without imputation, positioning LLM-based clinical trajectory modeling as a methodology that could reduce patient burden and accelerate drug development.
Authors: Himanandhan Reddy Kottur, Nusra Akter Takia, Mahamudul Hassan Fuad, Istiaq Firoz Shiam, Matthew Walsh, Navid Asadizanjani
Abstract: Failure analysis is being reshaped by heterogeneous integration, chiplet-based architectures, hybrid bonding, backside technologies, & increasingly buried package structures. To examine how practitioners view this transition, an anonymous survey was distributed across a broad set of organizations involved in semiconductor design, packaging, systems, tools, & failure analysis. The survey collected approximately one hundred responses & probed organizational background, supported product domains, future priorities in failure analysis, critical bottlenecks, sample preparation challenges, emerging architecture specific pain points, & perceived needs for workflow acceleration & data standardization. The results show that heterogeneous integration, chiplet, and three-dimensional products dominate the respondent base at 69%, while package & heterogeneous integration failure analysis received the highest importance rating at 7.92 out of 10. Hybrid bonding emerged as the most difficult new architecture to analyze at 54%, higher-resolution non-destructive imaging ranked as the most important future accelerator at 8.18 out of 10, and 83% of respondents supported formalized data standardization frameworks. The complete survey data are provided in Appendix A (Table II) to improve transparency & support future benchmarking.
Authors: Yongheng Sun, Minhui Yu, Mengqi Wu, Maureen Kohi, Mingxia Liu
Abstract: While longitudinal brain PET imaging is the gold standard for quantifying the spatiotemporal accumulation of Beta-amyloid, its widespread clinical utility is constrained by high operational costs and cumulative radiation risks. Recent deep generative models show promise in longitudinal image synthesis; however, they often fail to capture subtle pathological progression due to identity drift and a persistent bias toward trivially replicating baseline signal intensities rather than modeling temporal transition. To this end, we propose Delta-Diffusion, a novel progression-aware framework that redefines longitudinal PET synthesis as a conditional Poisson Diffusion Bridge (PDB) process. Unlike standard diffusion models that start from Gaussian noise, our PDB formulation is mathematically anchored to the subject's baseline PET, effectively transforming the generative task into a conditional distribution transition of the amyloid trajectory. To handle heteroscedastic nature of PET imaging, we introduce a physically-grounded Poisson perturbation within a Diffusion Transformer (DiT). This architecture uses adaptive scale-shift modulation to precisely calibrate the synthesis with the elapsed clinical interval and structural MRI context. A volume-of-interest balanced objective is designed to emphasize sparse, high-risk regions of amyloid accumulation. Validated on two cohorts with 542 subjects, Delta-Diffusion demonstrates superior performance in capturing longitudinal variations in amyloid deposition compared to state-of-the-art methods, offering a robust computational framework for tracking disease progression.
Authors: Manar Alsaid, Mandip Shrestha, Mohammad Abbas
Abstract: Lesion segmentation in breast ultrasound involves two related challenges. In images with lesions, speckle noise, low tissue contrast, and posterior acoustic shadowing cause boundary leakage and incomplete contour delineation. In images without lesions, those same artifacts generate false-positive activations in regions resembling solid lesion tissue. This study addresses both failure modes through a single modification to the training objective. Rather than weighting every boundary pixel equally, the proposed loss scales contour penalties by per-pixel predictive entropy and the ground-truth boundary map, concentrating gradient emphasis on lesion margin locations where the network remains uncertain. The loss was evaluated on the BUSI dataset through a controlled ablation against two baselines: a model without boundary supervision and a model with uniformly weighted boundary binary cross-entropy. Across 97 lesion-containing test images, mean Dice scores were statistically indistinguishable between the proposed method and the no-boundary baseline (0.7624 versus 0.7616, paired Wilcoxon p = 0.27), confirming that lesion segmentation quality is preserved. The primary effect appears in specificity. False-positive activations on 20 no-lesion test images fell from 14 of 20 and 19 of 20 for the two baselines to 5 of 20 with the proposed approach (McNemar p = 0.012 and 0.0005). Non-overlapping Wilson 95% confidence intervals confirm the difference is both statistically significant and practically substantial. A post-hoc spatial temperature scaling step further reduced expected calibration error from 0.0201 to 0.0095 without altering segmentation masks. Entropy-guided boundary supervision and spatial calibration thus function as complementary training-level and inference-level refinements that improve specificity and probability reliability within a U-Net framework.
Authors: Soyeon Kim, Kyowoon Lee, Jaesik Choi
Abstract: Path-based attribution methods such as Integrated Gradients (IG) are widely adopted for their strong axiomatic properties and effectiveness in attributing model predictions to input features by integrating gradients along a path from a baseline to the input. However, the choice of the attribution path largely affects the quality of explanations, and existing approaches rely on fixed or hand-crafted paths that often produce noisy or distorted attributions. To address this limitation, we propose Diffusion Integrated Gradients (DiffIG), a novel method that reformulates path generation as a conditional generative modeling problem. DiffIG first trains a diffusion model to learn a distribution over paths generated from a Stick-Breaking Process, then employs guided sampling to embed user guidance during the sampling procedure. We demonstrate that DiffIG quantitatively matches or outperforms existing path-based methods, achieving perceptually aligned explanations. This work introduces a new generative perspective for flexible, inference-time controllable Explainable Artificial Intelligence (XAI) methods.
Authors: Fangzhuo Zhang, Xinyu Wang, Xiao Yang, Jinchang Zhang
Abstract: Robotic ultrasound scanning in real clinical environments requires both high-level clinical workflow reasoning and low-level closed-loop execution. Physicians natural-language instructions often contain implicit anatomical targets, procedural logic, image-quality requirements, and safety constraints, while execution is affected by patient motion, contact variations, and target drift. We propose a fast and slow hierarchical embodied ultrasound system for safe and interpretable robotic ultrasound assistance. The Slow Brain performs intent parsing and stage-wise task planning with knowledge augmentation from an API and handbook corpus, and generates executable plans through task-graph construction and structured plan verification. The Fast Brain fuses multimodal feedback, including ultrasound images, robot pose and force states, and patient-motion information, to refine local actions and perform image-quality-guided recovery behaviors. The system further integrates a Safety Shield and a hierarchical escalation policy to constrain risky actions and trigger replanning or human confirmation under persistent failures or safety-bound violations. Experiments on planning evaluation, closed-loop execution under dynamic perturbations, and safety-mechanism validation demonstrate that the proposed hierarchical design improves task success rates while reducing safety violations.
Authors: Adam Koziak, Yuhong Guo
Abstract: Test-time adaptation (TTA) can mitigate domain shift without source data, but it is highly brittle under adversarially contaminated test streams, where corrupted inputs also destabilize online updates. We study robust test-time adaptation (RTTA) in the adversarial-stream setting, which remains comparatively underexplored relative to standard TTA, and propose SAFER (Stochastic Augmentation Framework for Enhanced Robustness), a training-free reliability-guided augmentation wrapper for RTTA. SAFER preserves the wrapped TTA objective while replacing brittle single-view predictions with a reliability-guided pooled predictor. For each test sample, SAFER generates stochastic augmentations and aggregates their predictions through correlation-weighted pooling with outlier detection. We further study an adaptive-mixing extension that improves clean-performance retention by adjusting original-versus-augmentation weighting using feature disagreement signals. We evaluate on PACS, VLCS, and OfficeHome under PGD attacks at various attack rates. Across benchmarks, SAFER improves resilience of TTA methods to adversarial attacks while maintaining competitive clean performance.
Authors: Narges Ghasemi, Amir Ziashahabi, Salman Avestimehr, Jonathan May
Abstract: Language models are widely used in assistant settings, where controlling behavioral attributes is often essential. Activation steering modifies hidden-state representations at inference time, providing a lightweight, training-free mechanism that can be toggled at runtime. Existing methods, however, have focused primarily on steering a single attribute at a time. When multiple attributes must be controlled simultaneously, naive summation of per-attribute steering vectors suffers from norm imbalance and directional cancellation, while classifier-based approaches require retraining whenever the attribute set changes. We introduce ORBIT (Orthogonal Rotation-Based Intervention Technique), a training-free extension of rotation-based steering to the multi-attribute setting. Our method constructs a joint subspace from per-attribute steering planes via singular value decomposition and applies a single norm-preserving rotation within that subspace toward a combined target direction. Adaptive per-token gating identifies which attributes need correction at each position, and an optional additive boost strengthens attributes with weak initial projection. We also introduce TraitFactory, a new multi-attribute benchmark that focuses on behavioral tendencies rather than surface-level style. We evaluate ORBIT on TraitFactory and ToneBank across three models (Llama-3.2-3B, Qwen-2.5-7B, Llama-3.1-8B) while steering multiple attributes simultaneously, showing that it achieves stronger and more balanced multi-attribute steering than existing training-free baselines while better preserving output coherence.
Authors: Yixin Gao, Xiaohan Pan, Lin Liu, Xin Li, Zhibo Chen, Qi Tian
Abstract: Recent generative video compression methods leverage powerful generative priors to achieve perceptually pleasing reconstructions. However, most existing approaches require additional training to adapt generative models to produce realistic reconstructions from compact representations. In this paper, we propose ZeroGVC, a zero-shot generative video compression framework that leverages pretrained autoregressive diffusion priors for low-delay video reconstruction. ZeroGVC encodes the first frame of each group of pictures (GOP) with an image codec and represents subsequent P-frames through Codebook-Guided Autoregressive Latent Compression. This design is motivated by our observation that the compression scheme of denoising diffusion codebook models is effective in few-step consistency sampling. By selecting compact combinations of reproducible codebook noise vectors, ZeroGVC steers the latent denoising trajectory toward the target P-frame while allowing the decoder to reproduce the same trajectory in only a few denoising steps. In addition, we design an optional bidirectional reference mode that mitigates error propagation by leveraging the next I-frame context without introducing any additional bitrate overhead. Extensive experiments on standard video compression benchmarks demonstrate that ZeroGVC achieves superior perceptual reconstruction quality at ultra-low bitrates without any additional training.
Authors: Prabhu Pugalenthi, Pramod Krishnaa Dhanbalan
Abstract: Road traffic accidents remain a critical global crisis, consistently serving as a primary driver of preventable mortality and severe injury. These incidents are frequently precipitated by human error, including overspeeding, driving under the influence of alcohol, and cognitive fatigue. To address this urgent public safety challenge, this paper presents an intelligent, Internet of Things (IoT)-based Accident Prevention and Detection System (APDS) designed to systematically mitigate driver risk and optimize post-collision emergency responses. The proposed framework features a multi-tiered architecture capable of executing continuous real-time telemetry monitoring, proactive local alarm triggering, and automated situational intervention. Furthermore, the system integrates automated emergency communication protocols that aggregate immediate spatial coordinates via GPS and dispatch targeted alerts to medical facilities in close proximity, thereby optimizing response times and reducing accident-related fatalities.
Authors: Yosuke Yamagishi, Atsushi Takamatsu, Mototsugu Sato, Tomohiro Kikuchi, Shouhei Hanaoka, Takeharu Yoshikawa, Osamu Abe
Abstract: Purpose: To evaluate whether large language model (LLM)-assisted label cleaning can identify label-report discordance in CT-RATE, a large-scale public chest CT dataset. Materials and Methods: After report-level deduplication, 24,446 unique radiology reports were identified. Twelve reports were excluded from the primary GPT-5.4 analysis because of Microsoft Azure AI Foundry content-safety filtering, leaving 24,434 reports and 439,812 label instances across 18 abnormality categories. GPT-5.4-derived binary labels were generated from report text using structured JSON output and compared with existing CT-RATE labels. Discordant instances were adjudicated by radiologists. In addition, 100 randomly sampled reports were manually annotated to compare CT-RATE labels, individual LLM-derived labels, and multi-LLM majority-vote labels against radiologist-annotated reference labels. Results: Overall agreement between GPT-5.4-derived and CT-RATE labels was 96.4%, with Cohen's kappa of 0.884. Lymphadenopathy showed the lowest agreement and kappa. In discordance review, radiologist adjudication supported GPT-5.4-derived labels in 72 of 97 (74.2%) general discordant instances and 91 of 99 (91.9%) targeted lymphadenopathy discordant instances. Against radiologist-annotated reference labels, multi-LLM majority-vote labels achieved the highest label-macro-averaged F1 score and Cohen's kappa. Conclusion: LLM-assisted label cleaning identified clinically meaningful label-report discordance in CT-RATE and may support scalable quality improvement of public imaging datasets. The cleaned dataset will be made publicly available to support future research.
Authors: Nicol\'as Violante, George Kopanas, Linus Franke, Julien Philip, George Drettakis
Abstract: 3D Gaussian Splatting (3DGS) is widely used to capture and render real scenes. Compositing objects from one capture into another has applications in many domains, such as VFX, architecture and interior design, or marketing. However, extracting an object from a source scene and naively pasting it into a target scene will fail to produce realistic results due to the different lighting conditions between the two scenes. To address this problem, we introduce a diffusion model that harmonizes naively composited images with inconsistent lighting. The model is trained with a heterogeneous dataset of image pairs (inconsistent composite input, consistent output), combining synthetic, generated, and real data. Our complete 3D solution allows a user to extract an object from the source scene and composite it into the target scene. From this, the (inconsistent) views of the target scene with the composite object are rendered. Our diffusion model harmonizes each one of these views, which are finally consolidated in a 3DGS representation with a post-optimization step. Our method provides visually compelling results, making object transfer between 3DGS easy to use and significantly improving quality compared to previous methods.
Authors: Yuhang Jiang, Xiaojing Chen
Abstract: Input Diversity (DI), which applies random resizing and padding at each attack iteration, is a near-default ingredient of transfer-based adversarial attacks, widely assumed to improve transferability. We show this assumption is regime-dependent and, for robustly trained surrogates, often reversed. Varying only the surrogate, increasing the DI probability raises transfer success for standard surrogates but lowers it for robust ones: the two response curves separate like a pair of scissors, a pattern we call the Scissors Effect. The effect is strong and consistent on ImageNet, where blind DI costs the robust source 10.3% attack success on average across CNN, ViT, Swin, and ConvNeXt targets and across ten attacks spanning 2018-2024; it is smaller on CIFAR-10 unless DI is made aggressive. A controlled robustness-strength sweep that varies only the training budget shows the harm is graded rather than binary, crossing from beneficial to harmful already in the little-robustness regime. We trace it to gradient geometry: a resize/translation decomposition attributes roughly 67% of the harm to resize, and a direct source-target gradient-alignment measurement confirms the same resize operation improves alignment for standard surrogates but degrades it for robust ones. We summarize the regime with Local Gradient Consistency (LGC), a single input-space probe that separates the two surrogate types, and prove a bias-variance crossover theorem isolating where DI helps from where its resize bias dominates. A training-free rule (CG-DI) that disables diversity when LGC is high avoids the loss on robust surrogates while keeping DI's benefit on standard ones, positioning the Scissors Effect as a DI-specific manifestation of the broader robustness-transferability trade-off.
Authors: Milton Mondal, Sushovan Chanda, Mohamad Mahdi Alawieh, Brijesh Sukhadiya, Donatus Krah, Clinton Gonsalves, Antonios Ntolkeras, Silvio O. Rizzoli, Ali H. Shaib
Abstract: Hybrid Quantum Neural Network (QNN) classifiers produce logits as expectation values of quantum measurement operators. For standard Pauli measurements, these outputs are intrinsically bounded to the interval [-1,1]. When such bounded logits are used directly with the cross-entropy loss applied to softmax-normalized logits for multi-class classification, the loss function operates in a regime of weak sensitivity to logit differences. As a consequence, parameter gradients are suppressed, leading to unstable optimization in variational quantum classifiers (VQCs). In this work, we identify this effect as measurement-induced logit contraction, a previously uncharacterized source of trainability degradation in hybrid QNNs. To address this limitation, we introduce a learnable scaling parameter, termed Quantum Measurement Temperature (QMT), which rescales quantum measurement outputs prior to the loss. Unlike post-hoc calibration, QMT acts during training and compensates for the physically imposed bounds on quantum measurement outputs. This rescaling increases gradient magnitude and variance, thereby improving loss sensitivity. The proposed mechanism is architecture-agnostic and does not modify the quantum ansatz, circuit depth, or measurement operators. Experiments on fluorescence microscopy images and a six-class variant of Fashion MNIST demonstrate that QMT consistently enhances logit separation, strengthens gradients, stabilizes training across random initializations, and improves classification accuracy, relative to unscaled measurement readouts. These results demonstrate that QMT enables stable and reliable training of hybrid QNNs for practical applications.
Authors: Zhuoran Jin, Kejian Zhu, Hongbang Yuan, Yupu Hao, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao
Abstract: Chain-of-Thought (CoT) has become a standard method for improving reasoning capabilities in large language models (LLMs) by eliciting step-by-step thinking, but its effectiveness in multimodal tasks remains unclear. In this paper, we aim to systematically investigate the key question: What can multimodal Chain-of-Thought reasoning do, and where and why does it fall short? To this end, we evaluate 12 multimodal tasks across perception and reasoning categories using both 14 non-reasoning models and 8 reasoning models. Our analysis reveals several important findings: (1) CoT is not a free lunch and should be used selectively depending on the specific requirements of each task. For perception tasks, CoT can lead to undesirable side effects, such as reduced performance in visual grounding and object counting. In contrast, it proves effective for reasoning tasks involving mathematical, scientific, and multi-image reasoning; (2) Compared to original models, existing open-source multimodal reasoning models often yield only marginal overall improvements, possibly due to an overemphasis on mathematical reasoning at the expense of broader capabilities; (3) Visual reasoning remains a key bottleneck for current multimodal CoT, as models exhibit a Look Light, Think Heavy pattern where verbal reflection rises and falls during reasoning, whereas visual reflection consistently diminishes. These findings suggest that while multimodal CoT handles verbal reflection relatively well, it lacks the ability to maintain deep visual introspection throughout the reasoning process.
Authors: Osama Wehbi, Sarhad Arisdakessian, Omar Abdel Wahab, Azzam Mourad, Hadi Otrok
Abstract: Federated Learning (FL) enables collaborative model training without sharing raw data, making it a promising paradigm for privacy-sensitive applications. However, its decentralized nature makes it inherently vulnerable to backdoor attacks, where malicious clients embed hidden triggers into local training data to manipulate model predictions. Existing defenses mainly operate during before and during aggregation cannot fully eliminate backdoor behaviors that persist in the converged global model. Moreover, the effectiveness of post-training sanitization is often limited by the server's lack of knowledge of trigger patterns or poisoned clients after convergence, resulting in residual backdoor behaviors or accuracy degradation due to neuron entanglement. To address this limitation, we propose SCRUB-FL (Sanitizing and Cleansing Representations via Unlearning of Backdoors), a two-phase solution for post-training backdoor removal in FL. During training, clients identify suspicious samples using spectral analysis and activation clustering, then train lightweight Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP) models to capture trigger-related distributions. The generator parameters are aggregated server-side to construct a global representation of suspicious patterns without exposing raw data. After convergence, the server synthesizes trigger-approximating samples and applies machine unlearning to erase the trigger-target association by redistributing predictions toward a uniform distribution. Experimental evaluations on CIFAR-10 and GTSRB across three attack types and up to 40% malicious participation demonstrate that SCRUB-FL reduces the backdoor attack success rate to as low as 3.88% while maintaining over 91% normal task accuracy, outperforming state-of-the-art defenses without requiring prior trigger knowledge or a large clean proxy dataset at the server.
Authors: Sandilya Sai Garimella, Daniel Chase Butterfield, Sean Wilson, Lu Gan
Abstract: We present HERCULES, an open-source simulator and data-collection pipeline for heterogeneous multi-robot autonomy. Built upon the Unreal Engine 5 (UE5)-based simulators AirSim and Cosys-AirSim, HERCULES resolves key architectural limitations of prior frameworks to enable concurrent unmanned aerial and ground vehicle (UAV-UGV) operation in large-scale, photorealistic, dynamic environments. It introduces a new waypoint-tracking UGV controller that mirrors existing UAV control interfaces, and provides a shared navigation stack for mapping, traversability analysis, planning, and control across heterogeneous platforms. Expanding inherited sensor suites, it adds physics-based long-wave infrared (LWIR) cameras and configurable night-vision modes for degraded visual environments. HERCULES provides lightweight APIs, ROS 2 wrappers, and rigorous time synchronization across sensors and platforms, and brings state-of-the-art game-engine capabilities into robotics simulation, integrating intelligent agents such as pedestrians, traffic, and wildlife with high-fidelity dynamic phenomena, including fire, flooding, and crop disease spread. HERCULES runs in two modes: passively, replaying offline-designed trajectories to generate reproducible multi-modal datasets, and actively, running an online planner in closed loop from live observations. Our experiments in heterogeneous multi-robot SLAM, collaborative perception, and exploration, using both HERCULES-generated data and active closed-loop execution, demonstrate its utility for advancing heterogeneous multi-robot autonomy. We publicly release our source code, experiment code, documentation, and datasets, including a heterogeneous multi-robot SLAM benchmark collected with two UAVs and two UGVs across kilometer-scale desert, forest, and city environments, at https://lunarlab-gatech.github.io/HERCULES-website.
Authors: Xingwei Zhong, Varun Sharma, Kar Wai Fok, Vrizlynn L. L. Thing
Abstract: Vision language models (VLMs) employ both visual and textual modalities to enable advanced vision-language inference. However, incorporating visual modalities expands the attack surface of VLMs, making them more susceptible to security threats such as adversarial perturbations and indirect prompt injection, wherein crafted malicious image prompts can elicit unintended model outputs. Existing defense methods against malicious image prompts remain insufficient as they typically demand extensive datasets for retraining or the deployment of additional, complex classifiers. Most critically, there is a profound lack of specialized defense mechanisms specifically targeting indirect prompt injections, a gap that serves as a primary motivation for this work. To address these limitations, we introduce DE-FIVE, a novel training-free framework for detecting malicious image prompts by leveraging Fourier features and the hidden state representations of the visual encoder (image vector embeddings) across perturbations. Specifically, we develop a hybrid detection strategy consisting of a black-box detector that operates on Fourier-domain features and a white-box detector that exploits image vector embeddings derived from only a few-shot malicious set. Extensive experiments demonstrate that the proposed framework consistently outperforms state-of-the-art baselines against malicious image prompts.
Authors: Haibiao Li, Di Lin, Xue Jiang, Weiwei Wu, Yanxi Li, Yugang Chi
Abstract: The clinical diagnosis of skin diseases is susceptible to interference from inter-class similarity of skin lesions, and over-reliance on clinicians'experience easily leads to subjective bias. Although existing deep learning aided diagnosis methods achieve competitive accuracy, they suffer from the black-box opacity of Vision Transformer (ViT) and poor adaptability to medical few-shot scenarios. Moreover, mainstream explainable algorithms generally face the bottleneck of significant accuracy degradation when improving interpretability. This paper proposes an interpretable ViT (IViT) constrained by Quadratic Programming (QP). The introduced pre-trained transfer learning adapts to few-shot feature extraction. A discrete QP feature selection framework is constructed to screen generic and discriminative features consistent with clinical diagnostic logic. A multi-objective loss function is designed to reduce feature redundancy and optimize activation distribution while preserving classification performance. Experimental results on six standard skin disease datasets show that IViT achieves an accuracy of 93.80%, only 0.21% lower than the baseline, with feature redundancy reduced by 29.5%. Its core activation regions are consistent with clinically concerned lesion areas. The proposed model balances accuracy and interpretability, providing a reliable solution for the clinical deployment of few-shot intelligent skin disease diagnosis.
Authors: Licheng Yang, Lingfeng Qian, Fei Zheng, Yonghao He, Wei Sui, Shuangshuang Li, Hu Su
Abstract: Imitation learning for robotic manipulation relies on large sets of human demonstration trajectories, which are often noisy and temporally irregular due to variable operator speed, intermittent pauses, and inconsistent action density. A common preprocessing strategy is time-uniform downsampling to shorten sequences, but it cannot effectively remove speed-induced non-uniformity or redundant pauses. This mismatch degrades data quality and hinders policy learning. To address this issue, we propose Information-Standardized Trajectory Resampling (ISR), an offline preprocessing method for effective imitation learning. ISR resamples each trajectory by enforcing approximately equal information distance between adjacent points. Specifically, we map trajectories onto an information-modulated Riemannian manifold and perform geodesic-equidistant parameterization. We construct an information-intensity field from velocity and acceleration norms: the velocity term removes small-motion redundancy, while the acceleration term preserves high-curvature and fine-manipulation phases. We evaluate ISR on three real-world manipulation tasks with mainstream imitation learning policies. Compared with the baseline time-uniform 3x downsampling, ISR improves task success rates by about 25%, remains robust across datasets collected from different operators, and reduces both dataset size and training cost. The code and videos are publicly available at https://d-robotics-ai-lab.github.io/isr.page.
Authors: Junrong Huang, Zhiyuan Zhang, Rui Tang, Hongbo Fu, Jnig Liao
Abstract: Realistic integration of user-specified textures into scene images is a fundamental task in computer graphics and image editing. While existing material transfer and reference-guided inpainting methods can edit surface appearances, they often fail to address the specific requirements of texture tiling. This task necessitates precisely repeating a reference pattern according to user-defined parameters such as frequency, orientation, and scale. Furthermore, current generative approaches often struggle to maintain the structural fidelity of the reference texture, limited by either destructive pixel-level resampling or the lack of fine-grained spatial information in semantic image encoders, and they frequently fail to preserve the coherent lighting and geometry of the original scene. In this paper, we propose a novel framework for controllable and high-fidelity texture tiling based on Diffusion Transformers. Our approach introduces two key technical innovations to decouple spatial manipulation from content generation. First, we propose a Coordinate-Transformed Rotary Embedding mechanism. By applying 2D affine transformations directly to the relative positional embeddings between the target latent and the image condition, we achieve precise control over tiling patterns without explicit pixel warping, thereby utilizing the full information of the reference condition without degradation. Second, a Disjoint Attention Mask is employed to shield reference features from semantic leakage. This preserves structural integrity while seamlessly blending the synthesized texture with the scene's original lighting and geometry. Extensive experiments demonstrate that our method outperforms state-of-the-art baselines in both control accuracy and texture fidelity.
Authors: Yincheng Zhou, Athena Zhuoming Zhong, Shijie Zhang, Kevin Zhang, Teresa Xiaotao Shang, Shanghang Zhang
Abstract: As multimodal agents move from interface understanding to real software control, successful trajectory discovery in live desktop environments becomes a key challenge. GUI tasks require long-horizon sequences of precise mouse and keyboard actions, while feedback is sparse, delayed, and costly to obtain through VM rollouts. We propose Environment-Native Verified Search (ENVS), a training-time search-and-filter pipeline that uses the environment to construct verified supervision before policy optimization: it branches over behaviorally distinct GUI actions in live OSWorld VMs, verifies successful leaves, and trains from globally balanced step-level supervision. To evaluate robustness under realistic desktop interruptions, we also introduce OSWorld-Noisy, a dynamic benchmark for recoverable desktop interruptions that preserves the original tasks while testing whether agents can refocus, dismiss, wait, or recover under live perturbations. On the 300-task OSWorld pool, ENVS reaches 30.3 pass@8 on original evaluations and 29.0 on OSWorld-Noisy, outperforming matched ARPO-style online RL while reducing compute from 184-192 to 138-153 GPU-hours; even with only 30% of its search data, ENVS reaches 27.0 pass@8, exceeding ARPO from the base model. Training from noisy environments also better preserves visual-reasoning abilities on auxiliary benchmarks, including OSWorld-G Refusal (16.7 vs. 1.9) and BLINK Functional Correspondence (26.2 vs. 23.1).
Authors: Ruolan Sun, Pawel Polak
Abstract: Inference-time alignment of pretrained text-to-image models is typically performed along a single control axis, such as classifier-free guidance, attention editing, or reward-based latent perturbations. This limitation prevents modeling joint dependencies between conditioning and latent variables and hinders transfer across generative transports. We propose PG-MAP, a training-free framework that formulates inference-time alignment as a trajectory-level Gibbs-MAP / proximal energy optimization over the conditioning $c$ and latent state $z_t$ via a forward-consistency coupling, optionally guided by a frozen preference reward. This joint formulation enables coordinated updates across modalities while remaining compatible with both diffusion and flow-matching models through transport-specific adaptations. Across diffusion backbones (SD~1.5, SDXL), PG-MAP consistently improves alignment metrics such as PickScore and Aesthetic, and can be effectively combined with tuned classifier-free guidance to achieve the strongest overall performance. On flow-matching models (SD3.5-medium), the framework reduces to a latent-only variant, achieving $\mathbf{91.9\%}$ PickScore and $75.7\%$ HPS win rates against a static baseline, with controlled experiments ruling out noise-related artifacts. Human evaluations further confirm consistent preference over strong baselines, including tuned CFG and compute-matched universal guidance. Finally, an oracle-routing analysis shows that the relative importance of conditioning and latent optimization depends on prompt types, surfacing further headroom that a per-prompt selector could exploit.
Authors: Guilhem Faur\'e (MULTISPEECH), Mostafa Sadeghi (MULTISPEECH), Sam Bigeard (MULTISPEECH), Slim Ouni (LORIA)
Abstract: Latent diffusion approaches to sign language production (SLP) rely on an initial stage that learns an encoding of sign pose sequences, enabling generative modeling in the resulting latent space. The autoencoder used in this stage is typically evaluated in terms of reconstruction quality using geometric metrics common in SLP. While informative, these metrics do not fully capture latent space properties that may influence the training and performance of the downstream generative model. In this work, we investigate how architectural and training objective design choices in a variational autoencoder (VAE) for sign pose encoding affect latent space structure, and how these differences translate into the performance of a latent diffusion model for text-to-sign generation. Our experiments on Phoenix14T dataset show that variations in generative performance, measured through back-translation BLEU scores, can sometimes be better explained by differences in latent space properties than by VAE reconstruction accuracy alone.
Authors: Xianda Guo, Bohao Zhang, Chenwei Huang, Shiyuan Chen, Ruilin Wang, Yiqun Duan, Cong Yang, Qin Zou, Wei Sui
Abstract: Occupancy prediction at voxel-level granularity is essential for safe robotic navigation and interaction in complex environments. Existing occupancy datasets, however, are predominantly designed for autonomous driving with vehicle-centric biases -- forward-facing cameras, far-field geometry, and static road priors -- limiting their applicability to embodied humanoid perception. We present Humanoid-OmniOcc, a large-scale panoramic stereo-based occupancy dataset tailored for humanoid robots. The dataset encompasses 15 diverse simulated indoor scenes and 5 real-world environments, yielding over 155K samples with broad scene and style diversity. Importantly, the dataset is designed around a Real2Sim2Real closed-loop paradigm: real sensor specifications drive physically accurate simulation, simulation produces large-scale annotated training data, and models trained in simulation are directly evaluated on real-world captures -- enabling iterative refinement of the sim-to-real pipeline. We further propose \textbf{H}umanoid \textbf{S}urround \textbf{S}tereo-guided \textbf{Occ}upancy model (Humanoid-OmniOcc) that exploits robust depth priors for accurate 2D-to-3D lifting. Extensive experiments show that Humanoid-OmniOcc consistently outperforms monocular baselines and generalizes well to both unseen simulated test scenes and real-world environments, validating the effectiveness of the Real2Sim2Real design. Code and data will be available upon acceptance at https://d-robotics-ai-lab.github.io/humanoid-omniocc.
