Authors: Yiwei Li, Zihao Wu, Huaqin Zhao, Yifan Zhou, Chao Cao, Dajiang Zhu, Tianming Liu, Lin Zhao
Abstract: Radiologist eye-tracking data provide a rich record of how experts search, compare, and accumulate evidence during image reading; yet, existing methods exploit this signal only partially, either as a static spatial prior or as an auxiliary prediction target decoupled from diagnosis. We propose GazeWorld, a medical imaging world model that treats the image as the world and the radiologist's fixation sequence as a trajectory through it. GazeWorld autoregressively predicts the latent representation of the next fixated patch from all previously visited ones, while a spatial-completion branch covers unvisited regions. At inference, GazeWorld generates a sequence of patch representations from the image alone without requiring real gaze data. Frozen GazeWorld features achieve state-of-the-art diagnostic accuracy across all nine supervised settings on CheXpert, RSNA Pneumonia, and SIIM-ACR Pneumothorax, as well as the highest zero-shot accuracy on all three benchmarks. On the GazeSearch benchmark, a generic decoder trained on the same frozen features outperforms the purpose-built LogitGaze-Med by over 16\% in ScanMatch and 22\% in SED, despite not being explicitly trained to predict gaze. GazeWorld demonstrates that modeling how experts read, not just what they conclude, offers a promising pretraining paradigm for medical imaging AI.
Authors: Siqiao Huang, Partha Kaushik, Michael Chen, Hengkai Pan, Omar Chehab, Fernando Moreno-Pino, Max Simchowitz
Abstract: World models have become a central paradigm for learning predictive simulators that support generation, planning, and decision-making. Yet, despite rapid progress in industry-scale interactive video generation, the broader research community still lacks compact, reproducible, and easily extensible implementations for studying the design choices underlying modern world models. We introduce Nano World Models, a minimalist codebase for future video prediction centered around diffusion forcing. Nano World Models provides a unified interface for generative objectives, model scales, action-conditioning mechanisms, latent observation spaces, datasets, evaluation protocols, and long-horizon rollout procedures. This design enables controlled studies of world-modeling components that are often entangled across separate implementations. Through experiments across simple control environments, game simulation, and real-robot data, we examine how prediction parameterization, architecture scale, action injection, sampling budget, and domain complexity affect video prediction quality and autoregressive rollout behavior. By releasing code, configurations, evaluation scripts, and pretrained checkpoints, Nano World Models aims to provide a compact yet extensible experimental substrate for open, reproducible, and scientific world-model research.
Authors: Jack Parry, Jack Saunders, Vinay Namboodiri
Abstract: Digital avatar watermarking presents unique challenges: avatars are routinely post-processed with background replacement, reframing, and format conversion before deployment. We introduce \textbf{RAW} (Robust Avatar Watermarking), a benchmark comprising 50 synthetic avatar videos from 5 commercial providers and 6 attacks simulating real-world avatar workflows. Evaluating 7 existing methods reveals that avatar-specific attacks such as background removal significantly degrade watermark recovery. We propose \textbf{WALT} (Watermarking Avatars with Learned Textures), which embeds watermarks in UV texture space via 3D face reconstruction. WALT achieves the highest robustness to zoom attacks (92.4\%) while maintaining strong performance on background removal (95.6\%). We release our benchmark to facilitate research into avatar-specific watermarking.
Authors: Chathura Wimalasiri
Abstract: Self-supervised learning (SSL) has emerged as a promising paradigm for addressing the annotation bottleneck in medical imaging by learning representations from unlabeled data. However, its effectiveness depends heavily on the design of the pretext task and its alignment with the downstream clinical objective. We present a systematic, task-oriented review of SSL in medical imaging, examining how different pretext-task formulations influence performance across classification, segmentation, detection, and other tasks. Following PRISMA guidelines, we analyze 75 studies published between 2017 and 2025 and organize them into four paradigms: contrastive, non-contrastive and predictive, generative and reconstruction-based, and hybrid learning. Rather than cataloguing methods by architecture, we map each paradigm to the downstream objectives it best supports. Our analysis shows there is no universally optimal SSL strategy; instead, performance is governed by the alignment between the pretext task, the imaging modality, and the target task. Contrastive methods learn global discriminative features and align well with classification, but may overlook subtle pathological patterns. Generative and spatial prediction-based approaches better preserve local anatomical structure, making them more suitable for segmentation and other dense prediction tasks, while hybrid methods offer the most balanced performance. We further show that modality-specific design is critical and that SSL provides its greatest benefit in low-label and few-shot regimes. Finally, we distill these findings into practical design guidelines and outline open challenges, including pathology-aware pretext task design, resource-efficient training for high-dimensional data, and standardized evaluation protocols. This work offers practical guidance for designing more effective and clinically relevant SSL frameworks in medical imaging.
Authors: Chi Kit Wong, Yan Liu, Haowen Yan
Abstract: We present a brain-to-image system that decodes visual stimuli from EEG signals recorded during natural image viewing. Our system addresses two tasks: (1) EEG-to-image retrieval, which ranks the correct stimulus image among 200 candidates given an EEG segment, and (2) EEG-to-image reconstruction, which generates an image consistent with the perceived stimulus. For retrieval, we implement a multi-level blurring approach improved with biologically inspired EVNet features and trained with the InfoNCE loss. Evaluated over 10 random seeds for a single subject, the retrieval model achieves a mean final-epoch Top-1 accuracy of 86.30% and Top-5 accuracy of 98.55%. For reconstruction, we implement CognitionCapturerPro, which aligns EEG representations to multi-modal CLIP embeddings, including image, text, depth, and edge embeddings, and synthesizes images with SDXL-Turbo conditioned via IP-Adapter. Averaged over 10 seeds, the reconstruction model achieves a CLIP score of 0.903 using ViT-H-14, a CLIP score of 0.870 using ViT-L/14, and an SSIM of 0.409. These results demonstrate the feasibility of decoding rich visual representations from EEG signals using modern multi-modal alignment and generative modeling techniques.
Authors: Chenghao Li, Fusheng Hao, Xikai Zhang, Likang Xiao, Yanwei Ren, Fuxiang Wu, Quan Chen, Liu Liu
Abstract: Multimodal large language models via reinforcement learning (RL) have demonstrated remarkable capabilities in complex visual reasoning tasks, yet they remain limited in long-horizon multimodal scenarios, often suffering from visual hallucination and logical error. Current methods typically pre-encode high-dimensional visual scenes into discrete textual proxies to facilitate downstream reasoning. As the reasoning chain unfolds, however, the inherent information asymmetry between text and visual scenes tends to erode visual grounding, resulting in misguided reasoning and erroneous outputs. To address this issue, we introduce IVR-R1 (Iterative Visual-grounded Reasoning), a novel RL training framework that facilitates dynamic visual re-alignment that actively rectifies reasoning trajectories to guide policy optimization. Specifically, by leveraging a reward-driven screening mechanism to identify flawed rollouts, IVR-R1 executes a fine-grained, step-level error attribution within the multimodal context. By iteratively cross-referencing intermediate reasoning states against pristine visual priors, a Re-Reasoning Loop enables automated trajectory rectification, effectively synthesizing expert-level demonstrations that serve as high-fidelity reasoning templates for the policy model. Our experiments across diverse multimodal benchmarks demonstrate that IVR-R1 consistently outperforms existing reinforcement learning methods, establishing a superior paradigm for maintaining logical and visual consistency in complex multimodal reasoning.