Authors: Giulia Martinelli, Niccol\`o Bisagno, Nicola Garau, Esa Rahtu, Nicola Conci
Abstract: We introduce VolHuMe, a dataset of high-quality 4D human scans captured with a state-of-the-art volumetric studio using 64 RGB and 32 depth cameras. VolHuMe contains individual captures of 104 subjects and provides extensive ground truth, including SMPL-X, high-resolution meshes, multi-view RGB/depth images, rigged meshes, point clouds, garment segmentation, and detailed hand and facial geometry. Unlike prior datasets that primarily rely on full-body imagery, VolHuMe uses a close-range, high-resolution capture setup that preserves fine-grained body-part details, improving geometric fidelity and texture resolution. We benchmark VolHuMe on state-of-the-art methods across 3D and 4D human reconstruction tasks, showcasing the dataset's quality and exposing the limitations of current evaluation testbeds.
Authors: Jaehyun Cho, YoungJoon Yoo
Abstract: Neighboring-slice self-supervised denoising is attractive for volumetric medical imaging, yet inter-slice misalignment breaks anatomical correspondence and often yields ghosting and blurred margins when adjacent slices are used naively as targets. We propose Neighbor-Guided Patch Sampling (NGPS), a lightweight framework that constructs neighboring supervision under local inter-slice misalignment without explicit registration. To avoid learning from misleading targets, prior methods commonly mask discrepant regions, but this stabilizes training at the cost of leaving a non-trivial portion of neighboring evidence unexploited, particularly around high-frequency anatomical boundaries. NGPS addresses this by decoupling structure matching from signal retrieval: for each masked location, it searches a local neighborhood for structurally similar candidate patches using a simple guide image (e.g., fast bilateral filtering), while retrieving the supervision signal directly from the raw noisy neighbor at the matched coordinates. By matching on a noise-attenuated guide while retrieving raw values from neighboring slices, NGPS constructs local pseudo targets without a learned registration module. Across the evaluated CT and synthetic-Rician MRI settings, NGPS improves fidelity and structure-sensitive metrics. Code is available at https://github.com/cv-cho/NGPS .
Authors: Vu Tuan Truong, Long Bao Le
Abstract: Diffusion models (DMs), despite their impressive capabilities across a wide range of generative tasks, have been shown to be vulnerable to backdoor attacks. However, existing backdoor methods face critical trade-offs among key factors: attack performance, stealthiness, time complexity, and required poison rates. For example, achieving high attack performance typically demands a high poison rate and prolonged training, which undermines stealthiness, making the attack more detectable by backdoor defenses. This paper proposes TooBad (trigger optimization for backdoor diffusion models), a backdoor framework which introduces a novel DM-tailored trigger optimization technique to dramatically enhance the performance of backdoor attacks on DMs. Experiments on representative benchmarks such as CIFAR-10 show that TooBad can achieve high ASRs ($> 85$%) at only 0.5% poison rate, significantly lower than the 10% typically required by prior work on the same datasets. At 5% poison rate, TooBad reaches nearly 100% ASR within just 3-5 backdoor injection epochs, whereas existing methods need at least 30-50 epochs at double the poison rate for comparable results. Despite its potency, TooBad easily evades SOTA defenses and maintains high utility. These results reveal a critical threat on DMs and highlight the need for more robust defenses against such stealthy yet efficient attacks.
Authors: Qi Sun, Kiyohiro Nakayama, Jing Nathan Yan, Qixing Huang, Alexander Rush, Leonidas Guibas, Gordon Wetzstein, Jing Liao, Guandao Yang
Abstract: Meshes are among the most common 3D scene representations, but directly generating meshes is challenging because the representation contains important symmetries, including permutation invariance of faces and vertices. MeshFlow learns to generate triangle meshes directly as triangle soups, avoiding the need to serialize meshes into long autoregressive sequences. We adopt equivariant optimal-transport flow matching models that respect the key symmetries of triangle soups: arbitrary permutations of faces and permutations of the vertices within each face. Toward this goal, we propose a simple yet effective modification to the Diffusion Transformer architecture, resulting in a scalable network capable of modeling a velocity field while maintaining the desired equivariance. We further introduce an optimal-transport-based training objective that improves convergence by eliminating supervision signals that violate these symmetries. MeshFlow achieves mesh quality comparable to state-of-the-art autoregressive mesh generators while providing about an 18$\times$ speedup during inference. Project page is at https://qiisun.github.io/MeshFlow/.
Authors: Haoling Li, Kai Zheng, Jie Wu, Can Xu, Qingfeng Sun, Han Hu, Yujiu Yang
Abstract: Scaling reinforcement learning for visual mathematical reasoning requires more than generating harder questions: as data volume grows, the reward labels themselves must remain reliable. Yet existing data pipelines scale supervision while trusting the labeller, and policy-side methods assume the underlying answers are already correct. We instead treat scaling as a verifiable data-construction problem and decouple two axes before any policy update: prompt difficulty, expanded by route-specific evolution operators, and answer reliability, enforced by offline hypothesis-test falsification. We instantiate this as VeriEvol, an iterative framework with two extensible components: a type-aware evolution module that rewrites low-difficulty image-question seeds into harder, image-grounded prompts; and HTV-Agent, a verifier that accepts an answer only after multi-source counter-evidence has failed to refute it. The resulting verified data scales in volume, extends by adding evolution routes or verifier channels, and plugs directly into existing GRPO-style RL recipes. On a five-benchmark visual-math suite, scaling evolved SFT data from 10K to 250K samples raises the mean accuracy from 35.42 to 54.73; then, with backbone, SFT initialization, and GRPO recipe held fixed, VeriEvol adds a cumulative +3.88 over an un-evolved RL baseline, of which +1.82 comes from evolved prompts and +2.06 from the HTV-Agent verifier. We release the prompts, data, models, code, and the full verifier trace of every sample, so that downstream work can scale and audit the pipeline rather than only inspect its outputs.
Authors: Xiaolin Zhou, Liu Liu, Tingyang Xiao, Wei Feng, Fa Fu, Xinrui Meng, Xinjie Wang, Jialiang Han, Boyang Yu, Yun Du, Wei Sui, Zhizhong Su
Abstract: LLM agents follow a practical execution loop in digital environments: they reason over structured states, invoke tools, inspect feedback, and revise actions. Extending this loop to physical robots is difficult because physical execution is continuous, embodiment-dependent, uncertain, and constrained by safety. Existing embodied-AI systems have advanced manipulation, spatial understanding, navigation, and humanoid control, but these capabilities often remain specialized modules or loosely coupled decision loops. In this work, we introduce HoloAgent-0, a unified embodied agent framework for real-world robot deployment. Embodied AgentOS converts language instructions into executable skill graphs, schedules robot resources, monitors execution, and triggers clarification or re-planning from runtime feedback. HoloAgent-0 organizes heterogeneous robot models and controllers through three coupled layers: Embodied AgentOS for closed-loop execution, 3D spatial memory for physical world grounding, and embodied skills for robot action. We deploy HoloAgent-0 on real hardware and evaluate its spatial memory, long-horizon navigation, and closed-loop execution across motion generation, object search, cross-robot coordination, and mobile manipulation.
Authors: Bole Ma, Jan Eitzinger, Harald Koestler, Gerhard Wellein
Abstract: Multimodal agents repeatedly re-examine the same video frames, UI screenshots, and rendered artifacts as their context window slides and reasoning iterates, yet every look-back re-encodes from scratch, because prefix caches serve reuse only at a fixed leading position. We show this recompute is avoidable, and identify exactly what naive KV reuse loses: the cross-chunk conditioning a chunk absorbs from its neighbours. This loss is asymmetric. The direct readout of a cached chunk is recovered exactly and for free by the standard state-merge. What remains is a diffuse, low-rank residue concentrated in deep layers, invisible to single-hop retrieval but precisely what multi-hop reasoning binds on. Blind reuse therefore leaves single-hop recall intact while halving multi-hop accuracy; this is the failure mode prior position-independent caches, designed for single-context or single-image reuse, do not address. We repair it with a small, training-free low-rank conditioning patch stored alongside each position-free chunk. Reuse reduces to one operator across MLA, GQA, and MHA: exact RoPE re-rotation to any target position, plus the patch that restores cross-chunk binding. This makes three window operations cheap: reorder (one patch serves every ordering of a cached set), sliding-window survival (surviving chunks relocate via rotation only, zero re-encode), and recall (an evicted chunk is rehydrated by its patch, never re-encoded). A rank-m patch recovers full task accuracy on cross-chunk-binding benchmarks, MM-NIAH across two attention families and two-page doc-QA, at a fraction of the KV footprint, and reconstructs re-prefill KV to within bf16 rounding in a production SGLang kernel across six backbones. The conditioning signal is strongest in redundant vision and video streams, making our solution most impactful where multimodal agents spend their recompute budget.
Authors: Seyed Hamid Reza Roodabeh, Zongyu Li, Homa Alemzadeh
Abstract: Robot-assisted minimally invasive surgery improves surgical precision but introduces complexity, making technical error detection essential for ensuring patient safety. Current executional error detection methods using video data often overlook fine-grained contextual descriptions of activities and error types within the hierarchical structure of surgical procedures. They also under-utilize complementary multimodal information. We propose a unified framework for executional error detection that leverages multimodal input, including video, kinematics, and descriptive textual prompts. Through activity prompting, we integrate descriptive language in gesture-level activities, instrument-object interactions, and error definitions. We also introduce activity-aware visual embeddings derived from vision encoders pretrained on surgical activity labels to compare the effectiveness of contrastive language-image embeddings with traditional image-based embeddings for error detection. By seamlessly integrating kinematic data with video and textual modalities, our framework significantly improves error detection performance. Achieving up to 5\% and 16.6\% F1 score improvements over state-of-the-art baselines on the JIGSAWS and SAR-RARP50 datasets, respectively, we demonstrate the value of combining curated textual prompts with multimodal data for accurate error detection.
Authors: Ibrahim Fadhil Djauhari, Adrian Bodenmann, Samuel Simmons, Cailei Liang, David White, Susan Gourvenec, Tom Bennetts, Darryl Newborough, Blair Thornton
Abstract: Global communications rely on subsea cable infrastructure that remains vulnerable to damage from natural hazards and human activity. Autonomous underwater vehicles (AUVs) offer an efficient means to inspect long sections of exposed cable, but uncertainty in cable route maps, small cable diameters and partial burial makes continuous tracking a challenge. This paper presents a novel cable search and tracking method that leverages uncertain prior cable route maps. Graph-based optimisation continuously update the cable route to remain consistent with visual observations. Route uncertainty is constrained as a function of distance from observations using physics-based catenary models that account for cable parameters (i.e., lay depth, diameter, and density), bounding the search space to physically feasible regions and improving search efficiency. Cable detection is performed using a semi-supervised classifier running in real-time on-board a camera-equipped AUV. These detections both update the graph-based optimisation and enable visual cable tracking. When tracking is lost due to misclassification, burial or imperfect control, the bounded search space enables efficient recovery. The approach was demonstrated in field trials using the University of Southampton's Smarty200 AUV. The system successfully located the cable despite deliberate errors in it initial cable route map, updating this to be consistent with observations and using visual tracking to inspect up to 59% of a 120m test cable, with successful recovered after tracking loss.
Authors: Ankur Garg, Ulrich A\"ivodji, Samira Ebrahimi Kahou, Vincent Michalski
Abstract: Machine learning models exploit spurious correlations, achieving high average accuracy but failing disproportionately on underrepresented subgroups. Existing methods address this by adjusting network parameters, guided either by subgroup annotations or inferred pseudo-group labels. Yet at inference, these methods produce only a class prediction, with no insight into a sample's latent subgroup. We propose neural classification trees (NCT), a framework that achieves robustness by encoding subgroup structure in its tree-shaped architecture. By routing each sample to an "easy" or "hard" node of this tree -- based on prediction correctness -- and reusing these routes as pseudo-labels for the next iteration, NCT disentangles conflicting subgroups, without requiring subgroup supervision. We evaluate NCT on five benchmarks spanning binary and multi-class spurious correlations. Our experiments show that the learned tree topology provides strong interpretability by consistently isolating minority subgroups, which provides a transparent mapping between the model architecture and the data's latent group structure, while yielding competitive robustness with state-of-the-art methods.
Authors: James M. Cozens, Simon J. Godsill
Abstract: We introduce PHAST-Net, an attention-guided, physics-informed network for unified estimation of Ideal Time-Frequency Representations (ITFRs), spanning spectral, tempo-based, metrical, and harmonic representations such as Spectrograms, Tempograms, and Metrograms. PHAST-Net learns an application-general mapping from a constellation of wavelet transforms, the proposed Continuous Log-frequency Adaptive Wavelet Transform (CLAWT), to high-resolution, cross-term-suppressed time-frequency (T-F) representations. The proposed constellation of CLAWTs is selected through Cohen's class kernel analysis to maximise curvature coverage in a logarithmic-frequency T-F plane tailored to harmonic signal structure. PHAST-Net further incorporates a proposed physics-informed auxiliary reprojection loss designed to reconstruct the idealised observed CLAWT constellation from the predicted ITFR and the corresponding Cohen's class kernels during training. This auxiliary objective promotes transform consistency and energy conservation, mitigates pathological target sparsity, and enhances optimisation stability. Attention layers further promote effective cross-term suppression across the input constellation. The log-frequency formulation also enables Harmonic PHAST-Net, which estimates a Harmonic ITFR that isolates fundamental structure, supporting robust fundamental-only representations for speech and music, such as derived fundamental Tempograms and Metrograms. We further introduce Spline-PHAST-Net, which parameterises detected and associated T-F ridges as continuous spline trajectories, enabling arbitrary-grid re-rendering and signal reconstruction. Trained on an effectively unbounded procedurally generated dataset, PHAST-Net demonstrates improved accuracy over established approaches, providing a unified framework for high-resolution, cross-term-robust analysis of speech, music, and broader nonstationary signals.
Authors: Chongyi Li, Chunle Guo, Ruicheng Feng, Shangchen Zhou, Chen Change Loy
Abstract: We present Curve Distillation, CuDi, for efficient and controllable exposure adjustment without the requirement of paired or unpaired data during training. Our method inherits the zero-reference learning and curve-based framework from an effective low-light image enhancement method, Zero-DCE, with further speed up in its inference speed, reduction in its model size, and extension to controllable exposure adjustment. The improved inference speed and lightweight model are achieved through novel curve distillation that approximates the time-consuming iterative operation in the conventional curve-based framework by high-order curve's tangent line. The controllable exposure adjustment is made possible with a new self-supervised spatial exposure control loss that constrains the exposure levels of different spatial regions of the output to be close to the brightness distribution of an exposure map serving as an input condition. Different from most existing methods that can only correct either underexposed or overexposed photos, our approach corrects both underexposed and overexposed photos with a single model. Notably, our approach can additionally adjust the exposure levels of a photo globally or locally with the guidance of an input condition exposure map, which can be pre-defined or manually set in the inference stage. Through extensive experiments, we show that our method is appealing for its fast, robust, and flexible performance, outperforming state-of-the-art methods in real scenes. Project page: https://li-chongyi.github.io/CuDi_files/.
Authors: Rishabh Dabral, Muhammad Hamza Mughal, Vladislav Golyanik, Christian Theobalt
Abstract: Conventional methods for human motion synthesis are either deterministic or struggle with the trade-off between motion diversity and motion quality. In response to these limitations, we introduce MoFusion, i.e., a new denoising-diffusion-based framework for high-quality conditional human motion synthesis that can generate long, temporally plausible, and semantically accurate motions based on a range of conditioning contexts (such as music and text). We also present ways to introduce well-known kinematic losses for motion plausibility within the motion diffusion framework through our scheduled weighting strategy. The learned latent space can be used for several interactive motion editing applications -- like inbetweening, seed conditioning, and text-based editing -- thus, providing crucial abilities for virtual character animation and robotics. Through comprehensive quantitative evaluations and a perceptual user study, we demonstrate the effectiveness of MoFusion compared to the state of the art on established benchmarks in the literature. We urge the reader to watch our supplementary video and visit https://vcai.mpi-inf.mpg.de/projects/MoFusion.
Authors: Feifei Wang, Zhentao Tan, Tianyi Wei, Yue Wu, Qidong Huang
Abstract: Despite the success of diffusion-based customization methods on visual content creation, increasing concerns have been raised about such techniques from both privacy and political perspectives. To tackle this issue, several anti-customization methods have been proposed in very recent months, predominantly grounded in adversarial attacks. Unfortunately, most of these methods adopt straightforward designs, such as end-to-end optimization with a focus on adversarially maximizing the original training loss, thereby neglecting nuanced internal properties intrinsic to the diffusion model, and even leading to ineffective optimization in some diffusion time steps. In this paper, we strive to bridge this gap by undertaking a comprehensive exploration of these inherent properties to boost the performance of current anti-customization approaches. Two aspects of properties are investigated: 1) We examine the relationship between time step selection and the model's perception in the frequency domain of images and find that lower time steps can give much more contributions to adversarial noises. This inspires us to propose an adaptive greedy search for optimal time steps that seamlessly integrates with existing anti-customization methods. 2) We scrutinize the roles of features at different layers during denoising and devise a sophisticated feature-based optimization framework for anti-customization. Experiments on facial benchmarks demonstrate that our approach significantly increases identity disruption, thereby protecting user privacy and copyright.
Authors: Ahc\`ene Boubekki, Samuel G. Fadel, Sebastian Mair
Abstract: Explainable AI methods for vision models aim to identify the parts of the input that are important for the final prediction and subsequently relate these regions to human-understandable concepts. Here, we propose focusing solely on the encoder and relating its intermediate outputs to the input, instead. We introduce Neuro-Activated Vision Explanations (NAVE), a post-hoc, unsupervised, and architecture-agnostic (across CNNs and ViTs) method for extracting and visualizing internal representations from frozen vision model encoders. Specifically, NAVE clusters composite feature activations from multiple encoder depths to produce interpretable segmentation maps with controllable granularity, requiring no fine-tuning or architectural modifications. Through extensive experiments, we quantitatively demonstrate that NAVE's concepts align with input semantics and can be used in downstream tasks. We further demonstrate NAVE as an inspection tool by analyzing how training strategies and architectures affect encoder representations. Overall, our results establish NAVE as an effective tool for post-hoc model inspection and enhancing transparency in vision models. \texttt{https://github.com/Ahcene-B/NAVE}
Authors: Jinqing Zhang, Yanan Zhang, Wenrui Cai, Qingjie Liu, Yunhong Wang
Abstract: Occupancy prediction has garnered increasing attention in recent years for its comprehensive fine-grained environmental representation and strong generalization to open-set objects. Nevertheless, mainstream occupancy prediction methods employ cumbersome voxel features as the scene representation, incurring substantial overheads in both memory and computation. When comparing the occupancy distribution in each spatial dimension, we find that the information entropy of the height dimension is much lower than the other two dimensions that constitute the Bird's Eye View (BEV) plane, which indicates that the height distribution of occupancy is easier to learn and predict. Accordingly, we propose Lightweight Spatial Embedding that can represent complete height information in a more compact way than voxel features, thus significantly enhancing its deployability. First, Single-Channel Occupancy is sampled from the multi-view depth distributions, which is then processed by Spatial-to-Channel mechanism to extract Lightweight Spatial Embeddings of different views by 2D convolution. These embeddings will interact with each other through the Lightweight Cross-View Interaction module to obtain the Unified Embedding, which can directly supplement BEV features with height information. Furthermore, we extract Edge-aware Spatial Embedding and apply Geometric Supervision on Spatial Embeddings, aiming to enhance their capability to represent spatial information. We also propose BEV-CutMix, a feature-level data augmentation strategy, to increase the diversity of the driving scenes. We integrate these innovative components into a pure 2D convolutional model, namely LightOcc. Sufficient experimental results show that LightOcc achieves state-of-the-art performance on multiple benchmarks while demonstrating significant efficiency advantages.
Authors: Haijing Liu, Tao Pu, Hefeng Wu, Keze Wang, Feng Gao, Fan Yang, Guanbin Li
Abstract: Benefiting from the generalization capability of CLIP, recent vision language pre-training (VLP) models have demonstrated the ability to capture a wide range of visual concepts in daily images. However, due to the presence of unseen categories in open-vocabulary settings, existing algorithms struggle to capture semantic correlations between categories, leading to suboptimal performance on open-vocabulary multi-label recognition (OV-MLR). Furthermore, the substantial variation in the number of discriminative areas across diverse object categories is misaligned with the fixed-number patch matching used in current methods, introducing noisy visual cues that hinder the capture of target semantics. To address these challenges, we propose a novel category-adaptive cross-modal semantic refinement and transfer (C$^2$SRT) framework to model semantic correlations both within each category and across different categories, in a category-adaptive manner. The proposed framework consists of two complementary modules, i.e., intra-category semantic refinement (ISR) module and inter-category semantic transfer (IST) module. Specifically, the ISR module leverages the cross-modal knowledge of the VLP model to adaptively select a set of local discriminative regions that represent the semantics of the target category. The IST module adaptively discovers a set of correlated categories for a target category by constructing a category-adaptive correlation graph and transfers semantic knowledge from the correlated seen categories to unseen ones. Experiments on OV-MLR benchmarks demonstrate that the proposed C$^2$SRT framework improves over current methods.
Authors: Yanshuo Wang, Xuesong Li, Jinguang Tong, Jie Hong, Jun Lan, Weiqiang Wang, Huijia Zhu, Haoxing Chen
Abstract: Continual test-time domain adaptation (CTTA) aims to adjust pre-trained source models to perform well over time across non-stationary target environments. While previous methods have made considerable efforts to optimize the adaptation process, a crucial question remains: can the model adapt to continually-changing environments with preserved plasticity over a long time? The plasticity refers to the model's capability to adjust predictions in response to non-stationary environments continually. In this work, we explore plasticity, this essential but often overlooked aspect of continual adaptation to facilitate more sustained adaptation in the long run. First, we observe that most CTTA methods experience a steady and consistent decline in plasticity during the long-timescale continual adaptation phase. Moreover, we find that the loss of plasticity is strongly associated with the change in label flip. Based on this correlation, we propose a simple yet effective policy, Adaptive Shrink-Restore (ASR), towards preserving the model's plasticity. In particular, ASR does the weight re-initialization by the adaptive intervals. The adaptive interval is determined based on the change in label flipping. Our method is validated on extensive CTTA benchmarks, achieving excellent performance.
Authors: Ingyun Lee, Jae Won Jang, Seunghyeon Seo, Nojun Kwak
Abstract: Neural Radiance Field (NeRF) has shown remarkable performance in novel view synthesis but requires numerous multi-view images, limiting its practicality in few-shot scenarios. Ray augmentation has been proposed to alleviate overfitting caused by sparse training data by generating additional rays. However, existing methods, which generate augmented rays only near the original rays, exhibit pronounced floaters and appearance distortions due to limited viewpoints and inconsistent rays obstructed by nearby obstacles and complex surfaces. To address these problems, we propose DivCon-NeRF, which introduces novel sphere-based ray augmentations to significantly enhance both diversity and consistency. By employing a virtual sphere centered at the predicted surface point, our method generates diverse augmented rays from all 360-degree directions, facilitated by our consistency mask that effectively filters out inconsistent rays. We introduce tailored loss functions that leverage these augmentations, effectively reducing floaters and visual distortions. Consequently, our method outperforms recent few-shot NeRF approaches on the Blender, LLFF, and DTU datasets. Furthermore, DivCon-NeRF demonstrates strong generalizability by effectively integrating with both regularization- and framework-based few-shot NeRFs.
Authors: Haojia Gao, Haohua Que, Mingkai Liu, Jiayue Xie, Hoiian Au, Yusen Qin, Qian Zhang, Jiajun Sun, Weihao Shan, Tianle Zhu, Handong Yao, Fei Qiao
Abstract: We present \textbf{SenseExpo}, a lightweight single-robot exploration framework that integrates a compact map prediction network into a frontier-based strategy. SenseExpo addresses two long-standing challenges in classical methods -- high computational overhead and poor environmental generalization. Our prediction network combines Generative Adversarial Networks (GANs), Transformers, and Fast Fourier Convolution (FFC) to achieve a remarkably small footprint of only 709K parameters. Despite its compactness, SenseExpo outperforms U-Net (24.5M) and LaMa (51M) on the KTH dataset, achieving PSNR 9.026 and SSIM 0.718, representing a 38.7\% PSNR gain over LaMa. Cross-domain evaluation further verifies strong generalization with an FID of 161.55 on HouseExpo. In exploration experiments, SenseExpo reaches target coverage 67.9\% faster on KTH and 77.1\% faster on MRPB~1.0 than a MapEx-style global obstacle-prediction baseline under the same simulator; because the methods predict different map semantics, this comparison evaluates planning utility rather than a direct predictor ranking. Implemented as a plug-and-play ROS (Robot Operating System) node, our framework integrates with existing navigation stacks, providing an efficient solution for resource-constrained robotic systems.
Authors: Seokha Moon, Janghyun Baek, Yujin Jeong, Daewon Chae, Giseop Kim, Jungbeom Lee, Jinkyu Kim, Sunwook Choi
Abstract: In this paper, we explore dense voxel streaming for accurate and efficient 3D occupancy prediction. While dense voxel representations offer fine-grained spatial details and streaming paradigm enables efficient temporal processing, naively combining the two introduces key challenges: (i) warping-induced distortions caused by interpolation used for temporal alignment, and (ii) degraded dynamic object representations due to motion misalignment and detail loss in image-to-voxel projection. To address these, we propose StreamOcc, a novel framework that utilizes two aggregation strategies. Specifically, it first refines propagated voxel features to reduce warping artifacts before temporal accumulation, and then selectively injects instance-level query features encoding dynamic-object semantics into the corresponding occupied voxel regions, preserving temporally consistent modeling while strengthening dynamic object representations. Unlocking effective dense voxel streaming, StreamOcc achieves state-of-the-art performance on SurroundOcc-benchmark and Occ3D-nuScenes under real-time constraints, outperforming the prior best methods by +1.3/2.5 and +1.5/2.0 in (overall/dynamic object) mIoU, respectively, while running at 83.3 ms per frame with only 2.8 GB of memory. The project page is available at https://moonseokha.github.io/StreamOcc/.
Authors: Wenhao Luo, Zhangyi Shen, Ye Yao, Feng Ding, Guopu Zhu, Weizhi Meng
Abstract: Image generation algorithms are increasingly integral to diverse aspects of human society, driven by their practical applications. However, insufficient oversight in artificial Intelligence generated content (AIGC) can facilitate the spread of malicious content and increase the risk of copyright infringement. Among the diverse range of image generation models, the Latent Diffusion Model (LDM) is currently the most widely used, dominating the majority of the Text-to-Image model market. Currently, most attribution methods for LDMs rely on directly embedding watermarks into the generated images or their intermediate noise, a practice that compromises both the quality and the robustness of the generated content. To address these limitations, we introduce TraceMark-LDM, an novel algorithm that integrates watermarking to attribute generated images while guaranteeing non-destructive performance. Unlike current methods, TraceMark-LDM leverages watermarks as guidance to rearrange random variables sampled from a Gaussian distribution. To mitigate potential deviations caused by inversion errors, the small absolute elements are grouped and rearranged. Additionally, we fine-tune the LDM encoder to enhance the robustness of the watermark. Experimental results show that images synthesized using TraceMark-LDM exhibit superior quality and attribution accuracy compared to state-of-the-art (SOTA) techniques. Notably, TraceMark-LDM demonstrates exceptional robustness against various common attack methods, consistently outperforming SOTA methods.
Authors: Aref Azizpour, Tai D. Nguyen, Matthew C. Stamm
Abstract: Rapid advances in generative AI have enabled the creation of highly realistic synthetic images, which, while beneficial in many domains, also pose serious risks in terms of disinformation, fraud, and other malicious applications. Current synthetic image identification systems are typically static, relying on feature representations learned from known generators; as new generative models emerge, these systems suffer from severe performance degradation. In this paper, we introduce the concept of an autonomous self-adaptive synthetic media identification system -- one that not only detects synthetic images and attributes them to known sources but also autonomously identifies and incorporates novel generators without human intervention. Our approach leverages an open-set identification strategy with an evolvable embedding space that distinguishes between known and unknown sources. By employing an unsupervised clustering method to aggregate unknown samples into high-confidence clusters and continuously refining its decision boundaries, our system maintains robust detection and attribution performance even as the generative landscape evolves. Extensive experiments demonstrate that our method significantly outperforms existing approaches, marking a crucial step toward universal, adaptable forensic systems in the era of rapidly advancing generative models.
Authors: Zhifeng Hao, Kai Hu, Juncai Zhang, Zhidan Zhao, Zhengming Chen
Abstract: Traffic prediction is difficult due to the complex interplay of temporal evolution, spatial interactions, and delayed spatio-temporal propagation over road networks. Existing methods either model spatial and temporal dependencies separately or employ unified spatio-temporal structures, but they often insufficiently characterize how neighboring sensors at historical timestamps influence a target node, while complex joint models may incur high computation. This paper proposes STEI-PCN, an efficient pure convolutional network based on spatio-temporal encoding and relation inference. It first builds a local causal joint spatio-temporal graph to restrict candidate interactions, then uses absolute position and relative distance encodings to infer dynamic edge weights. A single-layer graph convolution with a position-aware gated activation unit captures local joint dependencies, and temporal dilated causal convolutions complement long-range temporal patterns. A multi-view prediction module fuses raw, local propagation, and long-range temporal representations for direct multi-step forecasting. Experiments on PeMS03, PeMS04, PeMS07, PeMS08, and PeMS-Bay under multiple horizons show that STEI-PCN achieves competitive accuracy with moderate parameters and low training and inference costs. Ablation and fluctuation analyses further verify the contributions of the main components and empirically analyze the effects of the training-stage constraints under sharp speed changes. Our code is available at a GitHub link https://github.com/Jessez2/STEI-PCN.
Authors: Makoto Yamada, Kian Ming A. Chai, Ayoub Rhim, Satoki Ishikawa, Mohammad Sabokrou, Yao-Hung Hubert Tsai
Abstract: Representation learning is one of the key research topics in machine learning, and the framework of self-supervised learning (SSL) has revolutionized computer vision. However, these approaches have not yet fully leveraged insights from biological visual processing systems. In this paper, we introduce PhiNet v2, a novel architecture that processes temporal visual input (i.e., sequences of images) without relying on strong data augmentation, enabling it to learn robust visual representations in a manner similar to human visual processing. Our learning objective is derived from variational inference. Through extensive experiments, we demonstrate that PhiNet v2 achieves competitive performance compared to state-of-the-art vision representation models, including RSP and CropMAE, while retaining the ability to learn effectively from sequential input without strong data augmentation. This work represents a step toward more biologically plausible computer vision systems that process visual information in a manner more aligned with human cognitive processes.
Authors: Zhongpai Gao, Benjamin Planche, Meng Zheng, Anwesa Choudhuri, Van Nguyen Nguyen, Terrence Chen, Ziyan Wu
Abstract: Photorealistic volumetric rendering of CT scans greatly benefits clinical workflows, yet neural approaches such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) require prohibitive per-scan optimization (hours for NeRF, about 30 minutes for 3DGS), making them impractical in clinical settings. We propose Render-FM, a feedforward model that eliminates this bottleneck by directly regressing 6D Gaussian Splatting (6DGS) parameters from a CT volume in a single 2.8-second forward pass, a 500x speedup over per-scan optimization. To bridge the domain gap between natural scene reconstruction and medical volumetric rendering, we introduce Anatomy-Guided Priming (AGP), which incorporates segmentation masks and transfer functions as structural and appearance priors, information that existing Gaussian splatting methods overlook. Built on an nnU-Net-inspired 3D U-Net trained on diverse CT scans, Render-FM predicts per-voxel 6DGS parameters and supports immediate real-time rendering. Unlike per-scan methods, it generalizes to unseen anatomies, novel transfer functions, and enables compositional organ visualization with zero additional preparation time. Optional 89-second fine-tuning further improves quality, surpassing per-scan optimized baselines. Project page: https://gaozhongpai.github.io/renderfm/.
Authors: Nikolas Papadopoulos, Nikolaos Ioannis Bountos, Maria Sdraka, Andreas Karavias, Gustau Camps-Valls, Ioannis Papoutsis
Abstract: Monitoring volcanic activity is of paramount importance to safeguarding lives, infrastructure, and ecosystems. However, only a small fraction of known volcanoes are continuously monitored. Satellite-based Interferometric Synthetic Aperture Radar (InSAR) enables systematic, global-scale deformation monitoring. However, its complex data challenge traditional remote sensing methods. Deep learning offers a powerful means to automate and enhance InSAR interpretation, advancing volcanology and geohazard assessment. Despite its promise, progress has been limited by the scarcity of well-curated datasets. In this work, we build on the existing Hephaestus dataset and introduce Thalia, addressing crucial limitations and enriching its scope with higher-resolution, multi-source, and multi-temporal data. Thalia is a global collection of 38 spatiotemporal datacubes covering 7 years and integrating InSAR products, topographic data, as well as atmospheric variables, known to introduce signal delays that can mimic ground deformation in InSAR imagery. Each sample includes expert annotations detailing the type, intensity, and extent of deformation, accompanied by descriptive text. To enable fair and consistent evaluation, we provide a comprehensive benchmark using state-of-the-art models for classification and segmentation. This work fosters collaboration between machine learning and Earth science, advancing volcanic monitoring and promoting data-driven approaches in geoscience. See https://github.com/Orion-AI-Lab/Thalia
Authors: Lifeng Chen, Jiner Wang, Zihao Pan, Beier Zhu, Xiaofeng Yang, Chi Zhang
Abstract: Recent advances in text-to-image (T2I) generation have led to impressive visual results. However, these models still face significant challenges when handling complex prompt, particularly those involving multiple subjects with distinct attributes. Inspired by the human drawing process, which first outlines the composition and then incrementally adds details, we propose Detail++, a training-free framework that introduces a novel Progressive Detail Injection (PDI) strategy to address this limitation. Specifically, we decompose a complex prompt into a sequence of simplified sub-prompts, guiding the generation process in stages. This staged generation leverages the inherent layout-controlling capacity of self-attention to first ensure global composition, followed by precise refinement. To achieve accurate binding between attributes and corresponding subjects, we exploit cross-attention mechanisms and further introduce a Centroid Alignment Loss at test time to reduce binding noise and enhance attribute consistency. Extensive experiments on T2I-CompBench and a newly constructed style composition benchmark demonstrate that Detail++ significantly outperforms existing methods, particularly in scenarios involving multiple objects and complex stylistic conditions.
Authors: Peng Dai, Feitong Tan, Qiangeng Xu, Yihua Huang, David Futschik, Ruofei Du, Sean Fanello, Yinda Zhang, Xiaojuan Qi
Abstract: While video generation models excel at producing high-quality monocular videos, generating 3D stereoscopic and spatial videos for immersive applications remains an underexplored challenge. We present a pose-free and training-free method that leverages an off-the-shelf monocular video generation model to produce immersive 3D videos. Our approach first warps the generated monocular video into pre-defined camera viewpoints using estimated depth information, then applies a novel \textit{frame matrix} inpainting framework. This framework utilizes the original video generation model to synthesize missing content across different viewpoints and timestamps, ensuring spatial and temporal consistency without requiring additional model fine-tuning. Moreover, we develop a \dualupdate~scheme that further improves the quality of video inpainting by alleviating the negative effects propagated from disoccluded areas in the latent space. The resulting multi-view videos are then adapted into stereoscopic pairs or optimized into 4D Gaussians for spatial video synthesis. We validate the efficacy of our proposed method by conducting experiments on videos from various generative models, such as Sora, Lumiere, WALT, and Zeroscope. The experiments demonstrate that our method has a significant improvement over previous methods. Project page at: https://daipengwa.github.io/S-2VG_ProjectPage/
Authors: Shuteng Wang, Christian Theobalt, Vladislav Golyanik
Abstract: Quantum Implicit Neural Representations (QINRs) have emerged as a promising paradigm that leverages parametrised quantum circuits to encode and process classical information. However, significant challenges remain in areas such as ansatz architecture design, the effective utility of quantum-mechanical properties, training efficiency, and the integration with classical modules. This paper advances the field by introducing a novel QINR architecture for 2D image and 3D geometric field learning, which we collectively refer to as Quantum Visual Field (QVF). QVF encodes classical data into quantum statevectors using neural amplitude encoding grounded in a learnable energy manifold, ensuring meaningful Hilbert-space embeddings. Our ansatz follows a fully entangled design of learnable parametrised quantum circuits, with quantum (unitary) operations performed in the real Hilbert space, resulting in numerically stable training with fast convergence. QVF does not rely on classical post-processing -- in contrast to the previous QINR learning approach -- and directly employs measurements to extract learned signals encoded in the ansatz. Experiments on a quantum hardware simulator demonstrate that QVF outperforms an existing quantum approach and competes with widely used classical foundational baselines in terms of visual representation accuracy across various metrics and model characteristics. We also show applications of QVF in 2D and 3D field completion and 3D shape interpolation, highlighting its practical potential. Project page: https://4dqv.mpi-inf.mpg.de/QVF/.
Authors: Yeji Park, Minyoung Lee, Sanghyuk Chun, Junsuk Choe
Abstract: Large Vision-Language Models (LVLMs) exhibit strong performance on single-image tasks. However, their performance degrades significantly when handling multi-image inputs. While this degradation has been observed in prior work, its nature remains poorly understood. We empirically observe visual elements from different images become entangled in the model's representations and responses. We refer to this phenomenon as cross-image information leakage. To address this issue, we propose FOCUS, a training-free and architecture-agnostic method. FOCUS masks all but one image with random noise, guiding the model to focus on the single clean image. This process is applied across the target images to obtain logits under partially masked contexts. These logits are aggregated and then refined using a noise-only reference input, which suppresses the leakage and yields more accurate outputs. FOCUS consistently improves performance on diverse multi-image benchmarks. We further show that FOCUS generalizes to video understanding, extending its applicability beyond static multi-image inputs. This demonstrates that FOCUS offers a general solution for enhancing multi-image reasoning without additional training or architectural modifications.
Authors: Ravi Shankar Prasad, Dinesh Singh
Abstract: Craniofacial reconstruction in forensics is one of the processes to identify victims of crime and natural disasters. Identifying an individual from their remains plays a crucial role when all other identification methods fail. Traditional methods for this task, such as clay-based craniofacial reconstruction, require expert domain knowledge and are a time-consuming process. At the same time, other probabilistic generative models like the statistical shape model or the Basel face model fail to capture the skull and face cross-domain attributes. Looking at these limitations, we propose a generic framework for craniofacial reconstruction from 2D X-ray images. Here, we used various generative models (i.e., CycleGANs, cGANs, etc) and fine-tune the generator and discriminator parts to generate more realistic images in two distinct domains, which are the skull and face of an individual. This is the first time where 2D X-rays are being used as a representation of the skull by generative models for craniofacial reconstruction. We have evaluated the quality of generated faces using FID, IS, and SSIM scores. Finally, we have proposed a retrieval framework where the query is the generated face image and the gallery is the database of real faces. By experimental results, we have found that these generative models can be used as an assisting tool for craniofacial identifications in forensic science.
Authors: Geewook Kim, Minjoon Seo
Abstract: Speech and audio encoders developed over years of community effort are routinely excluded from video understanding pipelines, not because they fail, but because benchmarks never required listening. We audit 10 video benchmarks and find items largely solvable from visual cues alone: a single-frame probe answers about 76% of AVQA without audio, suggesting poor measurement of audio-visual reasoning. Building on LLaVA-OneVision, we attach a speech/audio encoder and compare five compressor architectures under 25-fold token reduction (25 Hz to 1 Hz). Across 10 benchmarks, with and without filtering, audio yields clear gains on tasks requiring speech comprehension or cross-modal grounding, while vision-centric suites remain largely unaffected. Our results show that speech encoders play a larger role in video understanding than current benchmarks suggest. We will open-source our work at https://github.com/naver-ai/unimambamia-av.
Authors: Jinpeng Lu, Linghan Cai, Yinda Chen, Guo Tang, Songhan Jiang, Haoyuan Shi, Zhiwei Xiong
Abstract: Lightweight 3D medical image segmentation remains constrained by a fundamental \textit{``efficiency / robustness conflict''}, particularly when processing complex anatomical structures and heterogeneous modalities. In this paper, we study how to redesign the framework based on the characteristics of high-dimensional 3D images, and explore data synergy to overcome the fragile representation of lightweight methods. Our approach, VeloxSeg, begins with a deployable and extensible dual-stream CNN-Transformer architecture composed of Paired Window Attention (PWA) and Johnson-Lindenstrauss lemma-guided convolution (JLC). For each 3D image, we invoke a ``glance-and-focus'' principle, where PWA rapidly retrieves multi-scale information, and JLC ensures robust local feature extraction with minimal parameters, significantly enhancing the model's ability to operate with low computational budget. Followed by an extension of the dual-stream architecture that incorporates modal interaction into the multi-scale image-retrieval process, VeloxSeg efficiently models heterogeneous modalities. Finally, Spatially Decoupled Knowledge Transfer (SDKT) via Gram matrices injects the texture prior extracted by a self-supervised network into the segmentation network, yielding stronger representations than baselines at no extra inference cost. Experimental results on multimodal benchmarks show that VeloxSeg achieves a 26\% Dice improvement, alongside increasing GPU throughput by 11$\times$, CPU by 48$\times$, and reducing training peak GPU memory usage by $1/20$, inference by $1/24$. Code is available at https://github.com/JinPLu/VeloxSeg.
Authors: Zhen-Hao Xie, Yan Wang, Lan Li, Han-Jia Ye, De-Chuan Zhan, Da-Wei Zhou
Abstract: Class-Incremental Learning (CIL) aims to endow models with the ability to continuously adapt to evolving data streams. Recent advances in pre-trained vision-language models (e.g., CLIP) provide a powerful foundation for this task. However, existing approaches often rely on simplistic templates, such as "a photo of a [CLASS]", which overlook the hierarchical nature of visual concepts. For example, recognizing "cat" versus "car" depends on coarse-grained cues, while distinguishing "cat" from "lion" requires fine-grained details. Similarly, the current feature mapping in CLIP relies solely on the representation from the last layer, neglecting the hierarchical information contained in earlier layers. In this work, we introduce HiErarchical Representation MAtchiNg (HERMAN) for CLIP-based CIL. Our approach leverages LLMs to recursively generate discriminative textual descriptors, thereby augmenting the semantic space with explicit hierarchical cues. These descriptors are matched to different levels of the semantic hierarchy and adaptively routed based on task-specific requirements, enabling precise discrimination while alleviating catastrophic forgetting in incremental tasks. Extensive experiments on multiple benchmarks demonstrate that our method consistently achieves state-of-the-art performance.
Authors: Shubhang Bhatnagar, Andy Xu, Kar-Han Tan, Narendra Ahuja
Abstract: Large Language Models (LLMs) with multimodal capabilities have revolutionized vision-language tasks, but their deployment often requires huge memory and computational resources. Post-training quantization (PTQ) has successfully compressed language models to as low as 1-bit precision, its effectiveness for multimodal LLMs (MLLMs) remains unexplored. In this paper, we present the first method for ultra-low-bit (<4-bit) quantization of MLLMs. Our analysis reveals that multimodal tokens and intermediate layer activations produced by them exhibit significantly higher entropy compared to text tokens, indicating greater functional complexity that makes MLLMs less tolerant to ultra-low bit quantization. However, this entropy varies significantly across layers, with some layers producing lower-entropy activation distributions that we empirically show can better tolerate ultra-low bit quantization. Existing PTQ methods optimize weight quantization within each layer but apply the same target precision uniformly, ignoring this variation in complexity across layers. Building on this insight, we propose LUQ: Layerwise Ultra-Low Bit Quantization, which characterizes each transformer layer's functional complexity via its output activation entropy and selectively applies ultra-low bit quantization to layers encoding simpler, more compressible functions. We also show that multimodal calibration (image and text tokens) boosts VQA performance in the ultra-low bit regime. Evaluated on LLaVA-1.5 and Qwen-2.5-VL across 9 VQA benchmarks, LUQ models use 40% and 31% less memory than their 4-bit counterparts while exhibiting less than 10% degradation on MME.
Authors: Derek Shi, Ruben Glatt, Christine Klymko, Shubham Mohole, Hongjun Choi, Shashank Kushwaha, Sam Sakla, Felipe Leno da Silva
Abstract: Recent advances in large video-language models (VLMs) rely on extensive fine-tuning techniques that strengthen alignment between textual and visual comprehension. Leading pipelines typically pair supervised fine-tuning (SFT) with reinforcement learning from preference data to enhance video comprehension. However, as VLMs scale in parameter size, so does the cost of gathering enough human feedback. To make fine-tuning more cost-effective, recent frameworks explore reinforcement learning with AI feedback (RLAIF), which replace human preference with AI as a judge. Current RLAIF frameworks rely on a specialized reward model trained with video narratives to create calibrated scalar rewards -- an expensive and restrictive pipeline. We propose Oracle-RLAIF, a novel framework that replaces the trained reward model with a more general Oracle ranker which acts as a drop-in model ranking candidate model responses rather than scoring them. Alongside Oracle-RLAIF, we introduce $GRPO_{rank}$, a novel rank-based loss function based on Group Relative Policy Optimization (GRPO) that directly optimizes ordinal feedback with rank-aware advantages. Empirically, we demonstrate that Oracle-RLAIF consistently outperforms leading VLMs using existing fine-tuning methods when evaluated across various video comprehension benchmarks. Oracle-RLAIF paves the path to creating flexible and data-efficient frameworks for aligning large multi-modal video models with reinforcement learning from rank rather than score.
Authors: Ran Eisenberg, Amit Rozner, Ethan Fetaya, Ofir Lindenbaum
Abstract: Deep neural networks can achieve high accuracy while relying on evidence that is hard to inspect or misaligned with the intended task. Concept Bottleneck Models (CBMs) expose human-interpretable concepts, but most treat concepts as global attributes and do not show how localized evidence is aggregated into a decision. We propose \textbf{SEG-MIL-CBM}, a spatially grounded CBM that decomposes each image into concept-guided regions and classifies it by attention-based aggregation of segment-level concept evidence. The same segment evidence terms form the prediction and the explanation, exposing which regions and concepts support the predicted logit without a separate post-hoc attribution module. Among evaluated CBM-family baselines, SEG-MIL-CBM improves Waterbirds worst-group accuracy from $65.1\%$ to $72.0\%$, reaches $87.4\%$ worst-group accuracy on Pawrious, remains competitive on standard recognition, and attains the best CBM accuracy on CIFAR-100 ($85.3\%$). Segment-level faithfulness experiments on CUB further show that its learned segment ranking matches or improves over evaluated segment-ranking controls.
Authors: Theo Di Piazza, Carole Lazarus, Olivier Nempont, Loic Boussel
Abstract: With the growing volume of CT examinations, there is an increasing demand for automated tools such as organ segmentation, abnormality detection, and report generation to support radiologists in managing their clinical workload. Multi-label classification of 3D Chest CT scans remains a critical yet challenging problem due to the complex spatial relationships inherent in volumetric data and the wide variability of abnormalities. Existing methods based on 3D convolutional neural networks struggle to capture long-range dependencies, while Vision Transformers often require extensive pre-training on large-scale, domain-specific datasets to perform competitively. In this work, we propose a 2.5D alternative by introducing a new graph-based framework that represents 3D CT volumes as structured graphs, where axial slice triplets serve as nodes processed through spectral graph convolution, enabling the model to reason over inter-slice dependencies while maintaining complexity compatible with clinical deployment. Our method, trained and evaluated on 3 datasets from independent institutions, achieves strong cross-dataset generalization, and shows competitive performance compared to state-of-the-art visual encoders. We further conduct comprehensive ablation studies to evaluate the impact of various aggregation strategies, edge-weighting schemes, and graph connectivity patterns. Additionally, we demonstrate the broader applicability of our approach through transfer experiments on automated radiology report generation and abdominal CT data.
Authors: Bohan Li, Zhuang Ma, Dalong Du, Baorui Peng, Zhujin Liang, Zhenqiang Liu, Xianda Guo, Zheng Zhu, Chao Ma, Yueming Jin, Xin Jin, Hao Zhao, Wenjun Zeng
Abstract: Autonomous driving world models are expected to work effectively across three core dimensions: state, action, and reward. However, existing methods are typically restricted to fragmented modality modeling, short-horizon drift, and imprecise action control, while lacking intrinsic mechanisms for policy evaluation. In this paper, we introduce OmniNWM, an Omniscient panoramic Navigation World Model that addresses all three dimensions within a consistent probabilistic framework. For State, OmniNWM generates panoramic videos of RGB, semantics, metric depth, and 3D occupancy, ensuring pixel-level alignment across modalities with joint distribution modeling. To mitigate autoregressive exposure bias, we propose a structured panoramic forcing strategy to stabilize long-horizon generation via stochastic manifold thickening. For Action, we introduce canonical geometric action encoding with normalized panoramic Pl\"ucker ray-maps. This representation decouples motion dynamics from sensor intrinsics, enabling precise, zero-shot trajectory control across heterogeneous datasets and camera configurations. For Reward, we derive intrinsic occupancy-grounded dense rewards directly from generated 3D volumes, establishing a reliable closed-loop simulation cycle for evaluating diverse planning agents. Extensive experiments demonstrate that OmniNWM achieves SOTA performance in generation fidelity and control precision, with remarkable zero-shot robustness to novel scenes on NuPlan and in-house datasets with distinct camera rigs. Project page is available at https://arlo0o.github.io/OmniNWM/.
Authors: Toan Van Nguyen, Rasmus G. K. Christiansen, Dirk Kraft, Leon Bodenhagen
Abstract: This paper introduces a novel multi-object tracking (MOT) method, dubbed GenTrack, whose main contributions include: first-a hybrid tracking approach employing both stochastic and deterministic manners to robustly handle unknown and time-varying numbers of targets, particularly in maintaining target identity (ID) consistency and managing nonlinear dynamics, second-leveraging particle swarm optimization (PSO) with some proposed fitness measures to guide stochastic particles toward their target distribution modes, enabling effective tracking even with weak and noisy object detectors, third-integration of social interactions among targets to enhance PSO-guided particles as well as improve continuous updates of both strong (matched) and weak (unmatched) tracks, thereby reducing ID switches and track loss, especially during occlusions, fourth-a GenTrack-based redefined visual MOT baseline incorporating a comprehensive state and observation model based on space consistency, appearance, detection confidence, track penalties, and social scores for systematic and efficient target updates, and five-the first ever publicly available source-code reference implementation with minimal dependencies, featuring three variants, including GenTrack Simple, Strengthen, and Super, facilitating flexible reimplementation. Experimental results have shown that GenTrack provides superior performance on standard benchmarks and real-world scenarios compared to state-of-the-art trackers, with integrated implementations of baselines for fair comparison. Potential directions for future work are also discussed. The source-code reference implementations of both the proposed method and compared-trackers are provided on GitHub: https://github.com/SDU-VelKoTek/GenTrack
Authors: Minjoon Jung, Junbin Xiao, Junghyun Kim, Byoung-Tak Zhang, Angela Yao
Abstract: Do Video-LLMs have consistent temporal understanding when videos capture the same event from different viewpoints? To study this question, we introduce EgoExo-Con(sistency), a benchmark of synchronized egocentric and exocentric video pairs with human-refined queries that ensure all concepts are visible in both viewpoints. EgoExo-Con emphasizes two temporal understanding tasks: Temporal Verification and Temporal Grounding. It evaluates not only correctness but consistency across viewpoints. Our analysis reveals two critical limitations of existing Video-LLMs: (1) models often fail to maintain consistency, with results far worse than their single-view performances. (2) When naively finetuned with synchronized videos of both viewpoints, the models show improved consistency but often underperform those trained on a single view. For improvements, we propose View-GRPO, a novel reinforcement learning framework that effectively strengthens view-specific temporal reasoning while encouraging consistent comprehension across viewpoints. Our method demonstrates its superior temporal understanding capabilities, especially for improving cross-view consistency. All resources have been made available at https://minjoong507.github.io/projects/EgoExo-Con/
Authors: Zhong Chen, Changfeng Chen
Abstract: Accurate intrinsic calibration is a crucial yet challenging prerequisite for 3D reconstruction using light field cameras. Existing calibration models typically analyze the main lens and micro lens array (MLA) in a coupled manner, resulting in high complexity and a large number of parameters. In this paper, we propose a linear fractional transformation (LFT) model that introduces a single parameter $\alpha$ to decouple the imaging processes of the main lens and the MLA. A dedicated matrix $\mathbf{H}_\alpha$ is designed to characterize the MLA projection, enabling the main lens and the MLA to be calibrated independently. The proposed calibration method consists of an analytical least-squares solution for $\mathbf{H}_\alpha$, followed by joint nonlinear refinement of all intrinsic parameters. Experimental results on both physical datasets and simulated data demonstrate that the proposed method achieves a mean translation error of $2.1\%$, outperforming the state-of-the-art, while maintaining sub-pixel reprojection accuracy. The complete codebase, including a light field simulator based on the proposed model, is openly available to the research community.
Authors: Aldino Rizaldy, Fabian Ewald Fassnacht, Ahmed Jamal Afifi, Hua Jiang, Richard Gloaguen, Pedram Ghamisi
Abstract: Detailed structural and species information on individual tree level is increasingly important to support precision forestry, biodiversity conservation, and provide reference data for biomass and carbon mapping. Point clouds from airborne and ground-based laser scanning are currently the most suitable data source to rapidly derive such information at scale. Recent advancements in deep learning improved segmenting and classifying individual trees and identifying semantic tree components. However, deep learning models typically require large amounts of annotated training data which limits further improvement. Producing dense, high-quality annotations for 3D point clouds, especially in complex forests, is labor-intensive and challenging to scale. We explore strategies to reduce dependence on large annotated datasets using self-supervised and transfer learning. Our objective is to improve performance across three tasks: instance segmentation, semantic segmentation, and tree classification using realistic and operational training sets. We observe improvements across all tasks, compared to training from scratch, evaluated with their respective metrics. For instance segmentation, self-supervised learning combined with domain adaptation improves AP50 by 16.98%. For semantic segmentation, self-supervised learning alone improves mIoU by 1.79%. For tree classification, hierarchical transfer learning improves mean Jaccard by 6.07%. To simplify use and encourage uptake, we integrated the tasks into a unified framework, streamlining the process from raw point clouds to tree delineation, structural analysis, and species classification. Pretrained models reduce energy consumption and carbon emissions by ~21%. This open-source contribution aims to accelerate operational extraction of individual tree information from laser scanning point clouds to support forestry, biodiversity, and carbon mapping.
Authors: Jose Reinaldo Cunha Santos A V Silva Neto, Hodaka Kawachi, Yasushi Yagi, Tomoya Nakamura
Abstract: Lensless imaging reconstructs scenes from highly multiplexed measurements, resulting in a severely ill-posed inverse problem. In this work, we identify a fundamental trade-off between measurement consistency, perceptual quality, and inference speed across lensless reconstruction paradigms. Traditional methods favor consistency but produce perceptually degraded results, supervised approaches achieve high-quality reconstructions with fast inference but may violate physical constraints, and diffusion-prior methods achieve high perceptual quality and consistency--particularly when structured constraints such as range-null decomposition are used--but remain slow due to iterative sampling. Motivated by this observation, we propose Null-Space Diffusion Distillation (NSDD), a single-pass reconstruction model that distills structured diffusion-prior inference into an efficient feed-forward network. NSDD learns to produce high-quality reconstructions that preserve measurement consistency while avoiding costly iterative sampling. Experimental results demonstrate that NSDD achieves perceptual quality and consistency competitive with diffusion-prior methods, while providing significantly faster inference and offering a favorable balance across all three objectives. Furthermore, ablation experiments show that distilling the range--null decomposition improves reconstruction quality and robustness over unstructured full-reconstruction distillation, including on unseen real scenes. These results highlight the potential of structure-aware distillation for efficient lensless imaging. Code is available at github.com/JRCSAVSN/NullSpaceDiffusionDistillation.
Authors: Jiancheng Fang, Shaoyu Wang, Junlin Wang, Weiwen Wu, Yikun Zhang, Qiegen Liu
Abstract: Multi-source stationary computed tomography (CT) has recently attracted attention for its ability to achieve rapid image reconstruction, making it suitable for time-sensitive clinical and industrial applications. However, practical systems are often constrained by ultra-sparse-view sampling, which significantly degrades reconstruction quality. Traditional methods struggle under ultra-sparse-view settings, where interpolation becomes inaccurate and the resulting reconstructions are unsatisfactory. To address this challenge, this study proposes Diffusion-Refined Neural Attenuation Fields (Diff-NAF), an iterative framework tailored for multi-source stationary CT under ultra-sparse-view conditions. Diff-NAF combines a Neural Attenuation Field representation with a dual-branch conditional diffusion model. The process begins by training an initial NAF using ultra-sparse-view projections. New projections are then generated through an Angle-Prior Guided Projection Synthesis strategy that exploits inter view priors, and are subsequently refined by a Diffusion-driven Reuse Projection Refinement Module. The refined projections are incorporated as pseudo-labels into the training set for the next iteration. Through iterative refinement, Diff-NAF progressively enhances projection completeness and reconstruction fidelity under ultra-sparse-view conditions, ultimately yielding high-quality CT reconstructions. Experimental results on multiple simulated 3D CT volumes and real projection data demonstrate that Diff-NAF achieves the best performance under ultra-sparse-view conditions.
Authors: Duo Li, Zuhao Yang, Xiaoqin Zhang, Ling Shao, Shijian Lu
Abstract: Discrete diffusion-based multimodal large language models (dMLLMs) have emerged as a promising alternative to autoregressive MLLMs thanks to their advantages in parallel decoding and bidirectional context modeling, but most existing dMLLMs incur significant computational overhead during inference due to the full-sequence attention computation in each denoising step. Pioneering studies attempt to resolve this issue from a modality-agnostic perspective via key-value cache optimization or efficient sampling but most of them overlook modality-specific visual token redundancy. In this work, we conduct a comprehensive study on how visual token redundancy evolves with different dMLLM architectures and tasks and how visual token pruning affects dMLLM responses and efficiency. Specifically, our study reveals that visual redundancy emerges only in from-scratch dMLLMs while handling long-answer tasks. In addition, we validate that visual token pruning introduces non-negligible information loss in dMLLMs and only from-scratch dMLLMs can recover the lost information progressively during late denoising steps. Furthermore, our study shows that layer-skipping is promising for accelerating AR-to-diffusion dMLLMs, whereas progressive or late-step pruning is more effective for from-scratch dMLLMs. Overall, this work offers a new perspective on efficiency optimization for dMLLMs, greatly advancing their applicability across various multimodal understanding tasks. The code is available at: https://github.com/Yrdal3910/dMLLM-Visual-Token-Redundancy-Analysis.
URLs: https://github.com/Yrdal3910/dMLLM-Visual-Token-Redundancy-Analysis.
Authors: Liav Hen, Tom Tirer, Raja Giryes, Shady Abu-Hussein
Abstract: Diffusion models provide powerful generative priors for solving inverse problems by sampling from a posterior distribution conditioned on corrupted measurements. Existing methods primarily follow two paradigms: direct methods, which approximate the likelihood term, and proximal methods, which incorporate intermediate solutions satisfying measurement constraints into the sampling process. Under standard Gaussian approximations and locally-linear measurements, we demonstrate that these approaches differ fundamentally in their treatment of the diffusion denoiser's Jacobian within the likelihood term. While this Jacobian encodes critical prior knowledge of the data distribution, training-induced non-idealities can degrade performance in zero-shot settings. In this work, we bridge direct and proximal approaches by proposing a principled Jacobian-Aware Posterior Sampler (JAPS). JAPS leverages the Jacobian's prior knowledge while mitigating its detrimental effects through a corresponding proximal solution, requiring no additional computational cost. Additionally, we integrate our guidance into DDIM sampling, with a corrected conditional factor that has been missing in previous works. Our method enhances reconstruction quality across diverse linear and nonlinear noisy imaging tasks, outperforming existing diffusion-based baselines in perceptual quality while maintaining or improving distortion metrics.