Authors: Junyi Wu, Weijian Luo, Haoyang Zheng, Ruizhe Zhang, Guang Lin
Abstract: Recent advances in one-step text-to-image generation have enabled real-time synthesis with remarkable efficiency and quality. Previous reinforcement learning methods for one-step generators combine image-space reward optimization with diffusion noisy-space distribution matching. This paradigm brings challenges due to a mismatch between terminal reward optimization and the underlying generative dynamics. As a result, optimization tends to exploit stochastic degrees of freedom, often improving reward at the expense of image fidelity. To address this issue, we propose Diff-Instruct with Diffused Reward (DIDR), a data-free trajectory-level alignment framework derived from Integral KL minimization. DIDR propagates the RLHF-optimal reward-tilted clean-image distribution across all noise levels along the diffusion trajectory. We show that this objective admits the same minimizer as clean-image RLHF, while naturally inducing the Diffused Reward Score (DRS), which acts as a reward-driven correction to the reference score function. To make this practical, we further introduce the Diffused Reward Proxy (DRP), an efficient estimator of DRS based on differentiable short-step denoising. Extensive experiments demonstrate that DIDR consistently Pareto-dominates existing one-step SDXL baselines. Moreover, when transferred to a 6B DiT backbone (Z-Image), DIDR surpasses its 50-step teacher in preference alignment while requiring only a single generation step.
Authors: Shuang Liua, Fiona Johnson, Rohitash Chandra
Abstract: Remote sensing techniques have been increasingly utilised in aquatic applications in recent years. A common challenge in using optical satellite data is the presence of missing observations due to cloud cover. These data gaps can lead to missed detection of critical events, such as algal blooms, in lakes of high interest to water authorities. As a result, enhancing the completeness of optical satellite datasets is crucial for improving the monitoring and prediction of algal blooms. In this study, we compared a traditional data imputation method (i.e., linear interpolation) with deep learning models for reconstructing missing spectral bands across four lakes with historical records of algal blooms. The deep learning models adopted include CNN-based architectures (i.e., CNN, Inception Resnet, and Autoencoder) and CNN-LSTM-based architectures (i.e., CNN-LSTM, Resnet-LSTM, and Autoencoder-LSTM). Our results demonstrated that deep learning models substantially outperformed the baseline linear interpolation method in imputing spectral band values within artificially masked regions. Among these models, CNN delivered the best performance across most lakes. Furthermore, we evaluated the performance of algal bloom indices (i.e., Green/Red and NDCI) derived from the imputed imagery by comparing them with the observed data. Our results demonstrate that deep learning models are effective for imputing missing data in PlanetScope SuperDove imagery, enabling more reliable applications in water monitoring.
Authors: Arash Akbari, Arman Akbari, Masih Eskandar, Qitao Tan, Yixiao Chen, Jingwu Luo, Bertha Pangaribuan, Liyun Zhang, Jennifer Dy, Geng Yuan, Xue Lin, Gaowen Liu, Stratis Ioannidis, Yanzhi Wang
Abstract: Vision-Language-Action (VLA) models exhibit remarkable action generation for embodied intelligence, but their heavy compute make deployment on edge platforms impractical. Aggressive, sub-4-bit weight quantization is the natural solution, yet existing post-training quantization (PTQ) methods suffer severe performance degradation in this regime. To address this, we introduce ActQuant, an action-guided mixed-precision PTQ framework that operates in two stages: (1) an inter-tensor bit allocator that assigns each weight matrix a single bit-width based on how much it contributes to predicting the agent's actions; (2) an intra-tensor scale optimizer tunes per-block quantization scales using action-aware curvature, so that dynamic range is concentrated on the weights most influential for control. To deliver the on-device benefits of our aggressive quantization, we further introduce OmniModel.cpp, an agentic conversion pipeline that ports architectures into a native C/C++ runtime with efficient low-bit kernels. We evaluate ActQuant both in simulation and on a real-world 6-DoF UR3 arm, with all models deployed through OmniModel.cpp. On the LIBERO benchmark, ActQuant is the only method that operates at or below 3 bits-per-weight, retaining 95.0% on OpenVLA-OFT and 94.8% on $\pi_{0.5}$. Pushed further, ActQuant reaches 2.5 bpw at 90.1% on OpenVLA-OFT, compressing the backbone from 14.3 GB to 2.7 GB (5.3$\times$). On the physical UR3 arm, $\pi_{0.5}$ quantized with ActQuant retains the baseline's success rate while reducing the memory footprint by 2.5$\times$.
Authors: Si Li, Yuanqing He, Chenkai Hu, Xiaogang Guo, Huay-Cheem Tan, Chieh Yang Koo, Xuan Zhang, Lei He, Jingyuan Zeng, Shan Xiao
Abstract: Aims: Coronary microvascular dysfunction (CMVD) affects approximately 40%-60% of patients with ischemia and non-obstructive coronary arteries, yet diagnosis remains challenging due to reliance on invasive functional testing or subjective Thrombolysis In Myocardial Infarction (TIMI) flow grade. The TIMI Myocardial Perfusion Frame Count (TMPFC) offers an objective, angiography-based quantitative measure of CMVD, but its clinical translation is hindered by cumbersome manual calculation and insufficient validation. This study aims to develop and validate a deep learning-powered TMPFC calculation (DL-TMPFC), enabling integration into clinical workflows. Methods and results: DL-TMPFC framework comprised two components. A stenosis detection network first excluded obstructive coronary artery disease (CAD). A territory-aware segmentation network then identified perfusion territories and TMPFC calculation module automatically determined the first and last frames from angiographic sequences. The framework was validated in a cohort of 655 patients (445 of obstructive CAD, 100 of confirmed CMVD, 110 of control group) from three independent institutions. DL-TMPFC showed excellent agreement with expert manual measurements (bias: -0.93 frames; 95% LoA: -5.33 to +3.47; r =0.98). DL-TMPFC markedly enhanced clinical feasibility by fully automating TMPFC and removing observer dependence. Clinically, DL-TMPFC accurately identified CMVD across a full spectrum of coronary pathologies and captured the continuous severity of CMVD beyond binary classification, enabling quantitative risk stratification. Conclusion: DL-TMPFC enabled automatic, standardized, and accurate quantification of CMVD directly from routine angiography. By providing an automatic and objective measure, this tool provided immediate diagnostic information for timely recognition and management of CMVD in clinical practice.
Authors: Anqi Lu, Yun Cheng, Youbing Hu, Zhiqiang Cao, Jie Liu, Zhijun Li
Abstract: The demand for unmanned aerial vehicle (UAV)-based image acquisition and analysis has surged, with UAVs increasingly utilized for semantic segmentation tasks. To meet the real-time analysis requirements of UAV remote sensing missions, performing onboard computation and making decisions based on the results is a natural approach. However, deploying semantic segmentation on resource-constrained UAV platforms presents two significant challenges: 1) hardware constraints limit the ability of UAVs to perform real-time semantic segmentation, and 2) environmental variations during flight cause data distribution shifts, deviating from the original training data. To address these issues, this paper introduces SkySeg, a heterogeneous multi-UAV air-air cooperation framework that integrates computer vision and flight pattern to enable onboard semantic segmentation using low-cost sensors. SkySeg employs an efficient information fusion inference method, combining low-definition, wide-area images with high-definition, focused-area images. Additionally, it incorporates a cross-device test-time adaptation (TTA) strategy to enhance segmentation performance in dynamic environments by collaboratively addressing distribution shifts of test data streams across UAVs. Experimental results demonstrate that our SkySeg framework accelerates inference latency by approximately 3.6x, improves onboard segmentation accuracy by 5.91\%, and achieves a 10.91\% average accuracy gain in the wild.