Authors: Xuelu Feng, Yunsheng Li, Ziyu Wan, Zixuan Gao, Junsong Yuan, Dongdong Chen, Chunming Qiao
Abstract: Reinforcement learning (RL) has recently emerged as a promising approach for aligning text-to-image generative models with human preferences. A key challenge, however, lies in designing effective and interpretable rewards. Existing methods often rely on either composite metrics (e.g., CLIP, OCR, and realism scores) with fixed weights or a single scalar reward distilled from human preference models, which can limit interpretability and flexibility. We propose RubricRL, a simple and general framework for rubric-based reward design that offers greater interpretability, composability, and user control. Instead of using a black-box scalar signal, RubricRL dynamically constructs a structured rubric for each prompt--a decomposable checklist of fine-grained visual criteria such as object correctness, attribute accuracy, OCR fidelity, and realism--tailored to the input text. Each criterion is independently evaluated by a multimodal judge (e.g., o4-mini), and a prompt-adaptive weighting mechanism emphasizes the most relevant dimensions. This design not only produces interpretable and modular supervision signals for policy optimization (e.g., GRPO or PPO), but also enables users to directly adjust which aspects to reward or penalize. Experiments with an autoregressive text-to-image model demonstrate that RubricRL improves prompt faithfulness, visual detail, and generalizability, while offering a flexible and extensible foundation for interpretable RL alignment across text-to-image architectures.
Authors: Taehoon Kim, Henry Gouk, Timothy Hospedales
Abstract: Test-time alignment (TTA) aims to adapt models to specific rewards during inference. However, existing methods tend to either under-optimise or over-optimise (reward hack) the target reward function. We propose Null-Text Test-Time Alignment (Null-TTA), which aligns diffusion models by optimising the unconditional embedding in classifier-free guidance, rather than manipulating latent or noise variables. Due to the structured semantic nature of the text embedding space, this ensures alignment occurs on a semantically coherent manifold and prevents reward hacking (exploiting non-semantic noise patterns to improve the reward). Since the unconditional embedding in classifier-free guidance serves as the anchor for the model's generative distribution, Null-TTA directly steers model's generative distribution towards the target reward rather than just adjusting the samples, even without updating model parameters. Thanks to these desirable properties, we show that Null-TTA achieves state-of-the-art target test-time alignment while maintaining strong cross-reward generalisation. This establishes semantic-space optimisation as an effective and principled novel paradigm for TTA.
Authors: Image Team, Huanqia Cai, Sihan Cao, Ruoyi Du, Peng Gao, Aiming Hao, Steven Hoi, Zhaohui Hou, Shijie Huang, Dengyang Jiang, Yuming Jiang, Xin Jin, Liangchen Li, Zhen Li, Zhong-Yu Li, David Liu, Dongyang Liu, Qilong Wu, Feng Yu, Zechao Zhan, Chi Zhang, Shifeng Zhang, Ruikai Zhou, Shilin Zhou
Abstract: The landscape of high-performance image generation models is currently dominated by proprietary systems, such as Nano Banana Pro and Seedream 4.0. Leading open-source alternatives, including Qwen-Image, Hunyuan-Image-3.0 and FLUX.2, are characterized by massive parameter counts (20B to 80B), making them impractical for inference, and fine-tuning on consumer-grade hardware. To address this gap, we propose Z-Image, an efficient 6B-parameter foundation generative model built upon a Scalable Single-Stream Diffusion Transformer (S3-DiT) architecture that challenges the "scale-at-all-costs" paradigm. By systematically optimizing the entire model lifecycle -- from a curated data infrastructure to a streamlined training curriculum -- we complete the full training workflow in just 314K H800 GPU hours (approx. $630K). Our few-step distillation scheme with reward post-training further yields Z-Image-Turbo, offering both sub-second inference latency on an enterprise-grade H800 GPU and compatibility with consumer-grade hardware (<16GB VRAM). Additionally, our omni-pre-training paradigm also enables efficient training of Z-Image-Edit, an editing model with impressive instruction-following capabilities. Both qualitative and quantitative experiments demonstrate that our model achieves performance comparable to or surpassing that of leading competitors across various dimensions. Most notably, Z-Image exhibits exceptional capabilities in photorealistic image generation and bilingual text rendering, delivering results that rival top-tier commercial models, thereby demonstrating that state-of-the-art results are achievable with significantly reduced computational overhead. We publicly release our code, weights, and online demo to foster the development of accessible, budget-friendly, yet state-of-the-art generative models.
Authors: Zeyu Zhang, Jinyuan Mao, Shuning Chang, Yuanyu He, Yizeng Han, Jiasheng Tang, Fan Wang, Bohan Zhuang
Abstract: Long video generation is a critical step toward building realistic world models, requiring both high visual fidelity and long-range interaction consistency. Recent autoregressive diffusion models enable long-horizon generation through KV cache reuse, yet suffer from two fundamental challenges: failure to preserve long-range interactions due to sliding-window KV cache and error accumulation that progressively degrades generation quality over time. To address these issues, we propose BIFE, a framework that introduces a semantic sparse KV cache for retrieval-based long-range conditioning and a Block Forcing training strategy to enforce cross-block consistency. Together, these designs preserve historical interactions while mitigating drift, enabling stable and coherent minute-long video generation. We also introduce InterVBench, a minute-long video benchmark with fine-grained block-level annotations and Video Drift Error metrics. Extensive experiments on InterVBench and VBench-Long demonstrate that BIFE achieves state-of-the-art performance, including a 22.2% improvement on VDE-Subject and a 19.4% improvement on VDE-Clarity over baselines. Website: https://alibaba-damo-academy.github.io/BIFE. Code: https://github.com/alibaba-damo-academy/BIFE.
URLs: https://alibaba-damo-academy.github.io/BIFE., https://github.com/alibaba-damo-academy/BIFE.
Authors: Shouhe Zhang, Dayong Ren, Wen Jie Li, Piaopiao Yu, Sensen Song, Kaikai Shao, Yurong Qian
Abstract: In this paper, we challenge the conventional notion in 3DGS-SLAM that rendering quality is the primary determinant of tracking accuracy. We argue that, compared to solely pursuing a perfect scene representation, it is more critical to enhance the robustness of the rasterization process against parameter errors to ensure stable camera pose tracking. To address this challenge, we propose a novel approach that leverages a smooth kernel strategy to enhance the robustness of 3DGS-based SLAM. Unlike conventional methods that focus solely on minimizing rendering error, our core insight is to make the rasterization process more resilient to imperfections in the 3DGS parameters. We hypothesize that by allowing each Gaussian to influence a smoother, wider distribution of pixels during rendering, we can mitigate the detrimental effects of parameter noise from outlier Gaussians. This approach intentionally introduces a controlled blur to the rendered image, which acts as a regularization term, stabilizing the subsequent pose optimization. While a complete redesign of the rasterization pipeline is an ideal solution, we propose a practical and effective alternative that is readily integrated into existing 3DGS frameworks. Our method, termed Corrective Blurry KNN (CB-KNN), adaptively modifies the RGB values and locations of the K-nearest neighboring Gaussians within a local region. This dynamic adjustment generates a smoother local rendering, reducing the impact of erroneous GS parameters on the overall image. Experimental results demonstrate that our approach, while maintaining the overall quality of the scene reconstruction (mapping), significantly improves the robustness and accuracy of camera pose tracking.
Authors: Chao Gong, Depeng Wang, Zhipeng Wei, Ya Guo, Huijia Zhu, Jingjing Chen
Abstract: Audio-Visual Large Language Models (AV-LLMs) face prohibitive computational costs of processing massive, redundant audio-visual tokens. Existing unimodal compression techniques fail to capture the heterogeneous and mutually influential information density of joint audio-visual signals. Furthermore, we identify a fundamental and overlooked theoretical bottleneck in sparse token reduction: positional aliasing. We demonstrate that aggressive sparse sampling on standard position-encoded sequences violates the Nyquist limit relative to the effective token interval, causing phase-wrapping collisions that corrupt temporal monotonicity. To address this, we introduce EchoingPixels, a framework for aliasing-resistant joint token reduction. Our Cross-Modal Semantic Sieve performs extractive selection on the synergistic audio-visual stream, dynamically allocating budgets based on joint-modality saliency rather than fixed per-modality ratios. To resolve positional aliasing, we derive Sync-RoPE, a spectral low-pass filter for Rotary Positional Embeddings that adapts encoding bandwidth to the sparse sampling rate, preserving monotonic temporal relationships in the reduced stream. Experiments show that EchoingPixels achieves performance comparable to full models using only 5-20% of original tokens, validating theoretically grounded sparse learning as a robust solution for efficient AV-LLMs. Code is available at https://github.com/CharlesGong12/EchoingPixels.
Authors: Felix O'Mahony, Roberto Cipolla, Ayush Tewari
Abstract: Generative video models, a leading approach to world modelling, face fundamental limitations. They often violate physical and logical rules, lack interactivity, and operate as opaque black boxes ill-suited for building structured, queryable worlds. To overcome these challenges, we propose a new paradigm focused on distilling an image caption pair into a tractable, abstract representation optimized for simulation. We introduce VDAWorld, a framework where a Vision-Language Model (VLM) acts as an intelligent agent to orchestrate this process. The VLM autonomously constructs a grounded (2D or 3D) scene representation by selecting from a suite of vision tools, and accordingly chooses a compatible physics simulator (e.g., rigid body, fluid) to act upon it. VDAWorld can then infer latent dynamics from the static scene to predict plausible future states. Our experiments show that this combination of intelligent abstraction and adaptive simulation results in a versatile world model capable of producing high quality simulations across a wide range of scenarios. We demonstrate several applications of VDAWorld across interactive control and counterfactual generation, and physical and logical reasoning, achieving state-of-the-art results on several benchmarks.
Authors: Wentao Jiang, Vamsi Varra, Caitlin Perez-Stable, Harrison Zhu, Meredith Apicella, Nicole Nyamongo
Abstract: Accurately quantifying vitiligo extent in routine clinical photographs is crucial for longitudinal monitoring of treatment response. We propose a trustworthy, frequency-aware segmentation framework built on three synergistic pillars: (1) a data-efficient training strategy combining domain-adaptive pre-training on the ISIC 2019 dataset with an ROI-constrained dual-task loss to suppress background noise; (2) an architectural refinement via a ConvNeXt V2-based encoder enhanced with a novel High-Frequency Spectral Gating (HFSG) module and stem-skip connections to capture subtle textures; and (3) a clinical trust mechanism employing K-fold ensemble and Test-Time Augmentation (TTA) to generate pixel-wise uncertainty maps. Extensive validation on an expert-annotated clinical cohort demonstrates superior performance, achieving a Dice score of 85.05% and significantly reducing boundary error (95% Hausdorff Distance improved from 44.79 px to 29.95 px), consistently outperforming strong CNN (ResNet-50 and UNet++) and Transformer (MiT-B5) baselines. Notably, our framework demonstrates high reliability with zero catastrophic failures and provides interpretable entropy maps to identify ambiguous regions for clinician review. Our approach suggests that the proposed framework establishes a robust and reliable standard for automated vitiligo assessment.
Authors: Zhuoxiao Li, Wenzong Ma, Taoyu Wu, Jinjing Zhu, Shuai Zhang, Jing OU, Tongyan Hua, Yinrui Ren, Rongjun Qin, Hui Xiong, Wufan Zhao
Abstract: Recent advances in Neural Radiance Fields and 3D Gaussian Splatting have demonstrated strong potential for large-scale UAV-based 3D reconstruction tasks by fitting the appearance of images. However, real-world large-scale captures are often based on multi-temporal data capture, where illumination inconsistencies across different times of day can significantly lead to color artifacts, geometric inaccuracies, and inconsistent appearance. Due to the lack of UAV datasets that systematically capture the same areas under varying illumination conditions, this challenge remains largely underexplored. To fill this gap, we introduceSkyLume, a large-scale, real-world UAV dataset specifically designed for studying illumination robust 3D reconstruction in urban scene modeling: (1) We collect data from 10 urban regions data comprising more than 100k high resolution UAV images (four oblique views and nadir), where each region is captured at three periods of the day to systematically isolate illumination changes. (2) To support precise evaluation of geometry and appearance, we provide per-scene LiDAR scans and accurate 3D ground-truth for assessing depth, surface normals, and reconstruction quality under varying illumination. (3) For the inverse rendering task, we introduce the Temporal Consistency Coefficient (TCC), a metric that measuress cross-time albedo stability and directly evaluates the robustness of the disentanglement of light and material. We aim for this resource to serve as a foundation that advances research and real-world evaluation in large-scale inverse rendering, geometry reconstruction, and novel view synthesis.
Authors: Yuanhao Cai, Kunpeng Li, Menglin Jia, Jialiang Wang, Junzhe Sun, Feng Liang, Weifeng Chen, Felix Juefei-Xu, Chu Wang, Ali Thabet, Xiaoliang Dai, Xuan Ju, Alan Yuille, Ji Hou
Abstract: Recent advances in text-to-video (T2V) generation have achieved good visual quality, yet synthesizing videos that faithfully follow physical laws remains an open challenge. Existing methods mainly based on graphics or prompt extension struggle to generalize beyond simple simulated environments or learn implicit physical reasoning. The scarcity of training data with rich physics interactions and phenomena is also a problem. In this paper, we first introduce a Physics-Augmented video data construction Pipeline, PhyAugPipe, that leverages a vision-language model (VLM) with chain-of-thought reasoning to collect a large-scale training dataset, PhyVidGen-135K. Then we formulate a principled Physics-aware Groupwise Direct Preference Optimization, PhyGDPO, framework that uses real-world video as winning case to guarantee correct physics learning and builds upon the groupwise Plackett-Luce probabilistic model to capture holistic preferences beyond pairwise comparisons. In PhyGDPO, we design a Physics-Guided Rewarding (PGR) scheme that leverages VLM-based physical rewards to direct the optimization to focus on challenging physics cases. In addition, we propose a LoRA-Switch Reference (LoRA-SR) scheme that avoids full-model duplication as reference for efficient DPO training. Experiments show that our method significantly outperforms state-of-the-art open-source methods on PhyGenBench and VideoPhy2. Please check our project page at https://caiyuanhao1998.github.io/project/PhyGDPO for more video results. Our code, data, and models are publicly available at https://github.com/caiyuanhao1998/Open-PhyGDPO
URLs: https://caiyuanhao1998.github.io/project/PhyGDPO, https://github.com/caiyuanhao1998/Open-PhyGDPO
Authors: Rongji Xun, Junjie Yuan, Zhongjie Wang
Abstract: Existing film-restoration methods frequently fail under fast motion, producing limb disappearance and structural distortion due to inaccurate motion modeling. Moreover, high-resolution restoration under spatially-persistent and mixed defects remains insufficiently studied. We propose HaineiFRDM, a Film Restoration Diffusion Model that leverages the content modeling capability of diffusion models for content-aware restoration, removing defects while preserving scene structure.To enable scalable high-resolution restoration, we adopt a patch-wise strategy with position-aware global fusion modules to maintain cross-patch coherence. We further introduce a frequency-based module to enhance texture consistency and a patch-consistent inference framework to alleviate blocking artifacts introduced by patch-based processing.We also construct a film restoration dataset comprising categorized defect templates, professionally restored films, and realistic synthetic degradations.Extensive experiments demonstrate our superior restoration quality with strong structural consistency. Our design also reduces memory requirements, enabling high-resolution restoration on a single 24GB-VRAM GPU.Code and the dataset will be released at https://anonymous.4open.science/r/HaineiFRDM.
Authors: Yingyan Xu, Pramod Rao, Sebastian Weiss, Gaspard Zoss, Markus Gross, Christian Theobalt, Marc Habermann, Derek Bradley
Abstract: 3D Gaussian Splatting (3DGS) has become a standard approach to reconstruct and render photorealistic 3D head avatars. A major challenge is to relight the avatars to match any scene illumination. For high quality relighting, existing methods require subjects to be captured under complex time-multiplexed illumination, such as one-light-at-a-time (OLAT). We propose a new generalized relightable 3D Gaussian head model that can relight any subject observed in a single- or multi-view images without requiring OLAT data for that subject. Our core idea is to learn a mapping from flat-lit 3DGS avatars to corresponding relightable Gaussian parameters for that avatar. Our model consists of two stages: a first stage that models flat-lit 3DGS avatars without OLAT lighting, and a second stage that learns the mapping to physically-based reflectance parameters for high-quality relighting. This two-stage design allows us to train the first stage across diverse existing multi-view datasets without OLAT lighting ensuring cross-subject generalization, where we learn a dataset-specific lighting code for self-supervised lighting alignment. Subsequently, the second stage can be trained on a significantly smaller dataset of subjects captured under OLAT illumination. Together, this allows our method to generalize well and relight any subject from the first stage as if we had captured them under OLAT lighting. Furthermore, we can fit our model to unseen subjects from as little as a single image, allowing several applications in novel view synthesis and relighting for digital avatars.
Authors: Ali Kurban, Wei Luo, Liangyu Zuo, Zeyu Zhang, Renda Han, Zhaolu Kang, Hao Tang, Yang Zhao
Abstract: Cryptocurrency trading increasingly depends on timely integration of heterogeneous web information and market microstructure signals to support short-horizon decision making under extreme volatility. However, existing trading systems struggle to jointly reason over noisy multi-source web evidence while maintaining robustness to rapid price shocks at sub-second timescales. The first challenge lies in synthesizing unstructured web content, social sentiment, and structured OHLCV signals into coherent and interpretable trading decisions without amplifying spurious correlations, while the second challenge concerns risk control, as slow deliberative reasoning pipelines are ill-suited for handling abrupt market shocks that require immediate defensive responses. To address these challenges, we propose WebCryptoAgent, an agentic trading framework that decomposes web-informed decision making into modality-specific agents and consolidates their outputs into a unified evidence document for confidence-calibrated reasoning. We further introduce a decoupled control architecture that separates strategic hourly reasoning from a real-time second-level risk model, enabling fast shock detection and protective intervention independent of the trading loop. Extensive experiments on real-world cryptocurrency markets demonstrate that WebCryptoAgent improves trading stability, reduces spurious activity, and enhances tail-risk handling compared to existing baselines. Code will be available at https://github.com/AIGeeksGroup/WebCryptoAgent.
Authors: Jianghao Yin, Qingbin Li, Kun Sun, Cheng Ding, Jie Wang, Qin Chen, Jie Zhou, Nan Wang, Changqing Li, Pei Wu, Jian Xu, Zheming Yang, Liang He
Abstract: While Multimodal Large Language Models (MLLMs) excel at single-image understanding, they exhibit significantly degraded performance in multi-image reasoning scenarios. Multi-image reasoning presents fundamental challenges including complex inter-relationships between images and scattered critical information across image sets. Inspired by human cognitive processes, we propose a Cognition-Inspired Meta-Action Framework (CINEMA), which decomposes multi-image reasoning into five structured meta-actions: Global, Focus, Hint, Think, and Answer, explicitly modeling the sequential cognitive steps humans naturally employ. For cold-start training, we introduce a Retrieval-Based Tree Sampling strategy that generates high-quality meta-action trajectories to bootstrap the model with reasoning patterns. During reinforcement learning, we adopt a two-stage paradigm: an exploration phase with Diversity-Preserving Strategy to avoid entropy collapse, followed by an annealed exploitation phase with DAPO to gradually strengthen exploitation. To train our model, we construct a dataset of 56k cold-start and 58k reinforcement learning instances spanning multi-image, multi-frame, and single-image tasks. We conduct extensive evaluations on multi-image reasoning benchmarks, video understanding benchmarks, and single-image benchmarks, achieving competitive state-of-the-art performance on several key benchmarks. Our model surpasses GPT-4o on the MUIR and MVMath benchmarks and notably outperforms specialized video reasoning models on video understanding benchmarks, demonstrating the effectiveness and generalizability of our human cognition-inspired reasoning framework.
Authors: Ziyi Wu, Daniel Watson, Andrea Tagliasacchi, David J. Fleet, Marcus A. Brubaker, Saurabh Saxena
Abstract: Lifting perspective images and videos to 360{\deg} panoramas enables immersive 3D world generation. Existing approaches often rely on explicit geometric alignment between the perspective and the equirectangular projection (ERP) space. Yet, this requires known camera metadata, obscuring the application to in-the-wild data where such calibration is typically absent or noisy. We propose 360Anything, a geometry-free framework built upon pre-trained diffusion transformers. By treating the perspective input and the panorama target simply as token sequences, 360Anything learns the perspective-to-equirectangular mapping in a purely data-driven way, eliminating the need for camera information. Our approach achieves state-of-the-art performance on both image and video perspective-to-360{\deg} generation, outperforming prior works that use ground-truth camera information. We also trace the root cause of the seam artifacts at ERP boundaries to zero-padding in the VAE encoder, and introduce Circular Latent Encoding to facilitate seamless generation. Finally, we show competitive results in zero-shot camera FoV and orientation estimation benchmarks, demonstrating 360Anything's deep geometric understanding and broader utility in computer vision tasks. Additional results are available at https://360anything.github.io/.
Authors: Minh-Quan Le, Gaurav Mittal, Cheng Zhao, David Gu, Dimitris Samaras, Mei Chen
Abstract: Text-to-video (T2V) generation aims to synthesize videos with high visual quality and temporal consistency that are semantically aligned with input text. Reward-based post-training has emerged as a promising direction to improve the quality and semantic alignment of generated videos. However, recent methods either rely on large-scale human preference annotations or operate on misaligned embeddings from pre-trained vision-language models, leading to limited scalability or suboptimal supervision. We present $\texttt{PISCES}$, an annotation-free post-training algorithm that addresses these limitations via a novel Dual Optimal Transport (OT)-aligned Rewards module. To align reward signals with human judgment, $\texttt{PISCES}$ uses OT to bridge text and video embeddings at both distributional and discrete token levels, enabling reward supervision to fulfill two objectives: (i) a Distributional OT-aligned Quality Reward that captures overall visual quality and temporal coherence; and (ii) a Discrete Token-level OT-aligned Semantic Reward that enforces semantic, spatio-temporal correspondence between text and video tokens. To our knowledge, $\texttt{PISCES}$ is the first to improve annotation-free reward supervision in generative post-training through the lens of OT. Experiments on both short- and long-video generation show that $\texttt{PISCES}$ outperforms both annotation-based and annotation-free methods on VBench across Quality and Semantic scores, with human preference studies further validating its effectiveness. We show that the Dual OT-aligned Rewards module is compatible with multiple optimization paradigms, including direct backpropagation and reinforcement learning fine-tuning. Project page: https://roar-ai.github.io/pisces
Authors: Yijia Xu, Zihao Wang, Haokun Gui, Jinshi Cui
Abstract: Multi-subject image generation aims to synthesize images that faithfully preserve the identities of multiple reference subjects while following textual instructions. However, existing methods often suffer from identity inconsistency and limited compositional control, as they rely on diffusion models to implicitly associate text prompts with reference images. In this work, we propose Hierarchical Concept-to-Appearance Guidance (CAG), a framework that provides explicit, structured supervision from high-level concepts to fine-grained appearances. At the conceptual level, we introduce a VAE dropout training strategy that randomly omits reference VAE features, encouraging the model to rely more on robust semantic signals from a Visual Language Model (VLM) and thereby promoting consistent concept-level generation in the absence of complete appearance cues. At the appearance level, we integrate the VLM-derived correspondences into a correspondence-aware masked attention module within the Diffusion Transformer (DiT). This module restricts each text token to attend only to its matched reference regions, ensuring precise attribute binding and reliable multi-subject composition. Extensive experiments demonstrate that our method achieves state-of-the-art performance on the multi-subject image generation, substantially improving prompt following and subject consistency.
Authors: Yuantao Chen, Jiahao Chang, Chongjie Ye, Chaoran Zhang, Zhaojie Fang, Chenghong Li, Xiaoguang Han
Abstract: The ubiquity of monocular videos capturing daily hand-object interactions presents a valuable resource for embodied intelligence. While 3D hand reconstruction from in-the-wild videos has seen significant progress, reconstructing the involved objects remains challenging due to severe occlusions and the complex, coupled motion of the camera, hands, and object. In this paper, we introduce ForeHOI, a novel feed-forward model that directly reconstructs 3D object geometry from monocular hand-object interaction videos within one minute of inference time, eliminating the need for any pre-processing steps. Our key insight is that, the joint prediction of 2D mask inpainting and 3D shape completion in a feed-forward framework can effectively address the problem of severe occlusion in monocular hand-held object videos, thereby achieving results that outperform the performance of optimization-based methods. The information exchanges between the 2D and 3D shape completion boosts the overall reconstruction quality, enabling the framework to effectively handle severe hand-object occlusion. Furthermore, to support the training of our model, we contribute the first large-scale, high-fidelity synthetic dataset of hand-object interactions with comprehensive annotations. Extensive experiments demonstrate that ForeHOI achieves state-of-the-art performance in object reconstruction, significantly outperforming previous methods with around a 100x speedup. Code and data are available at: https://github.com/Tao-11-chen/ForeHOI.
Authors: Jindong Li, Dario Zanca, Vincent Christlein, Tim Hamann, Jens Barth, Peter K\"ampf, Bj\"orn Eskofier
Abstract: Online handwriting recognition using inertial measurement units opens up handwriting on paper as input for digital devices. Doing it on edge hardware improves privacy and lowers latency, but entails memory constraints. To address this, we propose Error-enhanced Contrastive Handwriting Recognition (ECHWR), a training framework designed to improve feature representation and recognition accuracy without increasing inference costs. ECHWR utilizes a temporary auxiliary branch that aligns sensor signals with semantic text embeddings during the training phase. This alignment is maintained through a dual contrastive objective: an in-batch contrastive loss for general modality alignment and a novel error-based contrastive loss that distinguishes between correct signals and synthetic hard negatives. The auxiliary branch is discarded after training, which allows the deployed model to keep its original, efficient architecture. Evaluations on the OnHW-Words500 dataset show that ECHWR significantly outperforms state-of-the-art baselines, reducing character error rates by up to 7.4% on the writer-independent split and 10.4% on the writer-dependent split. Finally, although our ablation studies indicate that solving specific challenges require specific architectural and objective configurations, error-based contrastive loss shows its effectiveness for handling unseen writing styles.
Authors: Hua Xu, Juli\'an D. Arias-Londo\~no, Juan I. Godino-Llorente
Abstract: In critical decision support systems based on medical imaging, the reliability of AI-assisted decision-making is as relevant as predictive accuracy. Although deep learning models have demonstrated significant accuracy, they frequently suffer from miscalibration, manifested as overconfidence in erroneous predictions. To facilitate clinical acceptance, it is imperative that models quantify uncertainty in a manner that correlates with prediction correctness, allowing clinicians to identify unreliable outputs for further review. To address this necessity, this paper proposes a probabilistic optimization framework grounded in Bayesian deep learning. Specifically, the Confidence-Uncertainty Boundary Curve (CUBC) is first explored as an intermediate operational target. Grounded in this target, a novel Confidence-Uncertainty Boundary Loss (CUB-Loss) is proposed to regularize the alignment between prediction confidence and uncertainty estimates during training, imposing penalties on high-certainty errors and low-certainty correct predictions. Upon completion of training optimization, a Boundary Curve Calibration Error (BCCE) metric is further introduced to measure the degree of boundary alignment in the calibrated model. Building on this measurement, a Dual Temperature Scaling (DTS) strategy is devised to perform post-hoc refinement, further adjusting the posterior predictive distribution across different confidence-uncertainty regions. The proposed framework is validated on three distinct medical imaging tasks: automatic screening of pneumonia, diabetic retinopathy detection, and identification of skin lesions. Empirical results demonstrate that the proposed approach improves uncertainty calibration across diverse modalities, maintains robust performance in data-scarce scenarios, and remains effective on severely imbalanced datasets, underscoring its potential for real clinical deployment.
Authors: Lidia Garrucho, Smriti Joshi, Kaisar Kushibar, Richard Osuala, Maciej Bobowicz, Xavier Bargall\'o, Paulius Jaru\v{s}evi\v{c}ius, Kai Geissler, Raphael Sch\"afer, Muhammad Alberb, Tony Xu, Anne Martel, Daniel Sleiman, Navchetan Awasthi, Hadeel Awwad, Joan C. Vilanova, Robert Mart\'i, Daan Schouten, Jeong Hoon Lee, Mirabela Rusu, Eleonora Poeta, Luisa Vargas, Eliana Pastor, Maria A. Zuluaga, Jessica K\"achele, Dimitrios Bounias, Alexandra Ertl, Katarzyna Gwo\'zdziewicz, Maria-Laura Cosaka, Pasant M. Abo-Elhoda, Sara W. Tantawy, Shorouq S. Sakrana, Norhan O. Shawky-Abdelfatah, Amr Muhammad Abdo-Salem, Androniki Kozana, Eugen Divjak, Gordana Ivanac, Katerina Nikiforaki, Michail E. Klontzas, Rosa Garc\'ia-Dosd\'a, Meltem Gulsun-Akpinar, O\u{g}uz Lafc{\i}, Carlos Mart\'in-Isla, Oliver D\'iaz, Laura Igual, Karim Lekadir
Abstract: Breast cancer is the most frequently diagnosed malignancy among women worldwide and a leading cause of cancer-related mortality. Dynamic contrast-enhanced magnetic resonance imaging plays a central role in tumor characterization and treatment monitoring, particularly in patients receiving neoadjuvant chemotherapy. However, existing artificial intelligence models for breast magnetic resonance imaging are typically developed and evaluated using heterogeneous datasets, study populations, and assessment protocols, making direct comparison difficult and limiting understanding of model robustness across institutions and clinically relevant patient subgroups. The MAMA-MIA Challenge was designed to address these challenges by providing a standardized benchmark for the joint evaluation of primary tumor segmentation and prediction of pathologic complete response using pre-treatment magnetic resonance imaging only. The training cohort comprised 1,506 patients from multiple institutions in the United States, while evaluation was conducted on an external test set of 574 patients from three independent European centers to assess cross-continental and cross-institutional generalization. A unified scoring framework combined predictive performance with subgroup consistency across age, menopausal status, and breast density. Twenty-six international teams participated in the final evaluation phase. Results demonstrate substantial performance variability under a common external evaluation framework and reveal trade-offs between overall accuracy and subgroup fairness. The challenge provides standardized datasets, evaluation protocols, and public resources to promote the development of robust and equitable artificial intelligence systems for breast cancer imaging.
Authors: Phillip Howard, Xin Su, Kathleen C. Fraser
Abstract: Large Vision-Language Models (LVLMs) have grown increasingly powerful in recent years, but can also exhibit harmful biases. Prior studies investigating such biases have primarily focused on demographic traits related to the visual characteristics of a person depicted in an image, such as their race or gender. This has left biases related to cultural differences (e.g., religion, socioeconomic status), which cannot be readily discerned from an individual's appearance alone, relatively understudied. A key challenge in measuring cultural biases is that determining which group an individual belongs to often depends upon cultural context cues in images, and datasets annotated with cultural context cues are lacking. To address this gap, we introduce Cultural Counterfactuals: a high-quality synthetic dataset containing nearly 60k counterfactual images for measuring cultural biases related to religion, nationality, and socioeconomic status. To ensure that cultural contexts are accurately depicted, we generate our dataset using an image-editing model to place people of different demographics into real cultural context images. This enables the construction of counterfactual image sets which depict the same person in multiple different contexts, allowing for precise measurement of the impact that cultural context differences have on LVLM outputs. We demonstrate the utility of Cultural Counterfactuals for quantifying cultural biases in popular LVLMs.
Authors: Changda Zhou, Ziyue Gao, Xueqing Wang, Tingquan Gao, Cheng Cui, Jing Tang, Yi Liu
Abstract: While Vision-Language Models (VLMs) achieve near-perfect scores on digital document benchmarks like OmniDocBench, their performance in the unpredictable physical world remains largely unknown due to the lack of controlled yet realistic evaluations. We introduce Real5-OmniDocBench, the first benchmark that performs a full-scale, one-to-one physical reconstruction of the entire OmniDocBench v1.5 (1,355 images) across five critical real-world scenarios: Scanning, Warping, Screen-Photography, Illumination, and Skew. Unlike prior benchmark that either lack digital correspondence or employ partial sampling, our complete ground-truth mapping enables, for the first time, rigorous factor-wise attribution of performance degradation-allowing us to pinpoint whether failures stem from geometric distortions, optical artifacts, or model limitations. Our benchmark establishes a challenging new standard for the community, demonstrating that the 'reality gap' in document parsing is far from closed, and provides a diagnostic tool to guide the development of truly resilient document intelligence.
Authors: Jiaqi Li, Shuntian Zheng, Yixian Shen, Jia-Hong Huang, Xiaoman Lu, Minzhe Ni, Yu Guan
Abstract: Video Temporal Grounding (VTG) localizes the temporal boundaries of query-relevant moments in long videos, making video-language-model prohibitively expensive. While recent training-free token pruning has shown success in video question answering, naively applying these objectives to VTG causes drastic degradation, as VTG crucially depends on boundary-sensitive evidence and cross-frame reasoning chains. We therefore identify two VTG-specific pruning principles: evidence retention, which keeps query-critical patches, and connectivity strength, which preserves cross-frame connectivity for long-range evidence aggregation. We propose SemVID, a training-free pruning framework that constructs a compact yet coherent token subset with complementary semantic roles. SemVID first allocates per-frame budgets by balancing query relevance and inter-frame variation to avoid over-pruned segments, and then selects three types of tokens: object tokens for diverse query-critical evidence, motion tokens to capture transitions and serve as cross-frame relays, and context tokens for scene continuity. Extensive experiments show that SemVID achieves a strong accuracy-efficiency trade-off, retaining up to 95.4% mIoU with only 12.5% visual tokens and delivering up to a 5.8x prefill speedup. Our code is available at https://github.com/JiaqiLi404/SemVID
Authors: Siyuan Yang, Jun Liu, Hao Cheng, Chong Wang, Shijian Lu, Hedvig Kjellstrom, Weisi Lin, Alex C. Kot
Abstract: Recent advances in large-scale pretrained vision models have demonstrated impressive capabilities across a wide range of downstream tasks, including cross-modal and multi-modal scenarios. However, their direct application to 3D human skeleton data remains challenging due to fundamental differences in data format. Moreover, the scarcity of large-scale skeleton datasets and the need to incorporate skeleton data into multi-modal action recognition without introducing additional model branches present significant research opportunities. To address these challenges, we introduce Skeleton-to-Image Encoding (S2I), a novel representation that transforms skeleton sequences into image-like data by partitioning and arranging joints based on body-part semantics and resizing to standardized image dimensions. This encoding enables, for the first time, the use of powerful vision-pretrained models for self-supervised skeleton representation learning, effectively transferring rich visual-domain knowledge to skeleton analysis. While existing skeleton methods often design models tailored to specific, homogeneous skeleton formats, they overlook the structural heterogeneity that naturally arises from diverse data sources. In contrast, our S2I representation offers a unified image-like format that naturally accommodates heterogeneous skeleton data. Extensive experiments on NTU-60, NTU-120, and PKU-MMD demonstrate the effectiveness and generalizability of our method for self-supervised skeleton representation learning, including under challenging cross-format evaluation settings.
Authors: Ruiping Liu, Yufan Chen, Yuheng Zhang, Junwei Zheng, Kunyu Peng, Chengzhi Wu, Chenguang Huang, Di Wen, Jiaming Zhang, Kailun Yang, Rainer Stiefelhagen
Abstract: Situated reasoning often relies on active exploration, yet in many real-world scenarios such exploration is infeasible due to physical constraints of robots or safety concerns of visually impaired users. Given only a limited observation, can an agent mentally simulate a future trajectory toward a target situation and answer spatial what-if questions? We introduce WanderDream, the first large-scale dataset designed for the emulative simulation of mental exploration, enabling models to reason without active exploration. WanderDream-Gen comprises 15.8K panoramic videos across 1,088 real scenes from HM3D, ScanNet++, and real-world captures, depicting imagined trajectories from current viewpoints to target situations. WanderDream-QA contains 158K question-answer pairs, covering starting states, paths, and end states along each trajectory to comprehensively evaluate exploration-based reasoning. Extensive experiments with world models and MLLMs demonstrate (1) that mental exploration is essential for situated reasoning, (2) that world models achieve compelling performance on WanderDream-Gen, (3) that imagination substantially facilitates reasoning on WanderDream-QA, and (4) that WanderDream data exhibit remarkable transferability to real-world scenarios.
Authors: Yingtai Li, Shuai Ming, Qiuli Wang, Mingyue Zhao, Hongchun Zhang, Yuhe Tian, Haoran Lai, Rongsheng Wang, Rui Zhou, Rundong Wang, Yujia Li, Zhiyang He, Xiaodong Tao, Wei Chen, Wei Wei, Shaohua Kevin Zhou
Abstract: Radiology foundation models (RFMs) have largely inherited the scale-first recipe of natural-image vision--language pre-training. This recipe is difficult to deploy in 3D radiology, where training corpora are smaller, reports vary across institutions, and receiving hospitals often need local adaptation under privacy and compute constraints. We ask whether routine radiology reports can instead be converted into auditable diagnostic supervision that shapes the image encoder, text encoder, aligned space, and local-adaptation procedure. We develop GreenRFM, a supervision-centric pre-training framework organized around four empirical principles: More distilled, Ubiquitous, Semantic-enforcing, and Task-aligning (MUST) supervision. These principles convert noisy reports into structured diagnostic signals and use them to learn discriminative unimodal encoders plus an aligned image--text space for diagnosis-centered multimodal use. GreenRFM requires 24 GPU-hours on a single 24GB GPU (lightweight variant: 6GB VRAM, 4~hours) and reaches a zero-shot CT-RATE AUC of 84.8. Evaluations using more than 200,000 volumes from six institutions and two modalities show transfer to private clinical cohorts and to musculoskeletal MRI. On a local institutional cohort, computationally feasible retraining raises macro-AUC from 70.5 to 82.1. The aligned space also improves hepatocellular-carcinoma microvascular-invasion prediction and trans-arterial chemoembolization response analysis over established clinical scores. These results support supervision-centric pre-training as a practical route to resource-efficient, locally adaptable, diagnosis-centered radiology vision--language representations.
Authors: Duy M. H. Nguyen, Tuan A. Tran, Duong Nguyen, Siwei Xie, Trung Q. Nguyen, Mai T. N. Truong, Daniel Palenicek, An T. Le, Michael Barz, TrungTin Nguyen, Tuan Dam, Ngan Le, Minh Vu, Khoa Doan, Vien Ngo, Pengtao Xie, James Zou, Daniel Sonntag, Jan Peters, Mathias Niepert
Abstract: Recent token merging techniques for Vision Transformers (ViTs) provide substantial speedups by reducing the number of tokens processed by self-attention, often without retraining. However, their direct application to the Segment Anything Model (SAM) family is nontrivial: SAM's image encoder mixes windowed and global attention, and its mask decoder relies on dense, prompt-conditioned features for precise boundary prediction. We systematically evaluate representative token-merging methods on SAM and Medical SAM in a strict off-the-shelf setting, and find that existing destination-selection heuristics can erode boundaries and leak prompt information as merge rates increase. We propose \textbf{StructSAM}, a resolution-preserving merge-unmerge framework tailored to SAM. StructSAM computes a lightweight token-energy score from first-order feature gradients, uses grid-based flatness screening to protect boundary and prompt regions, and merges tokens within flat areas toward low-energy destinations with explicit token recovery. We further provide a spectral graph coarsening view showing that score-guided merging yields bounded Laplacian spectral distortion compared to random or window-restricted baselines. Across eight natural and medical benchmarks, StructSAM reduces encoder FLOPs by 25-30\% (up to 40\%+ with prompt-aware merging) with minor drops in mIoU/Dice, consistently outperforming ToMe, PiToMe, ToMeSD, VidToMe, and ALGM at the same compute.
Authors: Zhisong Xu, Takeshi Oishi
Abstract: Streaming Visual Geometry Transformers such as StreamVGGT enable strong online 3D perception, but their KV-cache grows unbounded over long streams, limiting practical deployment. We study bounded-memory streaming geometry from the perspective of memory organization: unlike language modeling, where useful information can often be compressed at token level, geometry-driven inference relies on coherent and mutually compatible observations across views. Under fixed memory budgets, retaining history as isolated entries can progressively fragment the geometric context needed for stable long-horizon matching and fusion. We therefore propose \textbf{FrameVGGT}, a bounded-memory framework that maintains a fixed-capacity set of complementary memory units for streaming geometry. In our implementation, each unit is instantiated as a frame-wise KV segment summarized by a compact key-space prototype, together with a sparse anchor tier for persistent long-range references. Across long-sequence 3D reconstruction, video depth estimation, and camera pose estimation, FrameVGGT achieves favorable accuracy--memory trade-offs under bounded budgets while maintaining more stable geometry over long streams.
Authors: Daniele Molino, Camillo Maria Caruso, Paolo Soda, Valerio Guarrasi
Abstract: Text-conditioned generative models for volumetric medical imaging provide semantic control but lack explicit anatomical guidance, often resulting in outputs that are spatially ambiguous or anatomically inconsistent. In contrast, structure-driven methods ensure strong anatomical consistency but typically assume access to ground-truth annotations, which are unavailable when the target image is to be synthesized. We propose a retrieval-augmented approach for Text-to-CT generation that integrates semantic and anatomical information under a realistic inference setting. Given a radiology report, our method retrieves a semantically related clinical case using a 3D vision-language encoder and leverages its associated anatomical annotation as a structural proxy. This proxy is injected into a text-conditioned latent diffusion model via a ControlNet branch, providing coarse anatomical guidance while maintaining semantic flexibility. Experiments on the CT-RATE dataset show that retrieval-augmented generation improves image fidelity and clinical consistency compared to text-only baselines, while additionally enabling explicit spatial controllability, a capability inherently absent in such approaches. Further analysis highlights the importance of retrieval quality, with semantically aligned proxies yielding consistent gains across all evaluation axes. This work introduces a principled and scalable mechanism to bridge semantic conditioning and anatomical plausibility in volumetric medical image synthesis. Code is available at https://github.com/arco-group/RAGText2CT.
Authors: Xinyu Tong, Meihua Zhou, Bowu Fan, Haitao Li
Abstract: Multimodal medical image segmentation often faces missing modalities at inference, which induces disagreement among modality experts and makes fusion unstable, particularly on small foreground structures. We propose Consistency Learning of Experts (CLoE), a consistency-driven framework for missing-modality segmentation that preserves strong performance when all modalities are available. CLoE formulates robustness as decision-level expert consistency control and introduces a dual-branch Expert Consistency Learning objective. Modality Expert Consistency enforces global agreement among expert predictions to reduce case-wise drift under partial inputs, while Region Expert Consistency emphasizes agreement on clinically critical foreground regions to avoid background-dominated regularization. We further map consistency scores to modality reliability weights using a lightweight gating network, enabling reliability-aware feature recalibration before fusion. Extensive experiments on BraTS 2020 and MSD Prostate demonstrate that CLoE outperforms state-of-the-art methods in incomplete multimodal segmentation, while exhibiting strong cross-dataset generalization and improving robustness on clinically critical structures.
Authors: Tongkun Guan, Zhibo Yang, Jianqiang Wan, Mingkun Yang, Zhengtao Guo, Zijian Hu, Ruilin Luo, Ruize Chen, Songtao Jiang, Peng Wang, Wei Shen, Junyang Lin, Xiaokang Yang
Abstract: When MLLMs fail at Science, Technology, Engineering, and Mathematics (STEM) visual reasoning, a fundamental question arises: is it due to perceptual deficiencies or reasoning limitations? Through systematic scaling analysis that independently scales perception and reasoning components, we uncover a critical insight: scaling perception consistently outperforms scaling reasoning. This reveals perception as the true lever limiting current STEM visual reasoning. Motivated by this insight, our work focuses on systematically enhancing the perception capabilities of MLLMs by establishing code as a powerful perceptual medium--executable code provides precise semantics that naturally align with the structured nature of STEM visuals. Specifically, we construct ICC-1M, a large-scale dataset comprising 1M Image-Caption-Code triplets that materializes this code-as-perception paradigm through two complementary approaches: (1) Code-Grounded Caption Generation treats executable code as ground truth for image captions, eliminating the hallucinations inherent in existing knowledge distillation methods; (2) STEM Image-to-Code Translation prompts models to generate reconstruction code, mitigating the ambiguity of natural language for perception enhancement. To validate this paradigm, we further introduce STEM2Code-Eval, a novel benchmark that directly evaluates visual perception in STEM domains. Unlike existing work relying on problem-solving accuracy as a proxy that only measures problem-relevant understanding, our benchmark requires comprehensive visual comprehension through executable code generation for image reconstruction, providing deterministic and verifiable assessment. Code is available at https://github.com/TongkunGuan/Qwen-CodePercept.
Authors: Pietro Bonazzi, Nicola Farronato, Stefan Zihlmann, Haotong Qin, Michele Magno
Abstract: Real-time, on-device segmentation is critical for latency-sensitive and privacy-aware applications such as smart glasses and Internet-of-Things devices. We introduce PicoSAM3, a lightweight promptable visual segmentation model optimized for edge and in-sensor execution, including deployment on the Sony IMX500 vision sensor. PicoSAM3 has 1.3M parameters and combines a dense CNN architecture with region of interest prompt encoding, Efficient Channel Attention, and knowledge distillation from SAM2 and SAM3. On COCO and LVIS, PicoSAM3 achieves 65.45% and 64.01% mIoU, respectively, outperforming existing SAM-based and edge-oriented baselines at similar or lower complexity. The INT8 quantized model preserves accuracy with negligible degradation while enabling real-time in-sensor inference at 11.82ms latency on the IMX500, fully complying with its memory and operator constraints. Ablation studies show that distillation from large SAM models yields up to +14.5% mIoU improvement over supervised training and demonstrate that high-quality, spatially flexible promptable segmentation is feasible directly at the sensor level.
Authors: Wen Yan, Yipei Wang, Shiqi Huang, Natasha Thorley, Mark Emberton, Vasilis Stavrinides, Yipeng Hu, Dean Barratt
Abstract: Label variability is a major challenge for prostate lesion segmentation. In multi-site datasets, annotations often reflect centre-specific contouring protocols, causing segmentation networks to overfit to local styles and generalise poorly to unseen sites in inference. We treat each observed annotation as a noisy observation of an underlying latent 'clean' lesion mask, and propose a hierarchical expectation-maximisation (HierEM) framework that alternates between: (1) inferring a voxel-wise posterior distribution over the latent mask, and (2) training a CNN using this posterior as a soft target and estimate site-specific sensitivity and specificity under a hierarchical prior. This hierarchical prior decomposes label-quality into a global mean with site- and case-level deviations, reducing site-specific bias by penalising the likelihood term contributed only by site deviations. Experiments on three cohorts demonstrate that the proposed hierarchical EM framework enhances cross-site generalisation compared to state-of-the-art methods. For pooled-dataset evaluation, the per-site mean DSC ranges from 29.50% to 39.69%; for leave-one-site-out generalisation, it ranges from 27.91% to 32.67%, yielding statistically significant improvements over comparison methods (p<0.039). The method also produces interpretable per-site latent label-quality estimates (sensitivity alpha ranges from 31.5% to 47.3% at specificity beta approximates 0.99), supporting post-hoc analyses of cross-site annotation variability. These results indicate that explicitly modelling site-dependent annotation can improve cross-site generalisation.
Authors: Yifan Yang, Lei Zou, Wenjing Gong, Kani Fu, Zongrong Li, Siqin Wang, Bing Zhou, Heng Cai, Hao Tian
Abstract: Analyzing street-view imagery with computer vision models offers a promising approach for rapid, hyperlocal disaster damage assessment, but existing approaches typically rely on black-box pre-trained vision models, which lack interpretability and reliability. This study proposes DamageArbiter, a multimodal disagreement-driven arbitration framework designed to improve the accuracy and reliability of street-view-based damage assessment. DamageArbiter leverages the complementary strengths of unimodal and multimodal models and employs a lightweight logistic regression meta-classifier to arbitrate cases in which model predictions disagree. Using 2,556 post-disaster street-view images, paired with manually generated or large language model (LLM)-generated text descriptions, we systematically compared DamageArbiter with fine-tuned unimodal (image-only and text-only) models and CLIP-based multimodal models in terms of classification performance and overconfidence errors. Results show that DamageArbiter improved accuracy to 75.85% and the Matthews correlation coefficient (MCC) to 0.6188, compared with the best-performing text-only baseline (63.07% accuracy, 0.4126 MCC), image-only baseline (74.33% accuracy, 0.5947 MCC), and CLIP baseline (74.22% accuracy, 0.5915 MCC). The overconfidence analysis further reveals that DamageArbiter substantially reduced the overconfidence error from 70.58% for the best-performing baseline, the image-only ViT model, to 16.45%. Overall, this study demonstrates that accuracy alone is insufficient for evaluating disaster damage classification models and highlights the importance of measuring overconfidence errors as part of model reliability assessment. DamageArbiter thus offers a more reliable framework for rapid, hyperlocal disaster damage assessment from street-view imagery.
Authors: Jingyu Guo, Ziye Chen, Ziwen Li, Zhengqing Gao, Jiaxin Huang, Hanlue Zhang, Fengming Huang, Yu Yao, Tongliang Liu, Mingming Gong
Abstract: Existing UAV vision-language navigation (VLN) benchmarks have enabled language-guided flight, but they largely focus on long, step-wise route descriptions with goal-centric evaluation, making them less diagnostic for real operations where brief, high-level commands must be grounded into safe multi-stage behaviors. We present HUGE-Bench, a benchmark for High-Level UAV Vision-Language-Action (HL-VLA) tasks that tests whether an agent can interpret concise language and execute complex, process-oriented trajectories with safety awareness. HUGE-Bench comprises 4 real-world digital twin scenes, 8 high-level tasks, and 2.56M meters of trajectories, and is built on an aligned 3D Gaussian Splatting (3DGS)-Mesh representation that combines photorealistic rendering with collision-capable geometry for scalable generation and collision-aware evaluation. We introduce process-oriented and collision-aware metrics to assess process fidelity, terminal accuracy, and safety. Experiments on representative state-of-the-art VLA models reveal significant gaps in high-level semantic completion and safe execution, highlighting HUGE-Bench as a diagnostic testbed for high-level UAV autonomy.
Authors: Kaizhen Tan, Yang Feng, Heqing Du
Abstract: Standard attribution heatmaps show where a vision-language model (VLM) focuses, but they do not reveal whether the recovered evidence is organized by the queried spatial relation or merely reflects image layout. To address this problem, we introduce CREG (Compass Relational Evidence Graph), a training-free diagnostic framework that converts token-level attribution into a reference-centered compass distribution and measures its directional alignment. CREG provides a shared directional readout across attribution methods and makes comparison with geometric controls explicit. Across three spatial-relation benchmarks, box-only geometry achieves Direction Alignment Error 28.4 to 34.4 degrees lower than the best current model-based attribution method on each dataset, leaving a substantial gap between attribution structure and simple target localization. To examine this gap, we apply a diagnostic battery including target intervention, reference-center randomization, and variance partition. Taken together, the results suggest that the directional structure recoverable from current attribution methods is limited and often mixed with image layout. We further find that higher task accuracy does not reliably coincide with better directional attribution: small-scale LoRA training and newer model generations can improve task accuracy while leaving Direction Alignment Error unchanged or worse. These findings characterize what current attribution methods reveal rather than the model's internal spatial representation. CREG provides a controlled protocol for testing whether improvements in spatial reasoning are accompanied by more directionally organized evidence.
Authors: Chedly Ben Azizi, Claire Guilloteau, Gilles Roussel, Matthieu Puigt
Abstract: Synthetic hyperspectral image (HSI) generation is essential for large-scale simulation, algorithm development, and mission design, yet traditional radiative transfer models remain computationally expensive and proposed emulation methods are often limited to spectrum-level outputs. In this work, we propose a latent representation-based framework for hyperspectral emulation that learns a probabilistic latent representation of hyperspectral data. The proposed approach supports both spectrum-level and spatial-spectral emulation and can be trained either in a direct one-step formulation or in a two-step strategy that couples variational autoencoder (VAE) pretraining with parameter-to-latent mapping. Experiments on PROSAIL-simulated vegetation data and Sentinel-3 OLCI imagery demonstrate that the method outperforms classical regression-based emulators in reconstruction accuracy, spectral fidelity, and robustness to real-world spatial variability. We further show that emulated HSIs preserve performance in downstream biophysical parameter retrieval, highlighting the practical relevance of emulated data for remote sensing applications.
Authors: Pengpeng Yu, Haoran Li, Runqing Jiang, Dingquan Li, Jing Wang, Liang Lin, Yulan Guo
Abstract: LiDAR point clouds are fundamental to various applications, yet the extreme sparsity of high-precision geometric details hinders efficient context modeling, thereby limiting the compression speed and performance of existing methods. To address this challenge, we propose a compact representation for efficient predictive lossless coding. Our framework comprises two lightweight modules. First, the Geometry Re-Densification Module iteratively densifies encoded sparse geometry, extracts features at a dense scale, and then sparsifies the features for predictive coding. This module avoids costly computation on highly sparse details while maintaining a lightweight prediction head. Second, the Cross-scale Feature Propagation Module leverages occupancy cues from multiple resolution levels to guide hierarchical feature propagation, enabling information sharing across scales and reducing redundant feature extraction. Additionally, we introduce an integer-only inference pipeline to enable bit-exact cross-platform consistency, which avoids the entropy-coding collapse observed in existing neural compression methods and further accelerates coding. Experiments demonstrate competitive compression performance at real-time speed. Code will be released upon acceptance. Code is available at https://github.com/pengpeng-yu/FastPCC.
Authors: Yousef Kotp, Vincent Quoc-Huy Trinh, Christopher Pal, Mahdi S. Hosseini
Abstract: Computational pathology needs whole-slide image (WSI) foundation models that transfer across diverse clinical tasks, yet current approaches remain largely slide-centric, often depend on private data and expensive paired-report supervision, and do not explicitly model relationships among multiple slides from the same patient. We present MOOZY, a patient-first pathology foundation model in which the patient case, not the individual slide, is the core unit of representation. MOOZY explicitly models dependencies across all slides from the same patient via a case transformer during pretraining, combining multi-stage self-supervision with scaled low-cost task supervision. In Stage 1, we pretrain a vision-only slide encoder on 77,134 public slide feature grids using masked self-distillation. In Stage 2, we align these representations with clinical semantics using a case transformer and multi-task supervision over 333 tasks from 56 public datasets, including 205 classification and 128 survival tasks across four endpoints. Across sixteen held-out tasks, MOOZY improves macro weighted F1, balanced accuracy, and macro weighted ROC-AUC relative to PRISM by +4.19\%, +7.93\%, and +6.95\%, respectively. MOOZY is also parameter efficient with 85.77M parameters, 14$\times$ smaller than GigaPath. These results suggest that patient-level pretraining yields transferable embeddings, providing a path toward scalable patient-first histopathology foundation models.
Authors: Seng Nam Chen, Hao Chen, Chenglam Ho, Xinyu Mao, Jinping Wang, Yu Zhang, Chao Li
Abstract: Long video understanding (LVU) remains a core challenge in multimodal learning. Although recent vision-language models (VLMs) have made notable progress, existing benchmarks mainly focus on either fine-grained perception or coarse summarization, offering limited insight into temporal understanding over long contexts. In this work, we define a scene as a coherent segment of a video in which both visual and semantic contexts remain consistent, aligning with human perception. This leads us to a key question: can current VLMs reason effectively over long, scene-level contexts? To answer this, we introduce a new benchmark, SceneBench, designed to provide scene-level challenges. Our evaluation reveals a sharp drop in accuracy when VLMs attempt to answer scene-level questions, indicating significant forgetting of long-range context. To further validate these findings, we propose Scene Retrieval-Augmented Generation (Scene-RAG), which constructs a dynamic scene memory by retrieving and integrating relevant context across scenes. This Scene-RAG improves VLM performance by +2.50%, confirming that current models still struggle with long-context retention. We hope SceneBench will encourage future research toward VLMs with more robust, human-like video comprehension.
Authors: Yanjiao Song, Bowen Cai, Timo Balz, Zhenfeng Shao, Neema Simon Sumari, James Magidi, Walter Musakwa
Abstract: Monocular building height estimation from optical imagery is important for characterizing urban vertical structure, yet remains challenging due to the heterogeneity of urban building morphology and the indirect relationship between optical image appearance and building height. The recently launched PhiSat-2 satellite provides a promising open-access data source for this task, with 4.75m spatial resolution and seven multispectral bands spanning the visible to near-infrared range. However, its suitability for monocular building height estimation has not been systematically assessed. This study presents an initial open-reference assessment of PhiSat-2 imagery for this task by constructing a PhiSat-2--Height Dataset (PHDataset) and proposing a Two-Stream Ordinal Network (TSONet). PHDataset integrates global PhiSat-2 imagery with open building-height references and contains 9,475 co-registered patch pairs from 26 cities worldwide. TSONet jointly learns dense height estimation and auxiliary footprint prediction, using footprint-aware structural guidance and ordinal height modeling to better exploit PhiSat-2 spatial--spectral information. Specifically, a Cross-Stream Exchange Module (CSEM) enables adaptive interaction between the height and footprint streams, while a Feature-Enhanced Bin Refinement (FEBR) module performs coarse-to-fine ordinal query refinement with multi-level features. Experiments on PHDataset show that TSONet outperforms representative competing methods, reducing MAE and RMSE by over 13.2% and 9.7%, respectively, while improving IoU and F1-score by over 14.0% and 10.1%. Additional analyses further indicate that PhiSat-2 imagery contains useful spatial--spectral cues for monocular building height estimation at an intermediate spatial resolution.
Authors: Boyang Gong, Yu Zheng, Fanye Kong, Jie Zhou, Jiwen Lu
Abstract: Like a body at rest that stays at rest, we find that visual attention in multimodal large language models (MLLMs) exhibits pronounced inertia, remaining largely static once settled during early decoding steps and failing to support the compositional understanding required for cognitive inference. While existing hallucination mitigation methods mainly target perceptual hallucinations concerning object existence or attributes, they remain inadequate for such cognitive hallucinations that require inter-object relational deduction. Through token-wise analysis, we identify visual inertia as a contributing factor: attention to semantically critical regions remains persistently focused and fails to dynamically support relational inference. We thereby propose Inertia-aware Visual Excitation (IVE) that breaks this inertial pattern by modeling cognitive inference as the dynamic responsiveness of visual attention. Specifically, IVE selects visual tokens that are dynamically emerging relative to historical attention trends while distinguishing tokens exhibiting inertial behavior. To further facilitate compositional inference, IVE introduces an inertia-aware penalty that discourages over-concentration and limits the persistence of attention within localized regions. Extensive experiments show the effectiveness of IVE across various MLLMs and benchmarks without additional training.
Authors: Riasad Alvi, Mohaimenul Azam Khan Raiaan, Sadia Sultana Chowa, Arefin Ittesafun Abian, Reem E Mohamed, Md Rafiqul Islam, Yakub Sebastian, Sheikh Izzal Azid, Sami Azam
Abstract: Precision livestock farming requires accurate and timely heat stress prediction to ensure animal welfare and optimize farm management. This study presents a physics-informed digital twin (DT) framework combined with an uncertainty-aware, expert-weighted stacked ensemble for multimodal forecasting of Core Body Temperature (CBT) in dairy cattle. Using the high-frequency, heterogeneous MmCows dataset, the DT integrates an ordinary differential equation (ODE)-based thermoregulation model that simulates metabolic heat production and dissipation, a Gaussian process for capturing cow-specific deviations, a Kalman filter for aligning predictions with real-time sensor data, and a behavioral Markov chain that models activity-state transitions under varying environmental conditions. The DT outputs key physiological indicators, such as predicted CBT, heat stress probability, and behavioral state distributions are fused with raw sensor data and enriched through multi-scale temporal analysis and cross-modal feature engineering to form a comprehensive feature set. The predictive methodology is designed in a three-stage stacked ensemble, where stage 1 trains modality-specific LightGBM 'expert' models on distinct feature groups, stage 2 collects their predictions as meta-features, and at stage 3 Optuna-tuned LightGBM meta-model yields the final CBT forecast. Predictive uncertainty is quantified via bootstrapping and validated using Prediction Interval Coverage Probability (PICP). Ablation analysis confirms that incorporating DT-derived features and multimodal fusion substantially enhances performance. The proposed framework achieves a cross-validated R2 of 0.783, F1 score of 84.25% and PICP of 92.38% for 2-hour ahead forecasting, providing a robust, uncertainty-aware, and physically principled system for early heat stress detection and precision livestock management.
Authors: Junfeng Xia, Wenhao Ye, Xuanye Pan, Xinke Shen, Mo Wang, Quanying Liu
Abstract: Current fMRI foundation models primarily rely on a limited range of brain states and mismatched pretraining tasks, restricting their ability to learn generalized representations across diverse brain states. We present Brain-DiT, a universal multi-state fMRI foundation model pretrained on 349,898 sessions from 24 datasets spanning resting, task, naturalistic, disease, and sleep states. Unlike prior fMRI foundation models that rely on masked reconstruction in the raw-signal space or a latent space, Brain-DiT adopts metadata-conditioned diffusion pretraining with a Diffusion Transformer (DiT), enabling the model to learn multi-scale representations that capture both fine-grained functional structure and global semantics. Across extensive evaluations and ablations on 7 downstream tasks, we find consistent evidence that diffusion-based generative pretraining is a stronger proxy than reconstruction or alignment, with metadata-conditioned pretraining further improving downstream performance by disentangling intrinsic neural dynamics from population-level variability. We also observe that downstream tasks exhibit distinct preferences for representational scale: ADNI classification benefits more from global semantic representations, whereas age/sex prediction comparatively relies more on fine-grained local structure.