Authors: Zhong Wang, Zukang Xu, Xing Hu, Dawei Yang
Abstract: Vision-Language Models (VLMs) achieve outstanding performance, yet their huge model size severely hinders deployment on edge devices with limited resources. As an efficient model compression technique, vector quantization (VQ) excels in ultra-low-bit representation, which maps model weights to discrete codewords in a compact codebook to cut memory consumption and transmission overhead while preserving model capability. Direct VQ application to VLMs still has two core limitations. First, cross-modality weight distribution differences brought by visual and textual inputs cannot be well fitted by a single unified codebook. Second, current second-order error compensation ignores first-order gradient information, causing weight deviation from pre-trained optimal states, gradient drift and biased compensation results. This work proposes MGVQ, a novel vector quantization framework integrating multi-dimensional sensitivity perception and gradient-Hessian fusion. It consists of two core modules: sensitivity-guided structured mixed-precision quantization dynamically assigns different bit-widths according to channel sensitivity via combined global and local sensitivity analysis for refined resource allocation; gradient-aware second-order error compensation embeds first-order gradients into error correction, and adopts Kronecker and Block-LDL decomposition to ensure low computational cost. Extensive experiments on mainstream VLMs including LLaVA-onevision, InternVL2 and Qwen2-VL verify the effectiveness of MGVQ. In 2-bit quantization settings, MGVQ surpasses existing advanced post-training quantization methods significantly, achieving a maximum accuracy improvement of 4.9 points (71.4% vs 67.0% on InternVL2-26B). The proposed method realizes stable and efficient ultra-low-bit VLM quantization, greatly promoting the practical deployment of multimodal large models in resource-limited environments.
Authors: Van Quang Nguyen
Abstract: Advancements at the intersection of computer vision and natural language processing are crucial for applications like assistive tech, multimedia querying, and robotics. This dissertation proposes novel architectures to improve intelligent agents across three key vision-language tasks: image captioning, visual dialog, and interactive instruction following. First, we address limitations in visual representation for image captioning. Traditional models rely on region-based features from CNN detectors, which lack global context and suffer from high computational overhead. We propose GRIT (Grid and Region-based Image captioning Transformer), a transformer-only architecture. By integrating grid and region features using a DETR-based detector, GRIT enables end-to-end training and out-performs prior methods in both inference accuracy and speed. Second, we tackle visual dialog, which requires multi-turn conversation about an image. The challenge lies in efficiently modeling interactions between multiple inputs (image, question, history). We introduce LTMI (Light-weight Transformer for Many Inputs). Utilizing a specialized attention block, an LTMI layer matches the representational power of a standard Transformer extension while utilizing less than one-tenth of its parameters, as validated on the VisDial dataset. Finally, we study interactive instruction-following for embodied AI using the ALFRED dataset. We propose a framework featuring a two-stage instruction interpretation: it first decodes language directives independently of visual context to predict a tentative action-object sequence, which is then fused with visual features for final execution. Using multiple egocentric views and hierarchical attention, our method accurately localizes objects and achieves a state-of-the-art unseen success rate of 8.37%.
Authors: Linda-Sophie Schneider, Andreas Maier
Abstract: This work introduces a continuous soft near-orthogonality score and a resolution-aware saturated coverage objective for projection selection in region-of-interest focused cone-beam CT, grounded in Tuy's completeness theory. Replacing the binary hit-or-miss model of classical Tuy completeness with a graded, differentiable formulation preserves a direct link to achievable feature sizes while enabling both efficient approximate and exact optimisation. We establish that the underlying discrete decision problems are NP-complete via polynomial-time reductions from Set Cover, motivating a submodular greedy algorithm with proven $(1-1/\mathrm{e})$ approximation guarantees and a mixed-integer linear program (MILP) that provides certified optimality bounds. The MILP serves as a quality certificate for the greedy solution rather than a competing optimiser. The primary empirical finding confirms this relationship: across a systematic benchmark spanning six target regions, multiple projection budgets, and four controlled occlusion conditions, the pooled median greedy-to-MILP objective ratio was 0.998, with a substantial fraction of cases certified globally optimal. A binary formulation is included as a diagnostic baseline; it strengthens hard directional completeness but is weaker on the continuous coverage scale. We additionally introduce Effective Spatial Resolution (ESR), a physically interpretable trajectory-level diagnostic that maps directional sampling gaps to achievable feature sizes. ESR correlates reliably with matched reconstruction quality across projection budgets and occlusion levels, providing a practical bridge between the selection stage and the image domain without requiring reconstruction.
Authors: Zhe Cheng, Wenyu Chen, Fode Zhang, Dehuan Shen
Abstract: Large vision-language models (LVLMs) often hallucinate content that is fluent yet unsupported by the image, limiting their reliability in real-world deployment. We show that a key failure mode arises from route competition: even when visual tokens receive attention, the final token decision can be dominated by the textual pathway, causing the decoder to follow linguistic priors over visual evidence. To mitigate this, we propose a training-free, decision-aligned intervention that decomposes each attention head into a visual route and a text route, and estimates their token-level effects using an efficient one-forward/one-gradient approximation. These estimates reveal route conflict within heads and identify prior-dominant ones, enabling selective suppression of only the text route while keeping the visual route intact. Across five benchmarks spanning discriminative and generative settings, our method consistently reduces hallucination-related errors across models with limited impact on overall multimodal performance, while incurring a modest inference-time overhead.
Authors: Youwei Pang, Changsheng Gao, Dong Liu, Huchuan Lu, Weisi Lin
Abstract: Large models have delivered remarkable performance across a wide range of perception and generation tasks, yet practical deployment is increasingly constrained by computational and memory budgets, as well as privacy requirements. Split execution alleviates these constraints by partitioning computation across devices, but it inevitably introduces intensive transmission and storage of intermediate features. Unlike conventional feature coding for CNNs that typically targets homogeneous spatial activation maps, modern large models generate heterogeneous features with varying statistical distributions and compression tolerances, e.g., multi-level/multi-modal representations and autoregressive context caches. These characteristics necessitate treating large model feature coding (LaMoFC) as a fundamental system component and call for a systematic evaluation framework. In this paper, we present a comprehensive benchmark and evaluation framework for LaMoFC. We first build the feature dataset LaMoFCBench, covering diverse task requirements across 4 categories and 16 scenarios while integrating widelyadopted architectures and various split-computing settings. We then specify representative split points according to practical application scenarios to extract intermediate features, establishing a unified pipeline for fair and reproducible comparisons. Finally, we benchmark mainstream universal feature codecs, exposing the profound misalignment between existing coding paradigms and the heterogeneous nature of large model features. These findings reveal that LaMoFC demands a fundamental departure from existing paradigms, and LaMoFCBench provides the shared empirical foundation to drive this transition. The data and code will be available at https://github.com/lartpang/LaMoFCBench.