Authors: Yanqi Wu, Xinhua Lu, Runhe Lai, Qichao Chen, Jia-Xin Zhuang, Wei-Shi Zheng, Ruixuan Wang
Abstract: Recent studies show that using potential out-of-distribution (OOD) labels from large corpora as auxiliary information can improve OOD detection in vision-language models (VLMs). However, these methods often fail when real-world OOD samples fall outside the predefined OOD label set. To address this limitation, we propose DynProto, a novel approach that learns OOD prototypes dynamically during testing using only in-distribution (ID) information. DynProto is inspired by a key observation: OOD samples predicted as the same ID class tend to cluster in the feature space. With this insight, we leverage easy-to-detect OOD samples as ``anchors'' to find their harder-to-detect, similar counterparts. To this end, DynProto introduces two modules: \textbf{Coarse OOD Pattern Capturing Module} caches OOD patterns that are easily confused with each ID class during testing, and \textbf{Fine-grained OOD Pattern Refinement Module} subsequently clusters these patterns within each cache and aggregates them into representative OOD prototypes. By measuring similarity to ID and dynamic OOD prototypes, DynProto enables accurate OOD detection. DynProto significantly outperforms prior methods across multiple benchmarks. On ImageNet OOD benchmark, DynProto reduces FPR95 by 11.60\% and improves AUROC by 4.70\%. Moreover, the framework is architecture-agnostic and can be integrated into various backbones.
Authors: Fengxian Ji, Jingpu Yang, Zirui Song, Lang Gao, Junhong Liang, Zhenhao Chen, Jinghui Zhang, Xiuying Chen
Abstract: Recent image generation and editing models demonstrate robust adherence to instructions and high visual quality on academic benchmarks. However, their performance on paid, real-world design projects remains uncertain. We introduce \textbf{ServImage}, a benchmark that explicitly correlates model outputs with economic value in commercial design projects. ServImage consists of (i) \textbf{\textit{ServImageBench}}: a dataset of 1.07k paid commercial design tasks and 2.05k designer deliverables totaling over \$295k, covering portrait, product, and digital content, along with 33k candidate images and 33k human annotations. (ii) \textbf{\textit{ServImageScore}}: an integrated scoring system that combines three quality dimensions: baseline requirements fulfilment, visual execution quality, and commercial necessity satisfaction. These three dimensions are designed to characterize the factors that drive human payment decisions and indicate whether an image is commercially acceptable. (iii) \textbf{\textit{ServImageModel}}: under this scoring system, we propose a payment prediction model trained on the human-annotated candidate images, achieving 82.00\% accuracy in predicting human payment decisions and producing calibrated payment probabilities. ServImage provides a comprehensive foundation for assessing the commercial viability of image generation models and offers a scalable resource for future research on economically grounded vision systems \href{https://github.com/FengxianJi/ServImage}{Github.}
Authors: Kehong Gong, Zhengyu Wen, Dao Thien Phong, Mingxi Xu, Weixia He, Qi Wang, Ning Zhang, Zhengyu Li, Guanli Hou, Dongze Lian, Xiaoyu He, Mingyuan Zhang, Hanwang Zhang
Abstract: Recent methods for arbitrary-skeleton motion capture from monocular video follow a factorized pipeline, where a Video-to-Pose network predicts joint positions and an analytical inverse-kinematics (IK) stage recovers joint rotations. While effective, this design is inherently limited, since joint positions do not fully determine rotations and leave degrees of freedom such as bone-axis twist ambiguous, and the non-differentiable IK stage prevents the system from adapting to noisy predictions or optimizing for the final animation objective. In this work, we present the first fully end-to-end framework in which both Video-to-Pose and Pose-to-Rotation are learnable and jointly optimized. We observe that the ambiguity in pose-to-rotation mapping arises from missing coordinate system information: the same joint positions can correspond to different rotations under different rest poses and local axis conventions. To resolve this, we introduce a reference pose-rotation pair from the target asset, which, together with the rest pose, not only anchors the mapping but also defines the underlying rotation coordinate system. This formulation turns rotation prediction into a well-constrained conditional problem and enables effective learning. In addition, our model predicts joint positions directly from video without relying on mesh intermediates, improving both robustness and efficiency. Both stages share a skeleton-aware Global-Local Graph-guided Multi-Head Attention (GL-GMHA) module for joint-level local reasoning and global coordination. Experiments on Truebones Zoo and Objaverse show that our method reduces rotation error from ~17 degrees to ~10 degrees, and to 6.54 degrees on unseen skeletons, while achieving ~20x faster inference than mesh-based pipelines. Project page: https://animotionlab.github.io/MoCapAnythingV2/
Authors: S M Asif Hossain, Shruti Kshirsagar
Abstract: Gliomas are aggressive brain tumors that infiltrate surrounding tissue beyond the visible tumor margins observed on Magnetic Resonance Imaging (MRI). Predicting the spatial extent of this infiltration is essential for surgical planning and radiation therapy, yet existing deep learning approaches focus on segmenting the visible tumor rather than estimating infiltration risk in the surrounding tissue. This paper presents InfiltrNet, a novel dual-branch architecture that combines a convolutional neural network (CNN) encoder with a Swin Transformer encoder through cross-attention fusion modules to predict three-zone infiltration risk maps from multimodal MRI. A label generation strategy based on distance transforms is proposed to derive reproducible infiltration risk zones from standard Brain Tumor Segmentation (BraTS) annotations. InfiltrNet is trained with a combined Dice-CrossEntropy and boundary-aware loss augmented by auxiliary supervision heads at intermediate decoder levels. Extensive experiments on BraTS 2020 and BraTS 2025 demonstrate that InfiltrNet outperforms five established baselines. Explainability analysis using GradCAM++ and Occlusion sensitivity confirms that the model attends to clinically relevant peritumoral regions.
Authors: Bernhard Kainz, Johanna P Mueller, Matthew Baugh, Cosmin Bercea
Abstract: Zero-shot anomaly localisation via vision-language models (VLMs) offers a compelling approach for rare pathology detection, yet its performance is fundamentally limited by the absence of healthy anatomical context. We reformulate zero-shot localisation as a comparative inference problem in which anomalies are identified through structured comparison against reference distributions of normal anatomy. We introduce WALDO, a training-free framework grounded in optimal transport theory that enables comparative reasoning through: (i) entropy-weighted Sliced Wasserstein distances for anatomically-aware reference selection from DINOv2 patch distributions, (ii) Goldilocks zone sampling exploiting the non-monotonic relationship between reference similarity and localisation accuracy, and (iii) self-consistency aggregation via weighted non-maximum suppression. We theoretically analyse the Goldilocks effect through distributional divergence, and show that references with moderate similarity minimize a bias-variance trade-off in comparative visual reasoning. On the NOVA brain MRI benchmark, WALDO with Qwen2.5-VL-72B achieves $43.5_{\pm1.6}\%$ mAP@30 (95\% CI: [40.4, 46.7]), representing a 19\% relative improvement over zero-shot baselines. Cross-model evaluation shows consistent gains: GPT-4o achieves $32.0_{\pm6.5}\%$ and Qwen3-VL-32B achieves $32.0_{\pm6.6}\%$ mAP@30. Paired McNemar tests confirm statistical significance ($p<0.01$). Source code is available at https://github.com/bkainz/WALDO_MICCAI26_demo .
Authors: Han Jang, Junhyeok Lee, Heeseong Eum, Joon Jang, Yoseob Han, Seung Hong Choi, Kyu Sung Choi
Abstract: Precise molecular subtyping of gliomas, including isocitrate dehydrogenase (IDH) mutation and 1p/19q codeletion, directly guides surgical and therapeutic decisions, yet currently relies on invasive tissue sampling. Deep learning on structural MRI has emerged as a non-invasive alternative, but anatomy-only approaches cannot capture the hemodynamic signatures that distinguish molecular subtypes. Radiogenomics based on dynamic susceptibility contrast (DSC) MRI holds immense potential for non-invasively characterizing glioma molecular subtypes, yet clinical deployment has been hindered by inter-site variability and the limitations of voxel-wise analysis. We introduce HiPerfGNN, a framework that first learns discrete hemodynamic representations from raw time-intensity curves using a vector-quantized variational autoencoder (VQ-VAE). These quantized perfusion codes define coarse-level graph nodes representing functional tumor habitats, each of which is hierarchically subdivided into fine-level subregions guided by structural MRI. A hierarchical graph neural network then propagates information across scales for molecular prediction. On an internal cohort (n=475), the model achieved AUCs of 0.96 (IDH), 0.89 (1p/19q), and 0.84 (WHO grade), and maintained robust IDH performance (AUC 0.89) on an independent external cohort (n=397) without recalibration. Gradient-based saliency analysis confirms biologically grounded attention patterns aligned with known glioma pathophysiology. Our results demonstrate the added value of integrating perfusion dynamics into radiogenomic pipelines for glioma molecular subtyping. Code is available at https://github.com/janghana/HiPerfGNN.
Authors: Mashrafi Monon, Umaima Rahman, Asif Hanif, Numan Saeed, Mohammad Yaqub
Abstract: Recent advances in 3D medical vision-language models have enabled joint reasoning over volumetric images and text, showing strong performance in medical visual question-answering (VQA) and report generation. Despite this progress, it remains unclear whether these models learn spatially grounded anatomy from 3D volumes or rely primarily on learned priors and language correlations. This uncertainty stems from the lack of systematic evaluation of semantic-spatial reasoning in volumetric medical VLMs for clinically reliable decision support. To address this gap, we introduce CT-SpatialVQA, a benchmark designed to evaluate semantic-spatial reasoning in 3D CT data. The benchmark comprises 9077 clinically grounded question-answer (QA) pairs derived directly from 1601 radiology reports and CT volumes, which are validated via a robust LLM-assisted pipeline with a 95% human consensus agreement rate. Our dataset requires explicit anatomical localization, laterality awareness, structural comparison, and 3D inter-structure relational reasoning. We also introduce a standardized evaluation protocol and benchmark eight 3D medical VLMs, finding severe degradation on semantic-spatial reasoning tasks, averaging 34% accuracy and often below random, highlighting the need for deeper integration of volumetric evidence for trustworthy clinical use.
Authors: Qiqi Li, Pengfei Wang, Hongyu Chen, Nenggan Zheng
Abstract: Long-term multimodal action quality assessment (AQA) evaluates action execution in several-minute audiovisual sequences by mining discriminative quality cues for score prediction. Existing multimodal methods usually model entire sequences with a single temporal encoder and fuse modality features by direct alignment or concatenation, causing key cues to be obscured by global trends, weakened by modal redundancy, and distorted during one-shot score mapping. To address this issue, we reformulate long-term multimodal AQA as a quality cue organization problem and propose MLCR, a multi-level cue refinement framework. MLCR organizes quality evidence at three levels: intra-modal representation, cross-modal interaction, and stage-wise aggregation. Specifically, the intra-modal decoupling encoder (IMDE) preserves modality identity while refining global temporal context and local frequency details. The cross-modal dynamic complementarity-aware retrieval (CMDCR) module retrieves incremental evidence conditioned on the evolving fused state and suppresses redundant responses. The stage-wise multimodal integration (SMI) block progressively accumulates intra-modal and cross-modal cues to refine the fused representation. Experiments on the Rhythmic Gymnastics and Fis-V datasets show that MLCR achieves the best or second-best performance in both Spearman correlation and prediction error, demonstrating its effectiveness and robustness.
Authors: Yonghui Wang, Shaokai Liu, Wengang Zhou, Hao Feng, Houqiang Li
Abstract: Shadow detection is commonly formulated as a vision-driven dense prediction problem, where models rely primarily on pixel-wise visual supervision to distinguish shadows from non-shadow regions. However, this formulation can become unreliable in visually ambiguous cases, where similar dark regions may correspond either to cast shadows or to intrinsically dark surfaces, making visual evidence alone insufficient for establishing a stable decision rule. In this work, we revisit shadow detection from a vision--language perspective and argue that robust prediction benefits from an explicit semantic reference beyond visual cues alone. We propose SVL, a Shadow Vision--Language framework that uses language as an explicit semantic reference to disambiguate shadows from visually similar dark regions. SVL aligns global image representations with shadow-related text embeddings through scene-level shadow ratio regression, and transfers this semantic guidance to dense prediction via global-to-local coupling and local patch-level constraints. Built on a frozen DINOv3 image encoder, SVL learns only lightweight projection and decoding modules, yielding a parameter-efficient design with less than $1\%$ trainable parameters. Extensive experiments on multiple shadow detection benchmarks, including dedicated hard-case evaluations, suggest strong overall performance and improved robustness under visually ambiguous conditions. Code is available at https://github.com/harrytea/SVL.
Authors: Jiashun Zhu, Ronghao Fu, Jiasen Hu, Jing Huang, Nachuan Xing, Bo Yang
Abstract: Interpreting ultra-high-resolution (UHR) remote sensing images requires models to search for sparse and tiny visual evidence across large-scale scenes. Existing remote sensing vision-language models can inspect local regions with zooming and cropping tools, but most exploration strategies follow either a one-shot focus or a single sequential trajectory. Such single-path exploration can lose global context, leave scattered regions unvisited, and revisit or count the same evidence multiple times. To this end, we propose GeoVista, a planning-driven active perception framework for UHR remote sensing interpretation. Instead of committing to one zooming path, GeoVista first builds a global exploration plan, then verifies multiple candidate regions through branch-wise local inspection, while maintaining an explicit evidence state for cross-region aggregation and de-duplication. To enable this behavior, we introduce APE-GRO, a cold-start supervised trajectory corpus that reformulates diverse UHR tasks as Global-Region-Object interactive reasoning processes with a unified, scale-invariant spatial representation. We further design an Observe-Plan-Track mechanism for global observation, adaptive region inspection, and evidence tracking, and align the model with a GRPO-based strategy using step-wise rewards for planning, localization, and final answer correctness. Experiments on RSHR-Bench, XLRS-Bench, and LRS-VQA show that GeoVista achieves state-of-the-art performance. Code and dataset are available at https://github.com/ryan6073/GeoVista.
Authors: Zhipeng Deng, Jiale Zhou, Wenhan Jiang, Haolin Wang, Xun Lin, Yafei Ou, Yefeng Zheng
Abstract: Deploying multi-sequence magnetic resonance imaging (MRI) segmentation models to new clinical environments is challenging due to variations in scanners and acquisition protocols. Although existing TTA methods handle basic per-modality shifts, they often fail under a fundamental dual-shift problem, as their adaptation signals fail to capture modality-interaction shifts that disrupt inter-sequence consistency. To address this, we propose Variance-gated Inter-Sequence Test-time Adaptation (VISTA), a source-free framework that tackles modality-interaction shifts. First, we design an Inter-Sequence Intervention Generator (ISIG) that generates a set of consistency probes by swapping low-frequency spectra and entropy-localized patches across sequences, preserving anatomical semantics while challenging inter-sequence dependencies. Second, we introduce Cross-View Disagreement-Aware Pseudo Labeling (CDPL), which establishes a voxel-wise reliability metric using cross-view disagreement variance to dynamically gate self-training and enforce interventional consistency, encouraging the network to rely on robust anatomical semantics. Extensive experiments adapting from standard adult MRI (BraTS-GLI-Pre) to African low-field (BraTS-SSA) and pediatric (BraTS-PED) cohorts show improved performance over competing methods under clinical shifts, achieving absolute Dice improvements of +1.89% (SSA) and +2.82% (PED) over the source model. The code is available at https://github.com/dzp2095/VISTA.
Authors: Yixuan Han
Abstract: We present a lightweight appearance adapter for Stable Diffusion that enables controllable and consistent anime character generation under diverse editing conditions. Instead of relying on large-scale vision-language models or per-subject fine-tuning, our method injects fine-grained visual features from a single reference image into the diffusion process. Based on CLIP emergent local spatialization, we develop semantic-selective local attention. To further disentangle character appearance from spatial layout, we incorporate pose-aware conditioning during adapter training. The resulting pretrained adapter remains compact, modular, and fully compatible with Stable Diffusion community workflows, while requiring no additional fine-tuning at deployment time. Furthermore, we present a high-quality anime character dataset based on curated and restructured Danbooru prompts, and evaluate our method across several practical character editing scenarios. Our code, model weights, and dataset will be publicly released upon acceptance.
Authors: Ruoyu Wang, Jingke Wang, Yukai Ma, Yuehao Huang, Shuangming Lei, Guanglin Xu, Aixue Ye, Yong Liu
Abstract: Recently, world models have made significant progress in enhancing end-to-end driving systems through both future situation forecasting and improved scene understanding. However, existing driving world models are typically built upon dense scene representations, causing high computational costs and redundant information. In this paper, we present SparseWorld, a lightweight world model that focuses on predicting only the critical layout of the scene, enabling efficient future forecasting for end-to-end driving systems. SparseWorld first performs autoregressive rollout to forecast future map elements and surrounding agents, enabling the model to learn how driving scenarios evolve over time. It then leverages these predicted futures to refine downstream motion prediction and trajectory planning. Specifically, we propose a Sparse Dreamer that anticipates future instances in the latent space through joint temporal and spatial attention. By interacting with predicted future instances, the motion planner captures more accurate motion patterns and generates more informed and safety-aware trajectories. Extensive experiments demonstrate that SparseWorld significantly reduces collision risk and achieves state-of-the-art performance on the open-loop planning metrics of the nuScenes dataset with a collision rate of 0.05\%. Moreover, it substantially outperforms the baseline method in closed-loop planning metrics on the Bench2Drive benchmark. Supplementary material is available at the project page: https://wryzju.github.io/SparseWorld/.
Authors: Chidera G. Oguine, Kanyifeechukwu J. Oguine, Obiozor M. Oguine, Ozioma C. Oguine
Abstract: This paper presents a rigorous empirical evaluation of Ultralytics YOLO26 against the YOLOv8 baseline, offering an independent real-world stress test of NMS-free architectures on non-COCO distributions. Engineered for edge deployment, YOLO26 introduces native end-to-end one-to-one label assignment, the removal of Distribution Focal Loss (DFL), and a spectral-constrained CSP-Muon backbone. We conducted a comprehensive, cross-scale comparative analysis across five model capacities, using the general object detection (Pascal VOC) and dense aerial small-object detection (VisDrone) datasets. Models are evaluated across accuracy (mAP_50 and mAP_50:95), model complexity, and hardware-specific CPU/GPU latency. Our findings revealed that while YOLO26 achieves a lower computational footprint and superior accuracy on Pascal VOC, with YOLO26-x reaching 0.635 mAP_50:95, this advantage narrows in dense aerial environments. On VisDrone, where over 75% of objects are under 2,000 pixels, both architectures struggle significantly, yielding a minimal performance gap (0.214 mAP_50:95 for YOLOv8-x vs. 0.224 mAP_50:95 for YOLO26-x). Crucially, hardware benchmarking demonstrates that YOLOv8 maintains a consistent edge in GPU inference latency across identical scales (e.g., 6.92 ms for YOLOv8-s vs. 8.38 ms for YOLO26-s), showing that NMS-free design does not inherently guarantee superiority in universal deployment. This work maps the operational boundaries of NMS-free frameworks to guide architecture selection based on dataset density, object scale, and hardware constraints.
Authors: Kai Bian, Xucheng Guo, Bin Chen, Lingyan Ruan, Yiran Shen, Ting Dang, Hong Jia
Abstract: Evaluations of dental vision-language models remain fragmented across datasets, task definitions and metrics, and often ignore their computational cost. This limits their widespread deployment for dental screening outside specialist centres, where timely inference, limited hardware, and local handling of patient images are vital for practical, privacy-preserving clinical prescreening. Here we present Pocket-Dentist, an efficiency-aware benchmark for dental multimodal question answering that brings together three datasets spanning approximately 1,159 patients from BRAR and MetaDent, five task types and seven metrics. Across 14 typical VLMs, our results reveal an interesting observation: compact VLMs, such as 2B-parameter models, become competitive with much larger VLMs on most metrics after lightweight adaptation while requiring substantially lower computational costs in dental image understanding. Deployed locally on an iPhone 17 Pro, our finetuned compact VLM Pocket-Dentist-2B processed each sample in 4.31 s, reducing latency by 4.9x and memory use by 2.3x compared with a 7B baseline. Our project page is available at https://2026-icml.github.io/pocket-dentist-icml.
Authors: Qi Xu, Yue Tan, Shihao Chen, Jiahao Meng, Anna Wang, Shunping Ji, Hao Fei, Jason Li
Abstract: Temporal Grounding (TG) aims to localize video segments corresponding to a textual query. Prior research predominantly focuses on single-segment retrieval. Real-world scenarios, however, often require localizing multiple disjoint segments for a single query -- a setting we term One-to-Many Temporal Grounding (OMTG). Previous state-of-the-art MLLMs, optimized for one-to-one settings, struggle in this context, often yielding near-zero scores due to a lack of event cardinality perception. To bridge this gap, we present a systematic solution with three key contributions. First, we establish the first comprehensive OMTG benchmark, introducing Count Accuracy (C-Acc) and Effective Temporal F1 (EtF1) as evaluation metrics. Second, we curate a high-quality OMTG dataset comprising 56k samples through a sophisticated construction pipeline. Third, we develop novel temporal and caption reward functions specifically designed for OMTG. In particular, the caption reward leverages Chain-of-Thought reasoning over dense video captions to explicitly guide policy optimization toward both preciseness and completeness. Extensive experiments show our model achieves a new state-of-the-art EtF1 of 43.65\% on OMTG Bench, outperforming Gemini 2.5 Pro and Seed-1.8 by 15.85\% and 15.61\%, respectively. Project Page: https://insomniaaac.github.io/OMTG/
Authors: Anku Rani, Wei Dai, Shravan Nayak, Pattie Maes, Mahdi M. Kalayeh, Paul Pu Liang
Abstract: As video generation models like Veo 3.1 and LTX-2 advance, their ability to accurately represent diverse global cultures remains a critical yet understudied frontier. Current metrics, such as VideoScore, only measure visual quality but offer no mechanism for assessing cultural faithfulness. Consequently, a model that replaces a Namaste with a handshake receives the same score as one that generates the gesture correctly. We propose CultureScore, a compositional evaluation framework that decomposes cultural faithfulness into three granular dimensions: Identity (who is represented), Context (culturally localized background), and Behavior (normative gestures and interactions). We operationalize this framework through an evaluation suite spanning 10 countries, yielding 6,174 generated videos across three state-of-the-art models. Our evaluation reveals that no current model achieves culturally faithful video generation: the best-performing model reaches only 56.8\% overall CultureScore, with Behavior the most challenging dimension, which remains below 52.1\% across all models. Furthermore, human preference rankings align directionally with CultureScore but are inverted relative to VideoScore; the highest-scoring model on visual quality was ranked last by annotators, underscoring that cultural faithfulness is an essential criterion for equitable video generation. Data and code are available at https://huggingface.co/datasets/ankurani/CultureScore.
URLs: https://huggingface.co/datasets/ankurani/CultureScore.
Authors: Yufei Wei, Shuhao Ye, Chenxiao Hu, Yiyuan Pan, Dongyu Feng, Rong Xiong, Yue Wang, Yanmei Jiao
Abstract: Recovering the relative 6-DoF pose between two image groups underlies cross-sequence relocalization and multi-camera rig odometry. Each group carries known intra-group geometry from visual odometry or rig calibration, and pretrained multi-view backbones already fuse such geometry into visual features. Yet current models treat all views as an unstructured set, leaving cross-group reasoning as the missing piece. We introduce \ours{}, which keeps the foundation model entirely frozen and adds three lightweight trainable modules to bridge the two groups: a perceiver resampler, a cross-group bridge with merged self-attention, and a multi-frame pose head. The trainable footprint totals about 32M parameters, under 6\% of the full model, and is supervised only by relative poses. Across four datasets that span indoor and outdoor simulation, real-world cross-season capture, and zero-shot sim-to-real transfer, \ours{} attains state-of-the-art accuracy on both tasks, while every baseline is retrained with its full original supervision. Code is available at https://github.com/WeiYuFei0217/G2G.
Authors: Zhang Chen, Shuai Wan, Mengting Yu, Fuzheng Yang, Junhui Hou
Abstract: Existing pruning methods for 3D Gaussian splatting (3DGS) suffer from either severe quality degradation or prohibitive computational overhead. In this paper, we propose REFINE, a highly accelerated 3DGS pruning framework centered on a novel rendering-free primitive importance metric. Our approach leverages an analytically approximated, rendering-aware Hessian field to quantify the expected perceptual error induced by the removal of individual primitives. By modeling the joint modulation of visibility, projection geometry and the content adaptive hyperparameter, we entirely bypass costly forward rendering passes and derive an anisotropic perceptual weight field that serves as a high-fidelity proxy for primitive importance. Extensive experiments across multiple benchmark datasets demonstrate that REFINE maintains highly competitive rendering quality while achieving an unprecedented $3,000\times$ reduction in pruning-related computational complexity compared to state-of-the-art pruning methods.
Authors: Zibin Liu, Shunkun Liang, Banglei Guan, Yang Shang, Qifeng Yu, Ji Zhao
Abstract: Despite the rapid advancements in event-based motion estimation, current geometric methods primarily focus on velocity estimation. However, absolute pose estimation, which is equally crucial for key applications such as robotic navigation and augmented reality, remains relatively underexplored. Consequently, the simultaneous recovery of absolute pose and velocity from event streams remains an open and challenging problem. To address this gap, we propose a geometric framework for absolute pose and velocity estimation by leveraging 3D lines in the scene and the events they trigger. At the core of the framework lie two key geometric constraints: the orthogonality between a 3D line and the normal vector of its corresponding event plane, and the collinearity of an event with the 2D projection of its associated line. Based on these constraints, we present both linear and polynomial solvers for absolute pose estimation. The former enables efficient computation, while the latter provides a globally optimal solution for rotation. For velocity estimation, we develop an efficient linear solver and a more accurate optimization-based solver to recover both angular and linear velocities. Notably, our methods require a minimum of three event-line correspondences to determine the 6-DoF absolute pose or velocities independently. Extensive experiments in simulation and on real-world datasets demonstrate that our methods achieve state-of-the-art performance, with significant improvements in accuracy and computational efficiency compared to existing methods. The demo code is publicly available at https://github.com/Zibin6/EventPoseVelocity.
Authors: Ewa Miazga, Jorge Condor, Piotr Didyk
Abstract: View-dependent appearance modeling remains a challenging problem in novel-view synthesis and reconstruction. Accurately representing complex angular effects often requires substantial memory and computational resources. For new learning-based methods, a common approach is to rely on SH. However, capturing high-frequency phenomena such as specular reflections demands high-order expansions, which increase memory usage and computational cost. Consequently, most methods employ low-order SH, which limits the ability to model complex view-dependent effects, resulting in overly smooth or diffuse representations. To address these limitations, we systematically evaluate a wide range of spherical functions in the context of scene reconstruction. Some of them are introduced to graphics and computer vision for the first time in this paper. Based on the insights from the experiment, we develop a novel spherical formulation, the Normalized Anisotropic Spherical Gabor function that enables efficient modeling and learning of high-frequency appearance effects while maintaining compact representation. Compared to existing approaches, our function achieves higher-quality reconstruction of view-dependent phenomena such as glints, while being up to five times more memory-efficient and more efficient to evaluate. We validate its performance in radiance-field reconstruction tasks.
Authors: Cong Wang, Zhentao Yu, Hongmei Wang, Weicong Liang, Zixiang Zhou, Zilin Yang, Jiarong Ou, Rui Chen, Yuan Zhou, Qinglin Lu
Abstract: Current identity-consistent video generation methods struggle to preserve appearance fidelity under large viewpoint changes. While introducing multi-view reference input offers a natural solution, progress remains constrained by the lack of effective frameworks for multi-view inputs and the scarcity of multi-view data. We address these challenges by proposing HarmoView, a robust framework for identity-consistent video generation that effectively integrates multi-view cues through three architectural refinements complemented by a staged training curriculum. Specifically, we first introduce Multi-level Feature Injection to anchor identity fidelity; by injecting raw ViT features from frontal references alongside text tokens via cross-attention, MFI provides persistent low-level appearance anchors that complement the high-level identity features within DiT blocks, leading to enhanced identity preservation. Then, we employ learnable proxy tokens to unify heterogeneous reference layouts across single-/multi-view settings while simultaneously resolving the reference-view mismatch problem. Jump-RoPE is further developed for identity-wise feature isolation to reduce identity crosstalk. To activate these structural capabilities while preserving the original generative priors, we propose the Progressive View Curriculum. This four-stage training strategy employs view dropout to facilitate a stable transition from vanilla T2V generation to high-fidelity, identity-persistent spatial reasoning. Furthermore, we construct a large-scale multi-view dataset to address the issue of data scarcity. Extensive evaluation on our multi-view benchmark, comprising 100 manually-curated cases spanning 52 unique identities, demonstrates that HarmoView significantly outperforms open-source baselines and matches leading closed-source engines, achieving state-of-the-art performance in identity-consistent video generation.
Authors: Duc Nguyen, Sieu Tran, Hao Vo, Khoa Vo, Duy Minh Ho Nguyen, Nghi D. Q. Bui, Anh Nguyen, Long Mai, Ngan Le
Abstract: Unsupervised video object-centric learning aims to decompose dynamic scenes into temporally persistent entity representations. Existing recurrent video slot-attention methods propagate a fixed set of slots across frames, but typically assume unconditional slot propagation: every slot is updated and decoded at every frame, regardless of whether its corresponding object is visible. We show that this design violates a basic lifecycle requirement for persistent slots: when an object is absent or fully occluded, its slot should preserve its previous state and avoid explaining unrelated visible content. Instead, unconditional propagation creates two failure pathways: update-induced state drift, where current-frame evidence overwrites the absent object's representation, and decoder-induced reconstruction interference, where the inactive slot remains coupled to reconstruction through decoder attention. We propose Temporal Slot Activation (TSA), a mechanism that learns a per-slot, per-frame activation score $\alpha_{k,t} \in (0, 1)$ without visibility supervision. TSA uses this activation as a shared latent control variable for slot lifecycle modeling. When a slot is inactive, TSA anchors its state to the previous slot via activation-gated updating and suppresses its decoder participation through an activation-dependent additive bias on attention logits before softmax normalization. This jointly reduces state drift and reconstruction-driven interference. To improve decisions under partial occlusion and gradual reappearance, TSA further conditions activation prediction on a per-slot temporal memory produced by a Temporal Context Encoder. We evaluate TSA on MOVi-C/E, YT-VIS, and OVIS benchmarks using both standard and tracking-based metrics (FG-ARI, mBO, IDF1, HOTA). TSA consistently improves object decomposition and temporal identity preservation, with large gains on long, heavily occluded videos.