Authors: Zikang Zhou, Haibo Hu, Xinhong Chen, Yifan Zhang, Nan Guan, Yung-Hui Li, Chun Jason Xue, Jianping Wang
Abstract: Multimodal motion forecasting is inherently under-supervised: each training scene provides only one realized future, yet multiple plausible futures exist. This sparse supervision often leads to mode collapse (redundant hypotheses and insufficient mode coverage) and unreliable confidence ranking when predicting a small set of trajectories. We propose Mode-as-Sequence, a unified decoding framework that translates an unordered mode set into an ordered mode sequence and explicitly models mode-to-mode dependency. Under this framework, we develop two complementary instantiations. ModeSeq performs recurrent mode decoding, where each mode is generated conditioned on the previously generated modes, encouraging diverse, non-redundant hypotheses with calibrated confidence ordering. To remove the mode-by-mode autoregressive bottleneck, we further propose Parallel ModeSeq, which preserves the same causal dependency using masked mode-to-mode self-attention while decoding all modes in a single forward pass, enabling efficient large-$K$ inference and scalable joint-scene prediction. To learn representative modes and calibrated confidence under sparse labels, we introduce Early-Match-Take-All (EMTA) and its joint-scene extension MA-EMTA, together with a lightweight ranking regularizer that reduces confidence inversions. Extensive experiments on large-scale benchmarks demonstrate consistent improvements in both ranking-oriented metrics and best-of-K accuracy across datasets, horizons, and object types. In the Waymo Open Dataset challenges, ModeSeq achieves 1st place in the 2024 LiDAR-free motion prediction track, and Parallel ModeSeq achieves 1st place in the 2025 Interaction Prediction Challenge, validating the effectiveness of Mode-as-Sequence for both accuracy and efficiency.
Authors: Lu\'is Maria Perdig\~ao, Miguel Costa, Carlos Santiago, Manuel Marques
Abstract: Cycling delivers significant public-health and environmental benefits, yet its uptake in cities is often limited by perceived safety. When street environments appear unsafe, individuals are less likely to cycle, making perception a key barrier to adoption. Recent work has shown that pairwise comparisons of street-view images provide a scalable way to learn subjective safety judgments. However, existing approaches do not explicitly model human visual attention, which plays a central role in how humans perceive safety. We propose an Eye-Tracking-Guided Perceived Cycling Safety framework (EG-PCS) that integrates gaze data into a pairwise learning pipeline based on vision transformers. By supervising the model's attention mechanism with eye-tracking signals, we encourage alignment between learned attention maps and human fixation patterns. Experiments show that gaze-guided models achieve similar ranking performance compared to state-of-the-art approaches while producing attention maps that more accurately reflect human visual attention behavior. Our results demonstrate that incorporating eye-tracking information enhances both predictive accuracy and interpretability in perception-based urban analytics.
Authors: Farhat Shaikh, Ayan Banerjee, Sandeep Gupta
Abstract: We introduce EMMA, a physics-informed multimodal framework that recovers all identifiable dynamical parameters of a system directly from raw video, audio, and image-based time-series observations. Unlike prior video-only approaches that struggle with occluded states, hidden actuation inputs, or assumptions about known initial conditions and coordinate frames, EMMA performs joint inference of explicit parameters, implicit dynamical components, and calibration invariants within a unified continuous-time model. EMMA leverages a Liquid Time-Constant (LTC) network to learn latent dynamics from heterogeneous modalities while a physics-constrained loss enforces consistency with the governing differential equations. A unified feature pipeline enables consistent alignment across video trajectories, acoustic signatures, and chart-derived measurements, allowing EMMA to estimate parameters under forced, implicit, and multivariate dynamics without requiring segmentation masks, differentiable rendering, or specialized sensors. Across 100+ scenarios including five standard dynamical benchmarks (75 Delfys videos), real-world rover and quadrotor systems with hidden inputs, and simulation-chart case studies spanning biological and chaotic systems, EMMA delivers robust multi-parameter recovery and significantly outperforms existing single-modality and equation-discovery baselines. Our results establish EMMA as a general, scalable solution for physics-consistent model extraction from opportunistic multimodal data. Code and data are available at: https://github.com/ImpactLabASU/EMMA-CVPR2026
Authors: Muhammad Asif Hasan, Yanming Zhu, Xuefei Yin, Alan Wee-Chung Liew
Abstract: Diagnosing Major Depressive Disorder (MDD) from functional magnetic resonance imaging (fMRI) using functional connectivity (FC) analysis requires large amounts of labeled data that are scarce in clinical settings. Existing augmentation methods synthesize FC matrices, which compress fMRI recordings into static pairwise summaries and discard temporal information. We propose fMRI-Diffusion, a framework that synthesizes region-of-interest (ROI)-level fMRI time series rather than FC matrices. A Temporal Transformer serves as the denoising network within a denoising diffusion probabilistic model, treating each time point as a token to capture temporal dependencies through self-attention. A supervised pretraining strategy initializes the Transformer with task-relevant representations before diffusion training, and FC matrices are derived from the synthesized time series for classification. Experiments on the REST-meta-MDD dataset show that augmenting training data with synthetic time series consistently improves diagnostic accuracy across ten classifiers, six parcellation atlases, and three acquisition sites. The method outperforms five recent FC-based synthesis approaches, with accuracy gains of up to 3.7 percentage points over the strongest baseline. Ablation studies confirm the contributions of both the Transformer-based denoiser and the pretraining strategy. Distributional fidelity metrics remain below 0.06 across all conditions, indicating close agreement between real and synthetic distributions. These findings suggest that synthesizing fMRI time series before FC computation preserves temporal information lost in matrix-level augmentation and provides a practical strategy for MDD diagnosis under limited data.
Authors: Muhammad Asif Hasan, Yanming Zhu, Xuefei Yin, Alan Wee-Chung Liew
Abstract: Major depressive disorder (MDD) is a common neuropsychiatric condition whose accurate diagnosis from resting-state functional magnetic resonance imaging (rs-fMRI) remains difficult. Dynamic functional connectivity (DFC) captures time-varying interactions among brain regions and provides rich spatio-temporal information, yet current DFC-based methods face three limitations: sliding-window Pearson correlation yields noisy estimates sensitive to window length and motion artifacts; correlation-derived node features do not fully exploit frequency-domain properties of blood-oxygen-level-dependent (BOLD) signals; and most spatio-temporal graph models handle spatial structure and temporal dynamics in separate stages, restricting their ability to represent coupled brain network evolution. To overcome these issues, we reformulate DFC learning as joint spatio-temporal graph representation learning under a Hawkes-process-inspired temporal dependency prior and propose HWSTCL, a two-stage framework built on a reliability-refined joint spatio-temporal graph with a kernel-weighted pretraining objective. Within each temporal window, BOLD signals are encoded as spectral node descriptors and functional edges are refined by an exponential distance-decay prior that down-weights less reliable long-range connections. The joint graph is then formed by linking each region to itself across future windows through a Hawkes-inspired exponential kernel, allowing spatial and temporal information to be propagated together during message passing. A kernel-weighted contrastive objective further promotes temporal consistency for each region across windows while reducing redundant similarity between different regions. Experiments on a benchmark rs-fMRI dataset show that HWSTCL outperforms recent baselines and yields coherent spatio-temporal representations for MDD diagnosis.