Authors: Ahmed Karam Eldaly, Matteo Figini, Daniel C. Alexander
Abstract: We propose a novel Bayesian framework for joint image reconstruction and uncertainty quantification from compressed sensing magnetic resonance imaging data. The problem is formulated as a linear inverse problem, where prior distributions are assigned to the unknown image parameters. Specifically, the image is assumed to be sparse in a given transform domain. We develop a general framework applicable to any sparsifying transform and demonstrate its performance using (1) a total variation transform based on image spatial gradients and (2) a wavelet-domain transform. Bayesian inference is performed using a split-and-augmented Gibbs sampler, while the resulting non-differentiable conditional distributions are efficiently sampled using a proximal Markov chain Monte Carlo method. The proposed algorithms are validated on both single-coil and multi-coil datasets using various k-space sampling patterns and acceleration factors. The results demonstrate that the proposed Bayesian methods consistently outperform their optimisation-based counterparts in image reconstruction while providing uncertainty estimates for the reconstructed images. Furthermore, the estimated uncertainty maps show a strong correlation with the true reconstruction errors and substantially outperformed deep learning-based uncertainty estimation methods.
Authors: Wan Siti Halimatul Munirah Wan Ahmad, Faris Syahmi Samidi, Mohammad Badal Ahmmed, Vimal Angela Thiviyanathan, Selvam Thavaraj, Anwar P. P. Abdul Majeed
Abstract: Characterising the tumour microenvironment (TME) from routine H&E-stained histology images requires simultaneous cell segmentation, feature extraction, and interpretable clinical reporting. We present SegTME-UNI2, a unified framework addressing these requirements. Its core is UNI2-UperHoVeR, a dual-head segmentation model pairing the UNI2-h pathology foundation model (ViT-Giant, pretrained on >100M tiles from 100K slides) with two parallel UperNet decoders: one for six-class semantic segmentation and one for horizontal-vertical gradient regression enabling watershed-based nuclear instance separation. To address the lack of pixel-level annotations in large real-world repositories, UNI2-UperHoVeR undergoes a three-stage progressive pseudo-label curriculum. Each stage trains a fresh model without weight transfer, driving improvement entirely via increased pseudo-label quality: Stage 1: Uses human-annotated PanNuke (7,901 images, 189,744 nuclei, 0.25 um/pixel). Stage 2: Uses entropy-filtered pseudo-labels from the Stage 1 model on 271,711 TCGA-UT scale-0 patches (0.5 um/pixel). Stage 3: Uses pseudo-labels from the Stage 2 model on all 1,608,060 TCGA-UT patches across six resolution scales (0.5-1.0 um/pixel). Segmentation outputs feed a structured TME feature extraction pipeline computing 20+ per-patch compositional, morphological, spatial entropy, and intercellular distance metrics. These are encoded as JSON and passed to a fine-tuned NVIDIA BioNeMo GPT model to generate clinically interpretable TME narratives. Preliminary validation on held-out PanNuke and TCGA-UT partitions demonstrates framework feasibility and internal consistency. The pseudo-labelled TCGA-UT dataset and UNI2-UperHoVeR checkpoint are publicly released to support large-scale TME profiling and spatial biology research.
Authors: Mahshad Lotfinia, Sebastian Ziegelmayer, Lisa Adams, Daniel Truhn, Andreas Maier, Soroosh Tayebi Arasteh
Abstract: Medical vision-language models report strong chest radiograph accuracy, and this is increasingly read as evidence that they use the image. That inference is unsafe: a model exploiting finding-name priors scores like one that reads the scan, and no standard benchmark separates them. We introduce a causal audit that intervenes on the image, occluding the relevant region, occluding an irrelevant one, and swapping in another patient's same-label scan, and combines three behavioral metrics to test whether a correct answer depends on the image. Across nine systems, a text-only model with no image access reaches within 5.7 accuracy points of the best multimodal one, and a 119-billion-parameter multimodal model is statistically indistinguishable from a 7-billion text-only baseline. The audit splits the cohort into three models that ignore the image, one that is unstable, and five that use it selectively, for a subset of findings; the categories hold across a second dataset, resolution, and prompt phrasing. Against board-certified radiologists, a text-only model is statistically indistinguishable from a radiologist's accuracy while grounding at zero, whereas the image-using models ground at radiologist-comparable rates. Reported confidence flags ungrounded answers only when a model uses the image. Grounding audits, not accuracy, should gate clinical deployment.
Authors: Tianyu Liu, Ziqing Wang, Zhaokang Liang, Tong Ding, Peter Humphrey, Lorraine Col\'on-Cartagena, Emily Ling-Lin Pai, Kenneth Tou En Chang, Mohamed Kahila, Jonathan Chong Kai Liew, Tinglin Huang, Rex Ying, Kaize Ding, Faisal Mahmood, Wengong Jin
Abstract: Predicting immune biomarkers associated with the tumor immune microenvironment (TIME) is critical for advancing precision oncology, yet existing approaches are largely limited to single image modalities and suffer from insufficient resolution and incomplete utilization of complementary clinical and biological information. Here we introduce MixTIME, a multimodal foundation model that leverages a mixture-of-experts (MoE) architecture to integrate pathology foundation models trained across distinct modalities: image only (UNIv2), image text (CONCHv1.5), and image transcriptomic (STPath) representations for pixel-level and slide-level prediction of multiplex immunofluorescence (mIF) protein expression from hematoxylin and eosin (HE) whole-slide images. MixTIME employs a learnable router to dynamically weight expert contributions and is trained with a distribution- and tendency-aware loss function. Benchmarked on two datasets of different scales, MixTIME achieves state-of-the-art performance across 17 protein markers as measured by correlation metrics. The predicted mIF profiles substantially enhance downstream tasks, including spatial domain identification, survival prediction, and AI-assisted pathology report generation validated by expert pathologists from multiple institutes across the world. Furthermore, MixTIME enables longitudinal tracking of protein expression dynamics across clinical time points and reveals protein gene interaction patterns linked to drug resistance and immune suppression in tumor microenvironments. Collectively, MixTIME provides a scalable framework for multimodal biomarker discovery and clinical translation in computational pathology.
Authors: Hiranya Garbha Kumar, Minhas Kamal, Balakrishnan Prabhakaran
Abstract: Accurately aligning CAD models to their corresponding objects in indoor RGB-D scans is a central challenge in 3D semantic reconstruction. The task requires estimating a 9-Degree-of-Freedom (DoF) pose-position, rotation, and scale along three axes-but is hindered by noisy and incomplete scans, as well as segmentation errors that cause geometric distortions. We present Completion-Assisted Object-CAD Alignment (CAOA), a method that integrates a semantically and contextually aware point cloud completion module with a symmetry-aware relative pose estimation algorithm, enabling precise alignment of CAD models to scanned objects. Existing completion methods are typically trained and evaluated on synthetic datasets, which often fail to generalize to real-world scans. To bridge this gap, we introduce a synthetic data generation strategy tailored to indoor scenes, significantly reducing the synthetic-to-real domain gap-validated through quantitative comparisons with widely used completion datasets. In addition, we release S2C-Completion, an expert-annotated dataset of over 8,500 object-CAD pairs from Scan2CAD, created for real-world indoor single-object completion and intended as a new benchmark for this task. For object-CAD alignment, we incorporate symmetry information via a symmetry-aware loss, improving robustness to symmetric ambiguities. On the Scan2CAD benchmark, CAOA achieves a 17% accuracy improvement over state-of-the-art methods.
Authors: Jiarui Xing, Tal Zeevi, Nian Wu, Jian Wang
Abstract: Learning unsupervised representations of medical imaging cohorts can reveal clinically meaningful prototypes without expert labels, which are often noisy and fail to capture true pathological heterogeneity. However, existing deep latent-variable models estimate Gaussian mixture priors via Euclidean averaging, producing prototypes that drift off the curved data manifold and degenerate as the number of sub-populations grows. We propose a manifold-anchored variational framework built on a geometry-aware Expectation-Maximization (EM) algorithm, whose M-step selects each sub-population prototype as the graph medoid with the highest diffusion centrality on a heat-kernel-weighted latent graph, ensuring that every prototype remains on-manifold. A Dirichlet energy regularizer enforces geometric smoothness of the latent space, and a per-sub-population uncertainty score enables label-free quality assessment. The manifold-anchored EM is a general-purpose geometric tool that extends standard EM and applies readily to other latent-variable models beyond this setting. On cardiac scar and brain MRI benchmarks, our framework attains the highest accuracy among all compared methods, produces the sharpest prototypes reported to date, and remains stable at large sub-population counts where all baselines degenerate. The Code and implementation details are available at https://github.com/jr-xing/On-Manifold-Variational-Learning-with-Heat-Kernel-Priors.
URLs: https://github.com/jr-xing/On-Manifold-Variational-Learning-with-Heat-Kernel-Priors.
Authors: Yucheng Tang, Alexander Ng, Wen Yan, Natasha Thorley, Pawel Rajwa, Yipei Wang, Aqua Asif, Clare Allen, Louise Dickinson, Francesco Giganti, Shonit Punwani, Daniel Alexander, Veeru Kasivisvanathan, Yipeng Hu
Abstract: Clinical prostate multi-parametric MRI relies heavily on high-quality diffusion-weighted imaging (DWI), yet reading DWI is frequently compromised by geometric distortion, often caused by rectal air. Assessing quality via the PI-QUAL scoring system is an emerging clinical standard, but it is subjective, time-consuming and suffers from a class imbalance where low-quality cases are diverse and relatively scarce. Using the PRIME clinical trial as an example, there are $6\%$ images with PI-QUAL scores lower than 4, $87\%$ of DWI issues are due to distortion. Many of the other clinical quality issues are under-represented. To address this common dual-scarcity of annotated clinical data, we propose a few-shot biparametric prototypical network for automated image quality assessment (IQA). Our framework utilizes a dual-branch 3D ResNet to fuse T2-weighted and DWI features, providing anatomical context to distinguish true morphology from distortion. To handle real-world heterogeneity, we introduce feature-wise linear modulation (FiLM) and a gradient reversal layer (GRL) to align feature distributions conditioned on varying b-values while suppressing acquisition-related biases. We demonstrate that a model meta-trained solely on comparatively objective, readily obtainable distortion labels can effectively adapt to predicting complex, multi-factorial clinical quality scores such as PI-QUAL using only five representative samples. Experimental results on two datasets show that our method significantly outperforms few-shot learning baselines for this challenging IQA task, offering a practically feasible and data-efficient solution for standardizing prostate MRI quality control in clinical workflows.
Authors: Xiangchen Yin, Wenzhang Sun, Jiahui Yuan, Zijie Liu, Yinda Chen, Wei Li, Dachun Kai, Chunfeng Wang, Xiaoyan Sun
Abstract: Video world models are moving toward preserving an observed world under controllable camera and object motion while allowing its environmental state to change. Yet these controls remain isolated, and weather generation typically relies on a source video or reconstructed scene that already specifies future structure. We study a first-frame-anchored source-to-state setting, where the model starts from a single image and follows explicit camera and object controls and an optional weather instruction, then generates a video that either preserves the source world or transfers it to a target weather state. To address these challenges, we first build HoloStateData, a state video dataset that turns diverse videos into unified control samples for camera, object, and weather supervision. Second, we introduce Holo-World, a unified controllable video world model that jointly controls scene from a single image. Its Unified Scene Adapter factorizes world preservation and weather transfer into distinct parameter subspaces, using rendered background, geometry buffers, and object controls to maintain controlled scene structure while modeling weather-dependent appearance and particle effects. Additionally, Scene-Weather Decomposed CFG guides scene and weather residuals separately, strengthening target weather effects without over-amplifying the full condition. Quantitative and qualitative experiments demonstrate that Holo-World maintains precise camera and object control with consistent scene structure while transferring scenes into diverse target weather state, outperforming video-to-video weather editing baselines on weather-state generation. Our project page is available at https://xiangchenyin.github.io/Holo-World/
Authors: Haoxuan Li, Ziya Erko\c{c}, Daniele Sirigatti, Vladislav Rosov, Lei Li, Angela Dai, Matthias Nie{\ss}ner
Abstract: We present TriFlow, a new generative approach for producing compact 3D meshes with artist-like triangle topology directly from input geometry conditions such as signed distance fields. Our key insight is to represent mesh topology as a nearest-vertex vector field (NVF) defined over the surface, where each point encodes its association to the nearest triangle vertex in the local barycentric frame. We train a latent flow-matching model to synthesize this field, enabling topology generation conditioned on the input geometry. To extract a coherent mesh, we cluster surface regions using the generated NVF and guide a constrained quadric error metric (QEM) mesh simplification with topology-aware optimization. This yields output meshes that closely match the input geometry while exhibiting structured, artist-like connectivity. Experiments demonstrate that TriFlow achieves stronger generalization and significantly improved topology quality compared to state-of-the-art learning-based approaches, alongside 90% lower Chamfer Distance and an 8x speedup.
Authors: Haochen Han, Jue Wang, Alex Jinpeng Wang, Fangming Liu
Abstract: Multimodal Large Language Models (MLLMs) have demonstrated remarkable success in various Remote Sensing (RS) tasks. However, their ability to comprehend negation remains underexplored, limiting deployment in real-world applications where models must explicitly identify what is false or absent, e.g., emergency responders need to locate non-flooded routes for evacuation. To comprehensively study this limitation, we introduce RS-Neg, the first benchmark to evaluate negation understanding across region-level to scene-level tasks. Specifically, we design an automated data generation pipeline for RS imagery, using LLMs to synthesize diverse negation queries, and introduce a dynamic visual focus module for verification. Our evaluation reveals that advanced RS MLLMs struggle with negation, exhibiting hallucinations and substantial performance degradation. To close this gap, we propose NeFo, a novel test-time learning method that explicitly incorporates the logical role of negation into the model optimization. Remarkably, using about 5\% unlabeled test samples, NeFo significantly improves the negation understanding of models and shows strong generalization to unseen tasks.
Authors: Maciej Wozniak, Jesper Ericsson, Hariprasath Govindarajan, Truls Nyberg, Thomas Gustafsson, Patric Jensfelt, Olov Andersson
Abstract: Leveraging Vision Foundation Models (VFMs) for camera-to-LiDAR knowledge distillation offers a promising solution to the scarcity of annotated data needed to represent the immense geometric and kinematic diversity of real-world autonomous driving (AD). However, current approaches typically treat VFMs as black-box teachers, relying exclusively on frame-wise feature similarity. Consequently, they do not fully exploit the teacher's layer-wise semantic structure and global context, as well as the rich spatiotemporal information inherent in LiDAR sequences. We propose HilDA, a self-supervised pretraining framework for LiDAR backbones that better captures the semantic what and geometric where needed for driving tasks. HilDA combines hierarchical distillation comprising multi-layer distillation for progressive semantic alignment and global context distillation for scene-level semantics, with a temporal occupancy diffusion objective promoting spatiotemporal consistency. Models pre-trained with HilDA achieve state-of-the-art results on cross-modal distillation benchmarks and outperform models trained via prior distillation approaches on 3D object detection, scene flow, and semantic occupancy prediction. Code available at: https://maxiuw.github.io/hilda.
Authors: Bo Yin, Xiaobin Hu, Chengming Xu, Ruolin Shen, Mo Yang, Jiangning Zhang, Peng-Tao Jiang, Cheng Tan, Shuicheng Yan
Abstract: Vision-language models (VLMs) often underperform on evidence intensive tasks because decisive visual evidence are small, localized, and easy to overlook, leading to failures in evidence readout even when high-level reasoning is intact. Prior inference-time visual interventions can improve grounding without retraining, but they are largely open-loop and lack a mechanism to verify whether highlighted evidence is actually used. We study answer-span prediction entropy as a model-internal feedback signal and show that naive entropy minimization is ambiguous, since low entropy may arise from evidence-grounded confidence or shortcut collapse. To resolve this ambiguity, we introduce low-entropy anchors and an entropy-shaping objective that reduces answer uncertainty while preserving baseline high-confidence tokens. We instantiate this principle in SPOT-E, a plug-and-play test-time method that produces question-conditioned spotlights, optimized per instance via light-weight tuning based on Group Relative Policy Optimization (GRPO). Across all benchmarks and different VLM families, SPOT-E yields consistent gains and improved robustness under visual corruptions. Code is publicly available at: https://github.com/YinBo0927/SPOT-E
Authors: Junhao Cai, Deyu Zeng, Junhao Pang, Junyu Chen, Qiwei Liang, Xiaopin Zhong, Zongze Wu
Abstract: Few-shot anomaly detection remains challenging due to limited training data. Multi-modal anomaly detection (MAD) offers a viable solution, leveraging 3D geometric cues to enrich 2D RGB representations and compensate for this scarcity. However, existing MAD methods apply spatially uniform feature processing, conflating stable macroscopic structures with high-frequency localized defect signals, exacerbating cross-modal misalignment and inflating false-positive rates. To overcome this, we present CMDS-AD, a Cross-Modal Dual-Stream Anomaly Detection framework. A LoRA-guided diffusion model generates diverse RGB samples to mitigate extreme data scarcity. For 3D normal augmentation, we employ a pre-trained diffusion model as a normal estimator. Crucially, this estimator inherently acts as a non-linear low-pass filter, directly extracting low-frequency normal representations from RGB inputs. This establishes an auxiliary estimated stream of purely low-frequency information, anchoring robust structural templates and assisting the uncompressed real stream, containing coupled high- and low-frequency components, to precisely isolate micro-defects. A Coordinate-Aware Hierarchical Feature Mapper adaptively aligns cross-modal semantics, while a multiplicative scoring mechanism filters modality-specific noise. Under the extreme 1-shot setting, CMDS-AD achieves absolute performance gains of 5.7% (I-AUROC) and 2.0% (AUPRO) on MVTec 3D-AD, alongside 7.7% and 5.6% improvements on EyeCandies, establishing a new state-of-the-art. Code is available at https://github.com/Junhaocai27/CMDS-AD
Authors: Yusuf Salcan (Computer Vision Group, University of Freiburg, Germany, CRIION-AI Lab, Freiburg, Germany), Simon Ging (Computer Vision Group, University of Freiburg, Germany, Adaptive & Agentic AI), Robin Tibor Schirrmeister (Department of Radiology, Medical Center -- University of Freiburg, Germany), Philipp Arnold (Department of Radiology, Medical Center -- University of Freiburg, Germany), Elmar Kotter (Department of Radiology, Medical Center -- University of Freiburg, Germany), Behzad Bozorgtabar (Adaptive & Agentic AI), Thomas Brox (Computer Vision Group, University of Freiburg, Germany)
Abstract: We study how to train visually grounded vision-language models (VLMs) for radiology without manual spatial annotations. We introduce RefRad2D, a large-scale bilingual (German/English) dataset of 1.2M CT and MR image-text pairs derived from clinical practice, with task-specific VQA and spatial grounding subsets generated automatically via LLM-based curation and automated segmentation. Trained on this data, our model RadGrounder jointly performs report generation, visual question answering, and spatial grounding via bounding-box detection or segmentation. On external VQA benchmarks (Slake, VQA-RAD), RadGrounder achieves competitive results with specialized medical VLMs. Adding our clinical data to the training mixture improves open-ended VQA over fine-tuning on the downstream datasets alone, showing the transferability of our dataset. Crucially, adding grounding supervision does not degrade language quality, enabling spatially verifiable outputs at no cost to VQA performance.
Authors: Xi Zhang, Xiaolin Wu
Abstract: Recently, numerous end-to-end optimized image compression neural networks have been developed and proved themselves as leaders in rate-distortion performance. The main strength of these learnt compression methods is in powerful nonlinear analysis and synthesis transforms that can be facilitated by deep neural networks. However, out of operational expediency, most of these end-to-end methods adopt uniform scalar quantizers rather than vector quantizers, which are information-theoretically optimal. In this paper, we present a novel Lattice Vector Quantization scheme coupled with a spatially Adaptive Companding (LVQAC) mapping. LVQ can better exploit the inter-feature dependencies than scalar uniform quantization while being computationally almost as simple as the latter. Moreover, to improve the adaptability of LVQ to source statistics, we couple a spatially adaptive companding (AC) mapping with LVQ. The resulting LVQAC design can be easily embedded into any end-to-end optimized image compression system. Extensive experiments demonstrate that for any end-to-end CNN image compression models, replacing uniform quantizer by LVQAC achieves better rate-distortion performance without significantly increasing the model complexity. Code is available at: https://github.com/xzhang9308/LVQAC.
Authors: Zhentao Liu, Huangxuan Zhao, Wenhui Qin, Zhenghong Zhou, Xinggang Wang, Wenping Wang, Xiaochun Lai, Chuansheng Zheng, Dinggang Shen, Zhiming Cui
Abstract: Digital Subtraction Angiography (DSA) is one of the gold standards for vascular disease diagnosis. With the help of a contrast agent, time-resolved 2D DSA images deliver comprehensive blood flow information and can be utilized to reconstruct 3D vessel structures for medical assessment. Current commercial DSA systems typically require hundreds of scanning views to perform reconstruction, resulting in substantial radiation exposure. In this study, we propose a neural rendering-based optimization framework tailored for high-quality sparse-view DSA reconstruction to reduce radiation dosage. Our approach, termed vessel probability guided attenuation learning, represents DSA imaging as a complementary weighted combination of static and dynamic attenuation fields, with the weights derived from the time-independent vessel probability field. Functioning as a foreground mask, vessel probability provides proper gradients for both static and dynamic fields adaptive to different scene types. This mechanism enables self-supervised decomposition between static backgrounds and dynamic contrast agent flow, and significantly improves reconstruction quality. Our model is trained by minimizing the discrepancy between synthesized projections and real captured DSA images. We further employ two training strategies to improve reconstruction quality: (1) coarse-to-fine progressive training for better geometry and (2) temporal perturbed rendering loss for temporal consistency. Experimental results have demonstrated high-quality 3D vessel reconstruction and 2D DSA image synthesis.
Authors: Sai Haneesh Allu, Itay Kadosh, Tyler Summers, Yu Xiang
Abstract: Persistent semantic monitoring of indoor spaces such as warehouses, hospitals, and offices requires a robot to repeatedly monitor an environment and track how objects change over time. Running full simultaneous localization and mapping (SLAM) with dense semantic reconstruction from scratch on every visit is redundant when the environment geometry stays the same and only the objects move. We present a modular two-stage system that separates geometric mapping from semantic updating. In the first stage, a frontier-based exploration method with a dynamic search window builds a 2D occupancy grid. In the second stage, the robot relocalizes in this map and builds a semantic object graph using an open-vocabulary object detector and a promptable segmentation model. Only the lightweight semantic stage is repeated on later visits, so the system scales well to frequent revisits. The object graph uses a category and distance based association rule to update objects, which lets the map reflect both intra-session changes (object changes within a single traversal) and inter-session changes (changes across revisits), such as objects being moved, removed, or added. We validate the system on a Fetch robot in two real indoor environments of about 8,500 sq.m and 117 sq.m, and report precision, recall, and F1 scores across multiple update iterations.
Authors: Maneet Mehta, Cody Buntain
Abstract: This paper examines potential biases and inconsistencies in the emotions evoked by images produced by generative artificial intelligence (AI) models and their potential bias toward negative emotions. We assess this bias by comparing the emotions evoked by an AI-produced image to the emotions evoked by prompts used to create those images. After developing and validating automated methods for emotion recognition across modalities, we examine correlations in the prevalence of emotions across text and images and measure the degree to which generative AI models tend to over-represent specific emotions in the resulting images. Findings indicate that AI-generated images from Stable Diffusion models are biased towards producing images that evoke fear, regardless of the original prompt, as metrics show a significant over-representation of that emotion compared to five other emotions. We extend this analysis to a more recent enterprise-level models, such as ChatGPT and Gemini, and find similar results, suggesting a systemic bias rather than one present only in a single model. While certain limitations in the alignment of emotions across modalities limit this work, the emotional skew we find in generative models is consistent with an over-representation of fearful content in training data, and this bias could amplify negative affective content in digital spaces further, perpetuating its prevalence and impact.
Authors: Sicheng Feng, Keda Tao, Huan Wang
Abstract: Oracle pruning, which selects unimportant weights by minimizing the pruned train loss, has served as the foundation for most neural network pruning methods for over thirty-five years, while few (if any) have thought about how much the foundation really holds. This paper, for the first time, attempts to systematically examine its validity on deep neural networks through empirical correlation analyses and provides meta-framework reflections on the field of neural network pruning. Specifically, this paper focuses on the pruning algorithms with three stages: training, pruning, and retraining. We analyze the correlation in model performance before and after the retraining stage. Extensive experiments (37K models are trained) across a wide spectrum of models (LeNet5, VGG, ResNets, ViT, MLLM) and datasets (MNIST, CIFAR10/CIFAR100, ImageNet-1K, MLLM data) are conducted. For large-scale experiments, we adopt approximate oracle pruning due to the prohibitive cost of exact oracle pruning. The results point to a counterintuitive conclusion: for deep learning models of nontrivial size (already at the scale of ResNet56 on CIFAR-10), pre-retraining performance is negligibly correlated with post-retraining performance. In other words, the weights identified by oracle pruning can scarcely guarantee strong performance following retraining. This further suggests that existing works that derive pruning criteria from oracle pruning may rest on a questionable foundational premise. Further studies suggest that rising task complexity is a primary factor behind the invalidity of oracle pruning nowadays. Finally, given the evidence, we argue that the retraining stage in a pruning algorithm should be accounted for when developing pruning criteria.
Authors: Michael W. Spratling, Heiko H. Sch\"utt
Abstract: Training deep neural networks (DNNs) on classification tasks can be performed with a number of different losses, but cross-entropy (CE) loss is the de-facto standard. Here, we propose an alternative loss, high error margin (HEM), which is a margin based loss modified to improve the training dynamics of neural networks. HEM loss is evaluated extensively using a wide range of DNN architectures and benchmark datasets with all experimental settings and training hyper-parameters taken from the literature, and hence, optimised for CE loss. HEM is found to be more effective than CE loss across a range of image-based tasks: unknown class rejection, adversarial robustness, learning with imbalanced data, continual learning, and semantic segmentation (a pixel-wise classification task). HEM is inferior to CE only in terms of clean and corrupt image classification with balanced training data, and this difference is small. We also compare HEM to specialised losses that have previously been proposed to improve performance for specific vision tasks. LogitNorm, a loss achieving state-of-the-art performance on unknown class rejection, produces similar performance to HEM for this task, but is much poorer for continual learning and semantic segmentation. Logit-adjusted loss, designed for imbalanced data, has superior results to HEM for that task, but performs worse on unknown class rejection and semantic segmentation. DICE, a popular loss for semantic segmentation, is inferior to HEM loss on all tasks, including semantic segmentation. Overall, HEM is competitive with the best alternative loss for all the tasks we have used and performs better than all other tested losses in terms of rejecting out-of-distribution examples, for continual learning, and by a substantial margin for semantic segmentation.
Authors: Maziar Sabouri, Ghasem Hajianfar, Alireza Rafiei Sardouei, Milad Yazdani, Azin Asadzadeh, Soroush Bagheri, Mohsen Arabi, Seyed Rasoul Zakavi, Emran Askari, Atena Aghaee, Sam Wiseman, Dena Shahriari, Habib Zaidi, Arman Rahmim
Abstract: Thyroid scintigraphy is vital for diagnosing thyroid disorders, yet deep learning (DL) models in this domain often struggle with limited, imbalanced datasets. This study investigates the impact of three data augmentation strategies including Stable Diffusion (SD), Flow Matching (FM), and Conventional Augmentation (CA), on enhancing DL-based classification of disease. Anterior thyroid scintigraphy images from 2,954 patients across nine medical centers were classified into four categories: Diffuse Goiter (DG), Nodular Goiter (NG), Normal (NL), and Thyroiditis (TI). Data augmentation was performed using CA as well as various SD and FM models, creating 18 distinct scenarios. Each augmented dataset was used to train a ResNet18 DL-classifier. Model performance was assessed using class-wise and average precision, recall, F1-score, AUC, and image fidelity metrics (FID and KID). FM-based methods demonstrated top-tier performance, with the Original dataset combined with FM (O+FM) configuration achieving the highest micro, macro, and weighted F1-scores (0.78, 0.77, 0.78) and AUC values (0.95, 0.93, 0.94). While the O+FM+CA model also yielded excellent, balanced results, O+FM was statistically superior, indicating that high-fidelity generative augmentation can supersede conventional heuristics. FM also produced the most realistic images, achieving the lowest overall FID (0.66) and KID (0.83). Among the SD variants, SD1 combining image and prompt inputs was the most effective (macro F1: 0.76; FID: 4.17), showing that physician-generated prompts provide critical clinical context. Integrating FM and clinically-informed SD augmentation substantially improves thyroid scintigraphy classification, highlighting the importance of advanced generative models for robust training on limited datasets. The code is available at: https://github.com/MaziarSabouri/Stable-Diffusion-Scintigraphy-Augmentation
URLs: https://github.com/MaziarSabouri/Stable-Diffusion-Scintigraphy-Augmentation
Authors: Junyu Chen, Shuwen Wei, Joel Honkamaa, Pekka Marttinen, Hang Zhang, Min Liu, Yichao Zhou, Zuopeng Tan, Zhuoyuan Wang, Yi Wang, Hongchao Zhou, Shunbo Hu, Yi Zhang, Qian Tao, Lukas F\"orner, Thomas Wendler, Bailiang Jian, Benedikt Wiestler, Tim Hable, Jin Kim, Dan Ruan, Frederic Madesta, Thilo Sentker, Wiebke Heyer, Lianrui Zuo, Yuwei Dai, Jing Wu, Jerry L. Prince, Harrison Bai, Yong Du, Yihao Liu, Alessa Hering, Reuben Dorent, Lasse Hansen, Mattias P. Heinrich, Aaron Carass
Abstract: Medical image challenges have played a transformative role in advancing the field, catalyzing innovation and establishing new performance benchmarks. Image registration, a foundational task in neuroimaging, has similarly advanced through the Learn2Reg initiative. Building on this, we introduce the Large-scale Unsupervised Brain MRI Image Registration (LUMIR) challenge, a next-generation benchmark for unsupervised brain MRI registration. Previous challenges relied upon anatomical label maps, however LUMIR provides 4,014 unlabeled T1-weighted MRIs for training, encouraging biologically plausible deformation modeling through self-supervision. Evaluation includes 590 in-domain test subjects and extensive zero-shot tasks across disease populations, imaging protocols, and species. Deep learning methods consistently achieved state-of-the-art performance and produced anatomically plausible, diffeomorphic deformation fields. They outperformed several leading optimization-based methods and remained robust to most domain shifts. These findings highlight the growing maturity of deep learning in neuroimaging registration and its potential to serve as a foundation model for general-purpose medical image registration.