Authors: Ilia Indyk, Ignat Penshin, Ivan Sosin, Maxim Monastyrny, Aleksei Valenkov, Ilya Makarov
Abstract: Fisheye cameras are increasingly adopted in robotics for near-field manipulation, navigation, and immersive perception, yet indoor depth benchmarks with accurate ground truth are still missing. To address this, we introduce WideDepth - the first indoor dataset for fisheye depth estimation, featuring 101 scenes containing 5K high-resolution stereo pairs labeled with millimeter-level ground truth depth and disparity. Our dataset also includes paired pinhole and fisheye samples across varying fields of view and baselines in both horizontal and vertical stereo setups. We further propose a method to adapt pinhole-trained stereo models to fisheye images and introduce a novel stereo fisheye image generation pipeline based on high-resolution LiDAR scans. Leveraging these methods, we thoroughly evaluate state-of-the-art monocular depth, stereo matching, and depth completion models on our benchmark. Additionally, we provide 18K LiDAR-derived sparse depth training samples, achieving up to a 62% performance boost on fisheye data when fine-tuning pinhole-based stereo models. In summary, the high precision and versatility of our benchmark set a strong foundation for advancing research in fisheye depth estimation and robotics perception. Project page: https://ilyaind.github.io/WideDepth
Authors: Kevin Richard, Alphin Varghese, Colin Pham, David Oh, Srijan Das
Abstract: Single-vehicle Vision-Language Models (VLMs) are fundamentally constrained by sensor occlusions. While Vehicle-to-Everything (V2X) systems mitigate this, current benchmarks lack the cooperative reasoning required for resolving ambiguities in complex environments. We introduce D2-V2X, a spatially-aware Question-Rationale-Answer (QRA) benchmark featuring 8,500 triplets derived from multimodal vehicle and infrastructure sensors. We additionally establish a baseline that aligns 3D LiDAR features with the VLM's latent space. By enforcing natural language Chain-of-Thought rationales prior to structured JSON outputs, our model is forced to explicitly articulate spatial relations. Our experiments demonstrate that grounding VLMs in cooperative LiDAR achieves 24.4% recall in identifying occluded hazards compared to near-zero in zero-shot models and reduces spatial estimation error for visible objects by 77% compared to the zero-shot baseline. While the model achieves a functional decision-making F1-score of 53.5, we identify 3D-to-2D projection as a fundamental bottleneck in current VLM architectures, establishing a new baseline for future innovation. Data, code, and trained models available at https://github.com/KevinRichard1/D2-V2X
Authors: Florian Barthel, Shalini De Mello, Koki Nagano, Wieland Morgenstern, Anna Hilsmann, Peter Eisert
Abstract: Recent 3D Gaussian Splatting (3DGS) GANs for human heads synthesize and render photorealistic 3D models in real-time and offer a vast variety in identity and appearance. However, controlling specific semantic attributes such as hair color or glasses remains challenging, as edits in the entangled latent space often induce unintended changes in identity or appearance. Although there are several methods that aim to disentangle the latent space post training by estimating directions that only modify certain features, these methods cannot guarantee complete disentanglement and often require pre-trained classifiers. In our approach, we propose a new generator architecture that synthesizes components, such as hair, skin, glasses, and torso, completely independently. This allows for changing the latent vector for one region while keeping the remaining parts fixed. Further, we achieve this separation using only sparse information such as the hair or skin color, eliminating the requirement of segmentation masks or geometric priors, often seen in prior work. To ensure matching shape and lighting conditions during editing, we allow minimal shared information via context tokens between the independent generators. These tokens even allow us to control the shape and light, without any prior annotation. Compared to existing works on GAN-based generation and editing, our method shows better disentanglement, more precise editing control, and competitive visual quality.
Authors: Gunjan Shrivastava, Saad Nadeem
Abstract: Accurate cell segmentation in pathology images typically requires dense pixel-wise annotations, which are costly and time-consuming to obtain. This challenge is especially important for emerging biological imaging modalities and multiplexed datasets with variable channel configurations, where expert-labeled data are scarce. In this work, we introduce ImPartial, a deep learning framework designed to achieve state-of-the-art segmentation performance in low-annotation regimes using sparse scribbles and limited supervision. ImPartial augments the segmentation objective via self-supervised multi-channel quantized imputation. This approach leverages the observation that perfect pixel-wise reconstruction or denoising of the image is not needed for accurate segmentation, and thus, introduces a self-supervised classification objective that better aligns with the overall segmentation goal. We demonstrate that ImPartial achieves performance at par with fully supervised models while requiring substantially fewer annotations. Extensive experiments on benchmark multiplexed cellular imaging and single-plex clinical brightfield immunohistochemistry datasets show consistent improvements over strong baselines with only partial annotations. All benchmark datasets and code are available via our Github: https://github.com/nadeemlab/ImPartial.
Authors: Filippos Bellos, Yutong Li, Jessie N Dong, Zaiyang Guo, Emily Mackay, Yayuan Li, Yannis Avrithis, Alison Pouch, Jason J. Corso
Abstract: Point-of-care transthoracic echocardiography (TTE) enables cardiac assessment in virtually any clinical setting, yet its diagnostic utility remains constrained by the expertise required for image acquisition and interpretation. Visual question answering (VQA) offers a promising paradigm for bridging this expertise gap through interactive clinical assistance, but existing echocardiography VQA datasets are limited in scale, restricted to high-quality images, and only cover a few views. We introduce EchoVQA, the first large-scale VQA dataset for echocardiography, comprising 14,299 images and 74,819 question-answer pairs. The dataset integrates public sources (EchoNet-Dynamic, CAMUS) with our own point-of-care acquisitions from two handheld probes (Lumify, Clarius), spanning diverse views and including both high-quality and suboptimal images. Uniquely, EchoVQA includes acquisition guidance questions to help users optimize transducer positioning toward a diagnostic apical 4-chamber view for left ventricular ejection fraction estimation -- a challenging task for novice operators in point-of-care settings. We further develop a parameter-efficient method based on multimodal learnable prompts achieving state-of-the-art performance on most benchmarks, including EchoVQA, with significantly less trainable parameters than existing state-of-the-art approaches.
Authors: Pouyan Navard, Sernam Lim
Abstract: Portrait animation transfers a driver clip's facial expression and head pose onto a single reference image while preserving the reference's identity. State-of-the-art diffusion systems address this by stacking trained modules for expression, pose, and identity in turn, paying for it in trainable parameters, proprietary corpora, and residual entanglement between the very axes the system is meant to control independently. This complexity compensates for an upstream choice -- learning facial expression and head pose from RGB, a representation in which identity, pose, and expression are inseparable without being learned apart. Loki steps out of RGB on the conditioning path. Driver expression and head pose are encoded by a face model whose parameter axes are identity-orthogonal by construction, then rasterised into a spatial map that the diffusion backbone consumes natively. Identity is routed separately through the diffusion backbone's own pretrained features via lightweight key-value injection. Because the parametric representation factorises identity from expression and pose, cross ID reenactment reduces to a coefficient substitution at inference, requiring no cross ID training data. Loki requires ~43% fewer inference parameters than leading diffusion baselines and trained on 1496x less video samples. We define two metrics that directly measure whether the generated head pose trajectory and facial expression followed the driver's -- the questions portrait animation actually asks; Loki leads or co-leads on both.
Authors: Sevan Brodjian, Michael Hobley, Pietro Perona
Abstract: Sonar is often the only modality suitable for high-resolution imaging underwater due to light attenuation and turbidity. Forward-looking imaging sonar provides measurements over range and horizontal angle but collapses vertical structure into a flat image, creating ambiguities that make 3D recovery challenging. A common use case for imaging sonar is underwater terrain mapping (bathymetry), yet current methods require many views, expensive multi-sensor setups, or significant training data, which limits use and adaptability to new environments. We present a training-free method that recovers bathymetry from a single sonar image in under 30 seconds via differentiable rendering, conditioned on a known seafloor tilt. To our knowledge, this is the first differentiable rendering approach for single-view height recovery in sonar. Our method implements differentiable sonar ray tracing and optimizes an explicit height field to reproduce the target image. On synthetic datasets, our approach outperforms a supervised CNN under distribution shift and remains close on rough terrain, while the CNN wins in-distribution. By modeling physically grounded priors of the sonar process, our method adapts across sensor configurations and environments without training data.