Authors: Artur Grigorev, Adriana-Simona Mihaita
Abstract: Identifying locations that offer maximum visual exposure to passing vehicular traffic is a core problem in urban analytics, with applications spanning urban design, navigation, location-based services, and the placement of street-level assets. Traditional site selection methods often rely on static traffic counts or subjective assessments. This research introduces a data-driven methodology to objectively quantify location visibility by analyzing large-scale connected vehicle trajectory data within urban environments. We model the dynamic driver field-of-view using a forward-projected visibility area for each vehicle position derived from interpolated trajectories. By integrating this with building vertex locations extracted from OpenStreetMap, we quantify the cumulative visual exposure, or ``visibility count'', for thousands of potential points of interest along roadways. The core technical contribution involves the construction of a BallTree spatial index over building vertices. This enables highly efficient (O(logN) complexity) radius queries to determine which vertices fall within the viewing circles of millions of trajectory points across numerous trips, significantly outperforming brute-force geometric checks. Analysis reveals two key findings: 1) Visibility is highly concentrated, identifying distinct 'visual hotspots' receiving disproportionately high exposure compared to average locations. 2) The aggregated visibility counts across vertices conform to a Log-Normal distribution.
Authors: Wenbo Cui, Chengyang Zhao, Yuhui Chen, Haoran Li, Zhizheng Zhang, Dongbin Zhao, He Wang
Abstract: The spatial information inherent in 3D point clouds is crucial for robotic manipulation. However, existing 3D pre-training methods face a fundamental trade-off: Masked Autoencoding (MAE) excels at capturing spatial-geometric features but lacks semantics, whereas contrastive learning, while able to distill semantics from 2D foundation models, is ill-suited for the fine-grained details required for manipulation tasks. To address these challenges, we propose CLAR, a novel 3D pre-training framework that synergizes global understanding with fine-grained local alignment. Our framework unifies MAE with global cross-modal contrastive learning to integrate robust spatial awareness with rich semantic understanding. To enhance its focus on fine-grained details, at the local level, we introduce an adaptive alignment mechanism that leverages deformable attention to force precise correspondences between local 3D geometry and 2D visual features, thereby overcoming the limitations of conventional global alignment in manipulation tasks. Extensive experiments in simulation and the real world demonstrate that CLAR achieves state-of-the-art performance, significantly outperforming existing methods in visuomotor policy learning.
Authors: Gal Lifshitz, Shahar Zuler, Ori Fouks, Dan Raviv
Abstract: End-to-end deep learning has achieved impressive results but remains limited by its reliance on large labeled datasets, poor generalization to unseen scenarios, and growing computational demands. In contrast, classical optimization methods are data-efficient and lightweight but often suffer from slow convergence. While learned optimizers offer a promising fusion of both worlds, most focus on first-order methods, leaving learned second-order approaches largely unexplored. We propose a novel learned second-order optimizer that introduces a trainable preconditioning unit to enhance the classical Symmetric-Rank-One (SR1) algorithm. This unit generates data-driven vectors used to construct positive semi-definite rank-one matrices, aligned with the secant constraint via a learned projection. Our method is evaluated through analytic experiments and on the real-world task of Monocular Human Mesh Recovery (HMR), where it outperforms existing learned optimization-based approaches. Featuring a lightweight model and requiring no annotated data or fine-tuning, our approach offers strong generalization and is well-suited for integration into broader optimization-based frameworks.
Authors: Maysam Behmanesh, Erkan Turan, Maks Ovsjanikov
Abstract: Graph alignment, the problem of identifying corresponding nodes across multiple graphs, is fundamental to numerous applications. Most existing unsupervised methods embed node features into latent representations to enable cross-graph comparison without ground-truth correspondences. However, these methods suffer from two critical limitations: the degradation of node distinctiveness due to oversmoothing in GNN-based embeddings, and the misalignment of latent spaces across graphs caused by structural noise, feature heterogeneity, and training instability, ultimately leading to unreliable node correspondences. We propose a novel framework employing a dual-pass encoder to inject high-frequency discriminability into node features, paired with a geometry-aware functional map module that learns bijective and isometric transformations to align latent spaces while acting as a low-pass filter on correspondences, enforcing smoothness and robustness as a structural prior in map space. Extensive experiments on graph benchmarks demonstrate that our method consistently outperforms existing unsupervised alignment baselines, exhibiting superior robustness to structural inconsistencies and challenging alignment scenarios. The implementation is available at https://github.com/maysambehmanesh/GADL.
Authors: Sung-Yeon Park, Adam Lee, Juanwu Lu, Can Cui, Luyang Jiang, Rohit Gupta, Kyungtae Han, Ahmadreza Moradipari, Ziran Wang
Abstract: Driving scene manipulation using real-world sensor data has emerged as a promising alternative to traditional driving simulators. Despite advances in language control and neural scene representations, existing methods treat grounding, editing, and simulation as loosely connected stages, relying on heuristic object localization, manual guidance, and single-agent validation, thereby constraining semantic expressiveness and hindering scalable, reactive scenario generation. We introduce SIMSplat, a driving scene editor built on scene-graph-based 4D Gaussian Splatting augmented with language-aligned features. By embedding appearance, motion, and location semantics directly into Gaussian scene-graph nodes, SIMSplat makes reconstructed scenes queryable through free-form natural language, bridging language understanding to object-level editing and multi-agent simulation within a single framework. Building on this language-grounded scene graph, SIMSplat supports diverse edits including fine-grained pedestrian manipulation, while a multi-agent path refinement module propagates changes across all agents to ensure reactive, physically plausible simulations. The pipeline further integrates with Vision-Language Models for automated scenario mining. Experiments show that SIMSplat more than doubles baseline grounding accuracy, achieves the highest task completion rate, and produces the lowest failure rates across diverse driving scenarios.
Authors: Jinda Du, Jieji Ren, Qiaojun Yu, Ningbin Zhang, Yu Deng, Xingyu Wei, Yufei Liu, Guoying Gu, Xiangyang Zhu
Abstract: Dexterous robotic hands are expected to perform complex, contact-rich object manipulation, but learning such skills remains challenging because high-dimensional hands require high-fidelity demonstrations. Imitation learning provides a practical route for acquiring dexterous manipulation skills from human demonstrations, yet collecting synchronized multimodal demonstrations with accurate hand actions and tactile observations remains a key bottleneck. We present MILE, a teleoperation-based data-collection system comprising the human-first MILE exoskeleton and the mechanically corresponding MILE-Tac robotic hand. The system integrates custom-designed and fabricated modular joint encoders and compact MILE fingertip visuotactile sensor modules. The exoskeleton is informed by human-hand anatomy and ergonomic constraints, while the robotic hand is co-designed to preserve the selected four-finger kinematic topology. This correspondence enables joint-space command transfer and reduces reliance on task-space IK-based retargeting. The system synchronously records task-specific visual observations, four fingertip visuotactile streams, robot-hand proprioception, and exoskeleton-derived action commands. We evaluate MILE through a four-task teleoperation benchmark against representative glove-based and vision-based interfaces, and through imitation-learning experiments that compare policies trained with and without fingertip tactile input. The project page is available at https://sites.google.com/view/mile-system.
Authors: Sungwoo Kang
Abstract: Background: Smartphone-based dermatology requires inter-device colorimetric reliability that holds across calibration regimes, yet quantitative multi-device benchmarks remain scarce. Materials and Methods: We analyzed matched facial images from 965 Korean subjects captured by a digital single-lens reflex (DSLR) camera, a consumer tablet, and a consumer smartphone, and evaluated two calibration methods against the DSLR reference. The methods are standard global linear Color Correction Matrix (CCM) normalization and region-specific CCM trained per anatomical region, both applied in Commission Internationale de l'Eclairage Lab* (CIELAB) space. Results: Linear CCM reduced inter-device color differences by 61-74% and placed both Melanin Index (intraclass correlation coefficient [ICC] = 0.80) and Individual Typology Angle (ITA, ICC = 0.78) in the good reliability band. Region-specific CCM raised both indices into the excellent reliability band (MI ICC = 0.95, ITA ICC = 0.93), with anatomical region exceeding the source device as the largest pre-calibration variance contributor (analysis-of-variance $\eta^2 = 0.18$ versus 0.12). Conclusion: Consumer-device skin colorimetry therefore achieves clinically useful inter-device reliability using standard calibration, with region-aware calibration the largest remaining source of improvement.
Authors: Youngjoong Kim, Duhoe Kim, Woosung Kim, Jaesik Park
Abstract: Consistency models have been proposed for fast generative modeling, achieving results competitive with diffusion and flow models. However, these methods exhibit inherent instability and limited reproducibility when training from scratch, motivating subsequent work to explain and stabilize these issues. While these efforts have provided valuable insights, the explanations remain fragmented, and the theoretical relationships remain unclear. In this work, we provide a theoretical examination of consistency models by analyzing them from a flow map-based perspective. This joint analysis clarifies how training stability and convergence behavior can give rise to degenerate solutions. Building on these insights, we revisit self-distillation as a practical remedy for certain forms of suboptimal convergence and reformulate it to avoid excessive gradient norms for stable optimization. We demonstrate that our strategy extends beyond image generation to diffusion-based policy learning, without reliance on pretrained diffusion models for initialization, illustrating its broader applicability.
Authors: Mengting Wei, Aditya Gulati, Guoying Zhao, Nuria Oliver
Abstract: Synthetic faces from text-to-image (T2I) models pervade digital media, yet their demographic biases under emotionally conditioned prompts remain poorly understood. We aim to systematically audit how emotionally conditioned prompts affect demographic and perceived-attractiveness biases in synthetic faces generated by T2I models, with particular attention to intersectional patterns and cross-ecosystem differences across model families. We audited eight (4 Western and 4 Chinese) T2I models and generated 56,000 faces under seven prompt conditions: a neutral baseline and six emotion conditions. We quantified biases in gender, race, age, and perceived attractiveness using information-theoretic divergence metrics. We further conducted intersectional analyses across combined demographic attributes and compared patterns between the Western and Chinese model groups to assess cross-ecosystem consistency and divergence in bias behavior. All models show strong overrepresentation of young faces, and most also overrepresent White-coded individuals. Intersectional analysis reveals compound underrepresentation or near-erasure of specific demographic combinations, such as young x female x Black faces, which are largely absent across models and are not captured by single-attribute audits. Emotion prompts act as additional demographic selectors: negatively valenced emotions (including sadness and fear) consistently shift outputs toward White, middle-aged, male-coded faces. This produces a valence-driven mapping that is also associated with lower perceived attractiveness in generated faces. These findings indicate that demographic bias in T2I face generation is both pervasive and shaped by emotional conditioning. They underscore the need for intersectional, emotion-conditioned, and multilingual demographic audits as part of standard pre-deployment evaluation practices.
Authors: Anika Shrivastava, Renu Rameshan, Samar Agnihotri
Abstract: Masked Autoencoders (MAEs) achieve impressive performance in image classification tasks, yet the internal representations they learn remain less understood. This work started as an attempt to understand the strong downstream classification performance of MAE. In this process we discover that representations learned with the pretraining and fine-tuning, are quite robust -- demonstrating a good classification performance in the presence of degradations, such as blur and occlusions. Through layer-wise analysis of token embeddings, we show that pretrained MAE progressively constructs its latent space in a class-aware manner across network depth: embeddings from different classes lie in subspaces that become increasingly separable. We further observe that MAE exhibits early and persistent global attention across encoder layers, in contrast to standard Vision Transformers (ViTs). To quantify feature robustness, we introduce two sensitivity indicators: directional alignment between clean and perturbed embeddings, and head-wise retention of active features under degradations. These studies help establish the robust classification performance of MAEs.
Authors: Tiago Assis, Colin P. Galvin, Joshua P. Castillo, Nazim Haouchine, Marta Kersten-Oertel, Zeyu Gao, Mireia Crispin-Ortuzar, Stephen J. Price, Thomas Santarius, Yangming Ou, Sarah Frisken, Nuno C. Garcia, Alexandra J. Golby, Reuben Dorent, Ines P. Machado
Abstract: Accurate compensation of brain deformation is critical for reliable image-guided neurosurgery. Surgical manipulation and tumor resection induce tissue motion, causing preoperative planning images to become misaligned with the intraoperative anatomy. In this review, we examine methods developed between 2020 and 2025 for modeling and correcting brain deformation, with a particular focus on learning-based approaches. A comprehensive literature search was conducted in PubMed, IEEE Xplore, Scopus, and Web of Science, with predefined inclusion and exclusion criteria focused on computational methods applied to brain deformation compensation for neurosurgical imaging, resulting in $46$ studies meeting these criteria. We provide a unified analysis of methodological strategies, including deep learning-based image registration, direct deformation field regression, synthesis-driven multimodal alignment, resection-aware architectures addressing missing correspondences, and hybrid models that integrate biomechanical priors. We also examine dataset utilization, reported evaluation metrics, validation protocols, and how uncertainty and generalization have been assessed across studies. While learning-based deformation models demonstrate promising performance and computational efficiency, current approaches exhibit limitations in out-of-distribution robustness, standardized benchmarking, interpretability, and readiness for clinical deployment. Our review highlights these gaps and outlines opportunities for future research aimed at achieving more robust, generalizable, and clinically translatable deformation compensation solutions for neurosurgical guidance. By organizing recent advances and critically assessing evaluation practices, this work offers a comprehensive reference for researchers and clinicians working on data-driven brain deformation modeling and correction.
Authors: Arushi Goel, Sreyan Ghosh, Vatsal Agarwal, Nishit Anand, Kaousheik Jayakumar, Lasha Koroshinadze, Yao Xu, Katie Lyons, James Case, Karan Sapra, Kevin J. Shih, Siddharth Gururani, Abhinav Shrivastava, Ramani Duraiswami, Dinesh Manocha, Andrew Tao, Bryan Catanzaro, Mohammad Shoeybi, Wei Ping
Abstract: Multimodal Large Language Models (MLLMs) have shown strong performance in visual and audio understanding when evaluated in isolation. However, their ability to jointly reason over omni-modal (visual, audio, and textual) signals in long and complex videos remains largely unexplored. We introduce MMOU, a new benchmark designed to systematically evaluate multimodal understanding and reasoning under these challenging, real-world conditions. MMOU consists of 20,000 carefully curated questions paired with 11877 web-collected videos of varying length, spanning diverse domains and exhibiting rich, tightly coupled audio-visual content. The benchmark covers 13 fundamental skill categories, all of which require integrating evidence across modalities and time. All questions are manually annotated across multiple turns by professional annotators, ensuring high quality and reasoning fidelity. We evaluate 20+ state-of-the-art open-source and proprietary multimodal models on MMOU. The results expose substantial performance gaps: the best closed-source model achieves only 64.2% accuracy, while the strongest open-source model reaches just 46.8%. Our results highlight the challenges of long-form omni-modal understanding, revealing that current models frequently fail to apply even fundamental skills in long videos. Through detailed analysis, we further identify systematic failure modes and provide insights into where and why current models break.
Authors: Lubin Gan, Jing Zhang, Heng Zhang, Xin Di, Zhifeng Wang, Wenke Huang, Xiaoyan Sun
Abstract: Whole slide image (WSI) analysis heavily relies on multiple instance learning (MIL). While recent methods benefit from large-scale foundation models and advanced sequence modeling to capture long-range dependencies, they still struggle with two critical issues. First, directly applying frozen, task-agnostic features often leads to suboptimal separability due to the domain gap with specific histological tasks. Second, relying solely on global aggregators can cause over-smoothing, where sparse but critical diagnostic signals are overshadowed by the dominant background context. In this paper, we present ReconMIL, a novel framework designed to bridge this domain gap and balance global-local feature aggregation. Our approach introduces a Latent Space Reconstruction module that adaptively projects generic features into a compact, task-specific manifold, improving boundary delineation. To prevent information dilution, we develop a bi-stream architecture combining a Mamba-based global stream for contextual priors and a CNN-based local stream to preserve subtle morphological anomalies. A scale-adaptive selection mechanism dynamically fuses these two streams, determining when to rely on overall architecture versus local saliency. Evaluations across multiple diagnostic and survival prediction benchmarks show that ReconMIL consistently outperforms current state-of-the-art methods, effectively localizing fine-grained diagnostic regions while suppressing background noise. Visualization results confirm the models superior ability to localize diagnostic regions by effectively balancing global structure and local granularity.
Authors: Jongbin Lim, Taeyun Ha, Mingi Choi, Jisoo Kim, Byungjun Kim, Subin Jeon, Hanbyul Joo
Abstract: We present HRDexDB, a paired cross-embodiment dexterous grasping dataset of high-fidelity dexterous grasping sequences featuring both human and diverse robotic hands. Unlike existing datasets, HRDexDB provides a comprehensive collection of grasping trajectories across human hands and multiple robot hand embodiments, spanning 100 diverse objects. Leveraging state-of-the-art vision methods and a dedicated multi-camera system, HRDexDB offers high-precision spatiotemporal 3D ground-truth motion for both the agent and the manipulated object. The dataset comprises 2.1K grasping trials, each enriched with synchronized visual and kinematic modalities, with contact-force signals available for tactile-enabled robotic hands. By providing closely aligned captures of human dexterity and robotic execution on the same target objects under comparable grasping motions, HRDexDB serves as a foundational benchmark for cross-embodiment dexterous manipulation.
Authors: Chaoshuo Zhang, Yibo Liang, Mengke Tian, Chenhao Lin, Zhengyu Zhao, Le Yang, Chong Zhang, Yang Zhang, Qian Wang, Chao Shen
Abstract: Text-to-image (T2I) models are increasingly optimized for following user instructions faithfully. However, we find that this capability introduces a safety vulnerability we call Multi-Concept Compositional Unsafety (MCCU). MCCU occurs when multiple individually safe concepts, if combined in a single generation request, lead to harmful or sensitive visual outputs. Unlike prior jailbreak settings, MCCU does not rely on adversarial prompts, model access, or explicitly disallowed content. Instead, the risk emerges from how the model composes multiple safe visual concepts into a single scene. To systematically measure this threat, we build TwoHamsters, a large-scale evaluation framework consisting of 20k prompts, 51 curated concept pairs, and six risk categories. We evaluate 13 T2I models under a black-box setting. Our results show a clear conflict between instruction-following and safety: models that follow prompts more faithfully tend to produce more MCCU failures. For example, FLUX.1 achieves a 99.35% Unsafe Alignment Rate while only reaching a 1.57% MCCU Defense Rate. We further evaluate three representative defenses, including safety filtering, MCCU-specific detector fine-tuning, and concept erasure, all of which fail against unseen concept combinations. Our findings suggest that compositional reasoning in T2I models creates an attack surface that is not captured by existing safety mechanisms. We anticipate the release of TwoHamsters will catalyze community development of advanced generative defense mechanisms.
Authors: Jiaming Li, Chenyu Zhu, Nanxi Yi, Youjun Bao, Li Sun, Quanying Lv, Xiang Fang, Daizong Liu, Jianjun Li, Kun He, Bowen Zhou, Zhiyuan Ma
Abstract: Reinforcement learning (RL) has shown extraordinary potential in aligning diffusion models to downstream tasks, yet most of them still suffer from significant reward hacking, which degrades generative diversity and quality by inducing visual mode collapse and amplifying unreliable rewards. We identify the root cause as the mode-seeking nature of these methods, which maximize expected reward without effectively constraining probability distribution over acceptable trajectories, causing concentration on a few high-reward paths. In contrast, we propose Trajectory Matching Policy Optimization (TMPO), which replaces scalar reward maximization with trajectory-level reward distribution matching. Specifically, TMPO introduces a Softmax Trajectory Balance (Softmax-TB) objective to match the policy probabilities of K trajectories to a reward-induced Boltzmann distribution. We prove that this objective inherits the mode-covering property of forward KL divergence, preserving coverage over all acceptable trajectories while optimizing reward. To further reduce multi-trajectory training time on large-scale flow-matching models, TMPO incorporates Dynamic Stochastic Tree Sampling, where trajectories share denoising prefixes and branch at dynamically scheduled steps, reducing redundant computation while improving training effectiveness. Extensive results across diverse alignment tasks such as human preference, compositional generation and text rendering show that TMPO improves generative diversity over state-of-the-art methods by 9.1%, and achieves competitive performance in all downstream and efficiency metrics, attaining the optimal trade-off between reward and diversity.
Authors: S. Sutharya, Remya K. Sasi
Abstract: Audio deepfake detection is well-studied as a binary problem, but partially manipulated speech, where a short synthesised segment is spliced into an otherwise genuine utterance, poses a harder and more realistic threat. Detecting such half-truth audio requires not only distinguishing it from real and fully fake speech, but also localising where the manipulation occurs. We present CAFNet, a 576k-parameter architecture that addresses both tasks jointly: it performs ternary classification (real, fully-fake, or half-truth) and regresses the temporal boundaries of the synthesised region in a single forward pass. CAFNet fuses Mel-Frequency Cepstral Coefficient (MFCC), Linear-Frequency Cepstral Coefficient (LFCC), and Chroma Short-Time Fourier Transform (Chroma-STFT) features through parallel depthwise-separable convolution branches with cross-attention, followed by a Bidirectional Long Short-Term Memory (BiLSTM) regression head for boundary prediction. On the combined Multi-Lingual Audio Deepfake Detection Corpus (MLADDC) T2+T3 test set, CAFNet achieves 92.71% accuracy and macro Area Under the Curve (AUC) of 0.9910, with boundary localisation Mean Absolute Error (MAE) of 0.075s and a median error of 0.052s. On binary detection, it achieves 96.76% accuracy and 3.20% Equal Error Rate (EER), outperforming fine-tuned XLS-R 300M (78.31%) and AST 87M (93.03%) at over 500 times fewer parameters. A cross-dataset study further shows that standard fine-tuning collapses cross-domain representations even under reduced backbone learning rates.
Authors: \"Umit Mert \c{C}a\u{g}lar, Alptekin Temizel
Abstract: Semantic segmentation of remote sensing imagery requires models that capture both global context and local detail under tight computational budgets. Prior work typically optimizes for one of these axes: attention for global context, convolution for local detail, or compactness for efficiency. While hybrid approaches aim to capture both, they require architectural changes and encoder backbones with computational overhead, limiting efficiency and performance. We present LALE (Lightweight-transformer Architecture for Land-cover Estimation), an end-to-end remote sensing image segmentation architecture, that bifurcates its encoder by resolution: lightweight ConvMixer stages handle high-resolution local features, while transformer stages handle low-resolution global context, confining the quadratic cost of self-attention to deep, downsampled feature maps. An all-MLP multi-scale decoder, together with RMSNorm and StarReLU throughout, further reduces compute and parameter count. On the large-scale ARAS400k remote-sensing segmentation benchmark, LALE establishes a strong efficiency-performance trade-off against CNN, transformer, and hybrid baselines. Our smallest variant, (just 1.6M parameters), reaches within 2.6 F1 points of the best baseline (UPerNet) while using 4.5x fewer parameters, 7x less storage, 17x fewer GMACs, and delivering 1.8x higher throughput. The codebase for LALE is publicly available at https://github.com/caglarmert/LALE.
Authors: Ting-An Chen, Chin-Yuan Yeh, De-Nian Yang
Abstract: Quantizing deep neural networks is essential for efficient inference on resource-constrained devices. However, most existing methods are designed for single-domain and class-balanced data, leaving practical settings with domain shifts or severe class imbalance underexplored. We address these challenges with Efficient Multi-Domain Alignment Quantization (EmaQ), which aligns domain distributions through a CDF-based projection and uses sensitivity-aware weight aggregation to stabilize multi-domain quantization. We further extend EmaQ to EmaQ-LT for long-tailed quantization by introducing class-conditioned variance scaling and confidence-based logit adjustment to mitigate majority-class overconfidence. Theoretical analyses establish convergence guarantees and motivate the proposed sensitivity and scaling mechanisms. Experiments on standard, multi-domain (Office-31, Digits), and long-tailed (SynDigits-LT, CIFAR-10-LT, CIFAR-100-LT) benchmarks show that EmaQ and EmaQ-LT achieve strong low-bit performance under domain shift and class imbalance.
Authors: Jamal Seyedmohammadi, Pai Chet Ng, Angelo Genovese, Zhixiang Chi, Jeannie Lee, Konstantinos N. Plataniotis
Abstract: Palmprint modality offers a privacy-preserving biometric solution, yet its deployment is hindered by the domain gap between controlled enrollment and unconstrained authentication. Existing datasets are largely restricted to controlled setups and fail to capture the compound variability of real-world environments. In this paper, we introduce X-Palm, a cross-domain dataset comprising 6,006 palm images from 103 individuals (206 hands). To the best of our knowledge, X-Palm is the first palmprint dataset providing novel paired-identity acquisition specifically designed to bridge the gap between reliably controlled multispectral enrollment and unconstrained mobile authentication while encompassing a broad spectrum of in-the-wild variability. Unlike existing datasets that focus on single to a few variations, X-Palm addresses the massive modality and environmental shifts encountered in practical deployments by capturing paired data for identities across two distinct domains: (1) a controlled Multispectral Palmprint setting using our custom-developed scanner, and (2) an unconstrained smartphone palmprint setting that is participant-driven, incorporating simultaneous variations in hardware, hand pose, illumination, background, camera-to-hand distance, perspective, and palm surface conditions (e.g., moisture and occlusions). Our extensive benchmarks of 12 SOTA models reveal that while existing methods achieve high performance on controlled data, they experience severe performance collapse on X-Palm. Conversely, models trained on X-Palm demonstrate consistent robustness across domains, positioning X-Palm as a valuable resource for training a model towards real-world, cross-domain generalization. Data access instructions and the related benchmarking codes are publicly available at: https://github.com/X-Palm/X-Palm-2026
Authors: Anju Chhetri, Pratik Shrestha, Ramesh Rana, Sam Philip, Prashnna Gyawali, Binod Bhattarai
Abstract: Deep neural networks have achieved remarkable performance across medical imaging tasks, yet their tendency to overgeneralize under distributional shifts poses a major obstacle to safe clinical deployment. Out-of-Distribution (OOD) detection methods aim to mitigate this risk, but most existing approaches rely on opaque internal signals with poorly understood semantic meaning, limiting trust in safety-critical settings. In this work, we propose an interpretable OOD detection framework that probes the stability of model predictions under class-conditioned semantic perturbations. Leveraging sparse autoencoders (SAEs), we learn class-specific concept vectors from in-distribution data that disentangle dense intermediate representations into sparse, semantically meaningful components. At inference, we perturb deeper-layer representations using the concept vectors associated with the model's predicted class and measure the class logits stability. We hypothesize that in-distribution samples exhibit low sensitivity to such perturbations, as their representations align with class-specific semantic directions, whereas OOD samples show amplified deviations due to representational misalignment. By framing OOD detection as a concept conditioned stability analysis, our approach provides both a discriminative OOD signal and an interpretable lens into the internal mechanisms driving model uncertainty, making it particularly suitable for high stakes medical applications.
Authors: Sihan Wang, Xiyao Liu, Lianqing Liu, Zhi Han
Abstract: On-policy self-distillation (OPSD) trains a model on its own rollouts and uses a frozen copy to provide dense token-level targets conditioned on a reference target. This works well for LLM reasoning, but a direct extension to multimodal large language models (MLLMs) can create a shortcut: the privileged target may guide tokens mainly based on the text reference target rather than the image. We propose ViGOS, a visually grounded OPSD framework for MLLM post-training. The student first writes a visual description and then reasons toward the final answer. For valid rollouts, an image-only perception teacher supervises the description, while a privileged reasoning teacher supervises the reasoning and final answer on the same student prefix. A reference teacher is used only for invalid rollouts to recover the output format. Across general vision-language, expert reasoning, visual math, spatial grounding, and visual-language-prior benchmarks, ViGOS keeps the main benefits of OPSD and improves image-grounded behavior in shortcut-prone settings.
Authors: Luke Rowe, Roger Girgis, Rodrigue de Schaetzen, Daphne Cornelisse, Alaap Grandhi, Felix Heide, Eugene Vinitsky, Christopher Pal, Liam Paull
Abstract: End-to-end autonomous driving models are typically trained on offline human-demonstration datasets that provide limited state coverage and often no closed-loop feedback, making them prone to compounding errors when deployed in closed-loop and brittle to long-tail agent interactions. To overcome these limitations, we propose an alternative strategy for training end-to-end driving models: large-scale self-play directly from pixels in simulation. While prior self-play approaches have shown promising transfer to real-world driving, they typically assume vectorized Bird's-Eye-View (BEV) observations that are incompatible with end-to-end policies operating directly on sensor observations. To this end, we introduce Gigapixel, a high-throughput batched driving simulator with perspective rendering, enabling scalable self-play directly from pixel observations. Rather than targeting compute-costly photorealistic sensor simulation, Gigapixel renders a simplified bounding-box world that preserves essential scene structure while achieving throughput at 50k agent steps per second. Since direct pixel-space self-play RL is prohibitively sample-inefficient at end-to-end model scale, we propose self-play DAgger training: we train pixel-based policies in self-play via on-policy distillation from a privileged RL teacher. To bridge the sim-to-real gap, we subsequently transfer the self-play trained policies to real-world sensor data through lightweight perception adaptation. Policies trained in Gigapixel and adapted to real-world sensor data achieve competitive performance on the HUGSIM and NAVSIM-v2 benchmarks without human trajectory supervision. Moreover, scaling self-play training yields proportional gains in policy performance, establishing self-play as a practical and scalable strategy for training end-to-end models.
Authors: Nafis Fuad Shahid
Abstract: Conformal risk control (CRC) provides distribution-free guarantees on segmentation quality by calibrating a prediction-set threshold on held-out data. In federated deployments, the standard approach pools calibration scores across sites into a single threshold. We provide the first quantification, on real multi-institutional brain tumor data (FeTS-2022, 1,251 subjects, 20 institutions), showing that this naive pooled CRC protects the average hospital but violates coverage at 40% of individual institutions, with the worst site exceeding the target false-negative rate by 7.8 percentage points. The naive alternative, per-site local CRC, largely restores coverage but inflates prediction sets by 83x, rendering them clinically useless. We propose a shrinkage-based federated CRC protocol: each site transmits only its empirical risk curve (G scalars) to a server, which computes a shrinkage-regularized threshold per site. A single hyperparameter n0 smoothly trades worst-case coverage for prediction-set efficiency; leave-one-site-out sensitivity analysis identifies n0=19, achieving 2.7/20 violations at 2.0x stretch. We further show that direct Lagrangian optimization of coverage budgets fails, concentrating risk on vulnerable hospitals, and that the finite-sample correction term is essential: removing it triples violations. The marginal CRC guarantee is preserved by construction under the stated site-mixture assumption; per-site coverage is validated across four targets with three seeds. No patient-level images, masks, or per-volume scores leave any site.