Authors: Mohammad Salmanpour, Mehrdad Oveisi, Isaac Shiri, Arman Rahmim
Abstract: Medical image computing software is essential for identifying imaging biomarkers that can support diagnosis, prognosis, treatment planning, and clinical research. However, the lack of standardized, user-friendly, and reproducible software environments has limited the broader adoption of advanced medical image analysis workflows. We present Radiuma, a freely available modular platform designed to support reliable and reproducible medical image analysis across multiple modalities and file formats. Radiuma integrates image reading, visualization, registration, fusion, processing, segmentation, radiomics feature extraction, and machine learning modules for classification, regression, and clustering. Its modular design allows users to execute each component independently or connect modules through a visual workflow system, where the output of one step can be graphically passed to the next. This enables the creation of custom, executable, and reproducible multi-step pipelines without requiring extensive programming expertise. Results from each module can be inspected directly in the visualization window, providing immediate feedback on processing quality and workflow accuracy. Radiuma also supports saving and sharing customized workflows, promoting transparency, reusability, and consistency across collaborative studies. By combining flexibility, usability, and standardized analysis tools, Radiuma provides a practical environment for radiomics and machine learning research in clinical and translational settings. The platform is designed to be accessible to users with diverse expertise, including radiologists, physicists, clinicians, and data scientists.
Authors: Diogo Lavado, Alessandra Micheletti, Cl\`audia Soares
Abstract: In 3D scene understanding, deep learning models rely on large models and extensive training to capture basic geometric structures that are present in the 3D data. However, existing methods lack explicit mechanisms to incorporate geometric information, such as learnable primitive shapes, often necessitating large models and more training data which in turn increases cost and can limit generalization. We introduce GIBLy, a lightweight geometric inductive bias layer that integrates learnable geometric priors into 3D segmentation pipelines. GIBLy enhances existing architectures -- whether MLP-based, convolution-based, or transformer-based -- by providing features aligned with simple geometric shapes (and thus human-interpretable) that improve segmentation performance with minimal computational overhead. We validate our approach across multiple 3D semantic segmentation benchmarks, demonstrating consistent performance gains, including up to +11.5% mIoU on TS40K with PTV3, while adding only 58K extra parameters. Our results highlight the benefit of explicitly encoding geometric structure to support accurate and efficient 3D scene understanding, with a lightweight add-on layer
Authors: Zahra Rahimi Afzal, Wataru Uegami, Saghir Alfasly, Saba Yasir, Judy C. Boughey, Matthew P. Goetz, Krishna R. Kalari, H. R. Tizhoosh
Abstract: Digital pathology archives increasingly contain multiple whole-slide images (WSIs) per case, capturing spatially distinct tumour regions and reflecting intrinsic morphological heterogeneity. However, most existing approaches rely on a single pathologist-selected slide, thereby discarding potentially informative evidence distributed across the remaining WSIs. To date, no autonomous framework has been proposed for comprehensive multi-WSI case processing. Here, we present an unsupervised framework for case-level analysis that integrates information from all available slides within a case. Rather than relying on a single designated slide, the proposed approach constructs case-level representations by selectively distilling informative patches across WSIs. We introduce Clustering-Based Redundancy-Reduced Instance Sampling for Pathology (CRISP), a two-stage framework that first reduces redundancy within individual WSIs and subsequently applies clustering-based sampling to select a compact yet representative set of patches for the entire case. The resulting patch set captures case-level heterogeneity while avoiding exhaustive processing of gigapixel images, and directly serves as a retrieval index. Using two Mayo Clinic breast cancer datasets for diagnosis and treatment planning, we demonstrate that CRISP consistently matches or surpasses the current standard practice of combined model and pathologist slide selection for patient/case search and retrieval. By automating case-level processing and eliminating subjective WSI selection, CRISP potentially enables the exploitation of clinically relevant information distributed across multiple WSIs that is currently overlooked.
Authors: Manuel P\'erez-Carrasco, Maya Nasr, Zhan Zhang, Apisada Chulakadabba, Javier Roger, Raia Ottenheimer, S\'ebastien Roche, Maryann Sargent, Chris Chan Miller, Daniel Varon, Jack Warren, Luis Guanter, Kang Sun, Jonathan Franklin, Jia Chen, Cecilia Garraffo, Xiong Liu, Ritesh Gautam, Steven Wofsy
Abstract: Automated detection and masking of individual methane plumes from satellite imagery is important for operational emission attribution and quantification. We present a machine learning framework for plume detection from MethaneSAT retrieved column-averaged dry-air mole fractions of methane. We address two core challenges: the scarcity of labeled MethaneSAT data and the need for inference reliability across diverse atmospheric and surface conditions. We first demonstrate that Mask R-CNN with a ResNet-50 backbone outperforms U-Net semantic segmentation on both MethaneAIR (an airborne version of MethaneSAT) and MethaneSAT data, with pixel-level F1 score gains of 10.49 and 5.48 respectively. To address MethaneSAT data scarcity, we evaluate three cross-sensor transfer strategies leveraging MethaneAIR flights and synthetic plumes. Mask R-CNN with ResNet-50 fine-tuned from MethaneAIR pre-trained weights is the most effective strategy, achieving instance-level precision of 0.60 and a near-perfect recall of 0.98 at the baseline operating point. A physics-informed post-processing pipeline converts detections into two operationally distinct modes. The first is a high-sensitivity mode that applies morphological filtering and proximity-based merging for comprehensive emission screening, achieving precision of 0.71 and recall of 0.94. The second is a high-precision mode that additionally applies a distribution-based classifier for confident source attribution, achieving precision of 0.92 and recall of 0.70. Manual review of detections classified as false positives against our wavelet-based ground truth labels reveals that a meaningful fraction of cases correspond to real methane enhancements excluded by conservative labeling criteria, indicating that precision values reported are lower bounds on true detection performance... Our data and code are available at: https://doi.org/10.7910/DVN/FR959H
Authors: Juan Ignacio Bustos Gorostegui, Maria Elena Buemi
Abstract: Egocentric action recognition is a challenging task due to erratic camera motion, frequent hand occlusion, and the difficulty of maintaining consistent visual representations over time. In this work, we propose a cross-modal architecture that combines RGB video and temporal hand skeleton data within a unified Mamba-based framework, exploiting the linear time complexity of State Space Models (SSMs). Our architecture consists of three components: a VideoMamba module for visual feature extraction, a skeleton encoder built on a stack of Mamba blocks, and a fusion module that integrates both modalities into a single representation. A central contribution of this work is the design and evaluation of four Class (CLS) token mixing strategies for multimodal fusion: Naive, Average, Weighted and Context-based. These strategies differ in how the pretrained unimodal CLS tokens, which role is to act as information sinks concentrating learned representations, are leveraged to initialize the mixed CLS token used for final classification. We evaluate all strategies on the H2O dataset. Experimental results show that the Average strategy achieves the best performance, yielding gains of over 10% Top-1 accuracy in the Tiny configuration and 2% in the Small configuration over the VideoMamba baseline.
Authors: Inseo Lee, Yoonji Kim, Eugene Sohn, Jiwoong Lee, Jungmin You, Joonseok Lee, Jin-Hwa Kim
Abstract: Articulated object reconstruction from sparse-view images is an ill-posed problem that requires simultaneous inference of geometry and underlying articulation structure. Existing methods for articulated object reconstruction based on NeRF and 3D Gaussian Splatting (3DGS) typically rely on dense views or strong priors (e.g., depth maps, joint types, predefined number of joints) and require costly per-object optimization. In this paper, we propose ArtSplat, the first feed-forward framework for articulated 3D Gaussian Splatting. It reconstructs both geometry and joint parameters from sparse multi-view images across multiple articulation states in a single forward pass. To address the challenges of single-pass articulated reconstruction, we introduce a per-pixel joint map representation that enables the integration of joint parameter estimation into the feed-forward pipeline. We further propose a Cross-State Attention (CSA) mechanism with state tokens, which effectively captures discrete motion across input states. Experiments on 68 articulated objects from PartNet-Mobility, including both single- and multi-joint configurations, demonstrate that ArtSplat achieves competitive performance in both geometry and joint estimation, while being over 400 times faster than baselines.
Authors: Zexi Jia, Zhiqiang Yuan, Xiaoyue Duan, Jinchao Zhang, Jie Zhou, Anil K. Jain
Abstract: AI-generated image detection faces a persistent trade-off between generalization and efficiency: lightweight artifact-based methods often degrade on unseen generators or domains, whereas more robust large-scale models are computationally expensive. Meanwhile, existing benchmarks mainly focus on cross-model evaluation in photorealistic settings, leaving cross-domain robustness underexplored. To address this gap, we introduce FakeForm, a large-scale benchmark with approximately 370,000 images across 62 diverse domains for both cross-model and cross-domain evaluation. Motivated by this broader setting, we revisit color-distribution probing as an efficient complementary cue for AI-generated image detection. We observe that, especially for photographic content, real photographs tend to exhibit smoother and more stable color patterns, whereas synthetic images often show characteristic color imbalances introduced by neural generation. Based on this observation, we propose CoDA, a compact 1.48M-parameter detector built on a Noise-Quantization Probe, together with a theoretical analysis linking probe responses to color non-uniformity. Experiments show that CoDA achieves state-of-the-art performance on standard benchmarks and the best results on the challenging cross-domain evaluation of FakeForm, while remaining highly competitive in cross-model photorealistic settings. These results suggest that persistent generative artifacts can provide a practical foundation for efficient and robust AI-generated image detection. The models and FakeForm benchmark will be made publicly available.
Authors: Wanhee Lee, Klemen Kotar, Rahul Mysore Venkatesh, Jared Watrous, Honglin Chen, Khai Loong Aw, Daniel L. K. Yamins
Abstract: Understanding 3D scenes requires flexible combinations of visual reasoning tasks, including depth estimation, novel view synthesis, and object manipulation, all of which are essential for perception and interaction. Existing approaches have typically addressed these tasks in isolation, preventing them from sharing a common representation or transferring knowledge across tasks. A conceptually simpler but practically non-trivial alternative is to unify these diverse tasks into a single model, reducing different tasks from separate training objectives to merely different prompts and allowing for joint training across all datasets. In this work, we present a physical world model for unified 3D understanding and interaction (3WM), formulated as a probabilistic graphical model in which nodes represent multimodal scene elements such as RGB, optical flow, and camera pose. Diverse tasks emerge from different inference pathways through the graph: novel view synthesis from RGB and dense flow prompts, object manipulation from RGB and sparse flow prompts, and depth estimation from RGB and camera conditioning, all zero-shot without task-specific training. 3WM outperforms specialized baselines without the need for finetuning by offering precise controllability, strong geometric consistency, and robustness in real-world scenarios, achieving state-of-the-art performance on NVS and 3D object manipulation. Beyond predefined tasks, the model supports composable inference pathways, such as moving objects aside while navigating a 3D environment, enabling complex geometric reasoning. This demonstrates that a unified model can serve as a practical alternative to fragmented task-specific systems, taking a step towards a general-purpose visual world model.
Authors: Nahid Alam
Abstract: Video world models learn representations of physical dynamics, but controlling their physical expectations at inference time remains an open problem. Recent interpretability work identified a Physics Emergence Zone (PEZ), a group of middle transformer layers in VideoMAE where physical plausibility is represented separately from other visual features. However, it remained unclear whether this structure could be used to directly control the model's physics reasoning. We present physics steering, a training-free method that uses the weight vector of a linear probe at a PEZ layer as a Concept Activation Vector (CAV) and injects it into hidden states during inference. This shifts the model's physical expectations without changing any model weights. On the IntPhys benchmark, this intervention reliably shifts the model's plausibility judgment in either direction, depending on the steering sign. The effect appears only when the intervention is applied within the Physics Emergence Zone, suggesting that the relevant physics representation is localized there. We further find that physics is encoded separately from motion direction, and that different intuitive physics principles occupy distinct directions within this representation space. Together, these results show that physical reasoning in VideoMAE is not only readable, but also directly steerable.
Authors: Xiangzhi Tong, Chengrui Zhang, Mac Flaherty, Andre Matteo Garcia, Dominic Gorman, Jonathan Jaramillo, Justine E. Vanden Heuvel, Yu Jiang
Abstract: Cluster closure, defined as the progressive filling of gaps between the berries in a grape bunch, is a key trait in vineyard management, impacting disease risk. However, traditional visual scoring methods are labor-intensive, subjective, and lack temporal resolution. Existing datasets rarely support fine-grained berry-level analysis, limiting the development of robust deep learning models. In this work, we present ViViD-5k, a large-scale in-field Vineyard Vision Dataset containing 5,000 images with dense annotations, including over 648,000 berry centroids and cluster segmentation masks spanning 13 grape varieties. Building on this dataset, we introduce GrapeSAM, a two-stage visual pipeline that combines point-based berry localization with prompt-based segmentation using Segment Anything, followed by transformer-based cluster segmentation. The pipeline enables automated, in-field estimation of cluster closure with minimal supervision. Quantitative results demonstrate strong segmentation and counting accuracy across diverse conditions, while visualizations confirm robustness on both in-domain and out-of-domain samples. This work provides a scalable and objective alternative to manual compactness scoring and supports high-throughput grape phenotyping with enhanced spatial detail.
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: Rafael Mendon\c{c}a Duarte, Jean Roberto Ponciano, Lucas Pascotti Valem
Abstract: The exponential growth of data has intensified the gap between the availability of unlabeled data and the high cost of manual annotation. Graph Neural Networks (GNNs) have emerged as a promising solution, as they exploit relational structures and learn from both labeled and unlabeled data, performing semi-supervised learning. A crucial component of many of these models is degree-based normalization, which influences message propagation but typically assumes uniform importance among neighboring nodes. In image classification, graphs are usually constructed from feature similarity, where treating all neighbors equally may overlook important variations in relevance. Motivated by this gap, we propose GRaNDe (Gaussian Rank-based Neighborhood Degree). This novel degree measure integrates neighborhood ranking with Gaussian distance weighting to better capture node importance. Experiments on five public image classification datasets show consistent accuracy improvements and competitive or superior results compared to state-of-the-art methods.
Authors: Yuanhe Tian, Yan Song
Abstract: CT report generation (CTRG) requires models to summarize three-dimensional anatomical context and pathological findings from hundreds of axial slices. Existing methods typically learn a direct image-to-text mapping, providing limited mechanisms for modeling how CT evidence evolves across slices or how reports respond to controlled changes in latent lesion-related factors. We propose SliceWorld, a CT-specific world-state framework that treats an axial CT scan as an ordered sequence along the z-axis. SliceWorld encodes prefix CT evidence into factor-aware latent states containing anatomy, lesion, and uncertainty components, and projects these states into world tokens used for multi-step future-slice feature prediction, lesion-factor intervention, and LLM-based report generation. The model is first pretrained on CT slice sequences with predictive, factor-aware, and counterfactual objectives, and is then fine-tuned on paired CT-report data. Experiments on M3D-Cap and CT-RATE show that SliceWorld improves natural language generation metrics and clinically oriented automatic evaluation. Further analyses demonstrate multi-horizon future-slice prediction, measurable factor alignment, reduced-slice robustness, and selective lesion-sensitive report modulation.
Authors: Tarun Gehlaut, Difan Liu, Charu Bansal, Krutik Malani, Souymodip Chakraborty, Ankit Phogat, Matthew Fisher, Vineet Batra
Abstract: Recent vision-language model (VLM)-based approaches have achieved impressive results on image vectorization tasks. However, they are typically evaluated on synthetic benchmarks, where clean SVGs are rasterized at high resolution and then re-vectorized. As a result, these methods generalize poorly to real-world scenarios, such as images with unknown rasterization methods or those generated by text-to-image models. We introduce VectorArk, a new VLM-based model designed for robust and practical image vectorization. VectorArk employs a novel rounded polygon representation that simplifies the learning process while naturally producing smooth, visually appealing primitives. We also propose a degradation model that enhances robustness across diverse and imperfect inputs. Our experiments show that, in contrast to previous methods, VectorArk achieves superior geometric completeness and artifact suppression across multiple datasets, with comprehensive ablations validating the contribution of each component.
Authors: Yaoxuan Feng, Yuxin Li, Weijiang Lv, Zixuan Zhao, Yubiao Wang, Wenchao Chen, Bo Chen, Hongwei Liu
Abstract: Multi-class anomaly detection aims to build unified models across diverse product categories. However, as the number of categories grows, its performance often degrades due to increasingly complex and heterogeneous normal distributions. To address this challenge, we propose DPDiff-AD, a Dual Prototype-conditioned Diffusion model for large-scale multi-class Anomaly Detection. DPDiff-AD models heterogeneous normal distributions through complementary local and global prototypes. Local prototypes capture representative fine-grained structural patterns via nearest-prototype aggregation, while global prototypes regulate holistic feature geometry through optimal transport regularization. Together, these dual-scale representations define a structured normality space. This space is refined through diffusion-based reconstruction conditioned on both local and global prototypes via prototype-aware attention. By jointly leveraging dual prototypes during generation, DPDiff-AD achieves precise normality modeling, preserves structured separability as category cardinality grows, and enables scalable anomaly discrimination. Extensive experiments across five benchmarks demonstrate the effectiveness and scalability of DPDiff-AD. On the 160-category large-scale dataset, it improves image- and pixel-level AUROC by 5.3 and 2.9 points over the previous state-of-the-art method Dinomaly+, while maintaining stable performance as category cardinality increases.
Authors: Denys Iliash, Jiayi Liu, Egor Fokin, Qirui Wu, Ali Mahdavi-Amiri, Manolis Savva, Angel X. Chang
Abstract: We present Artiverse, a diverse and physically grounded dataset of high-quality articulated 3D objects designed for realistic functional modeling and simulation. Artiverse contains 5.4K human-authored objects across a broad range of 88 categories, aggregated from multiple 3D static repositories. Objects are annotated with functional parts, interior structures, realistic kinematic relationships and articulated joints including multi-DoF joints, and physical attributes such as metric scale, material, and mass. We develop a semi-automated annotation pipeline that combines few-shot segmentation, geometric reasoning, and multi-stage human verification to achieve high-quality and efficient annotation, reducing manual annotation time by over 30%. We demonstrate the value of Artiverse on tasks of part mobility analysis, articulated object generation, and physics-based interaction. Artiverse provides a data resource to advance functional understanding for articulated objects.
Authors: Bill Psomas, Dionysis Christopoulos, Thanasis Petropoulos, Nikos Efthymiadis, Ioannis Kakogeorgiou, Ond\v{r}ej Chum, Yannis Avrithis, Giorgos Tolias, Konstantinos Karantzalos
Abstract: Remote sensing composed image retrieval (RSCIR) enables search in large satellite image archives using composed queries that combine a reference image with a textual modifier. Although RSCIR offers a flexible interface for expressing targeted retrieval intent, the transferability of modern composition methods to Earth observation (EO) imagery and their relevance to operational EO workflows remain underexplored. We address this gap through a unified benchmark and an application-oriented study. First, we systematically adapt and evaluate representative composed image retrieval methods with six vision-language backbones on PatternCom under a standardized protocol, analyzing their behavior across backbones, composition strategies, and query types. Second, we introduce xView2-CIR, a change-centric dataset for disaster and damage monitoring, where retrieval is conditioned on scene identity and a target post-event state. Our results show that training-free composition methods provide strong and scalable baselines for EO retrieval, while change-centric retrieval presents different challenges from attribute-based retrieval, particularly due to the need to preserve scene identity. Overall, this study establishes a practical benchmark for RSCIR and positions composed retrieval as a complementary tool for remote sensing image retrieval, archive exploration, and change analysis. The dataset and code are available at https://github.com/billpsomas/rscir.
Authors: Jiachen Song, Dazhi Zhang, Fanghui Song, Zhichang Guo, Shengzhu Shi
Abstract: Interactive segmentation aims to precisely isolate target objects using sparse user guidance. However, traditional methods often suffer from heavy interaction burdens and parameter sensitivity, while deep learning approaches struggle with data dependency and iterative instability. Motivated by these limitations, we propose the Sustainable Interactive Level Set Method (SILSM). The proposed level set evolution equation incorporates interaction, regularization, and segmentation terms. Specifically, high-order regularization is employed to maintain numerical stability, and unlike traditional methods, we decouple user guidance into an independent interaction term to enable direct manual control over the zero-level set evolution. Furthermore, we develop a numerical algorithm tailored for multiple interactions, which facilitates dynamic refinement by effectively updating the segmentation results based on sequential user inputs. We theoretically demonstrate that the high-order term provides stronger regularization constraints than the conventional length term, while the interaction term ensures segmentation strictly within the user-selected region. Experimental results further demonstrate that the proposed method is robust to interactive inputs, achieves competitive performance at the first interaction, and supports stable multi-round interactions with progressively improved segmentation quality.
Authors: Jinzhao Li, Yinuo Chen, Dongxu Piao, Panwang Pan, Yifan Yu, Dong Wang, Honglei Yan, Liang Yue, Shaofei Wang, Yixin Chen, Siyuan Huang, Miao Liu
Abstract: Humans constantly reason about 3D proximity, the relations between their body and surrounding objects, to guide perception and action in daily life. Whether multimodal large language models (MLLMs) can perform such embodied 3D reasoning remains unclear. To this end, we introduce EgoProx, a benchmark for egocentric 3D proximity reasoning. We organize our tasks along a cognitive chain, covering intention, exploration, exploitation, and chain-of-actions reasoning. We also design an agent based data engine that produces diverse and consistent QA pairs at scale. We benchmark prevailing MLLMs on EgoProx and conduct additional analyses with dataset specific and task specific instruction tuning. We observe large cross-domain gains, indicating that current MLLMs contain some spatial knowledge; however, they still struggle to effectively leverage it for spatial reasoning VQA.
Authors: Alif Tri Handoyo, Vincent C. S. Lee, Rizka Widyarini Purwanto, Alex M. Lechner, Deanna Kemp, Muhamad Risqi U. Saputra
Abstract: Automatically mapping and segmenting global mining footprints using remote sensing and deep learning is critical for monitoring the socio-environmental risks and impacts of mining, yet its progress is hindered by the scarcity of fine-grained annotated data. Although large-scale datasets with coarse boundaries are widely available, leveraging them to improve fine-grained segmentation is challenging due to significant domain shift. To address this, we propose MineC2FNet, a coarse-to-fine domain incremental learning framework that exploits abundant coarse data to enhance fine-grained mining footprint segmentation. MineC2FNet adopts a teacher-student architecture with attentive distillation at both the feature and prediction levels, selectively transferring generalized knowledge from the coarse domain while enabling boundary refinement using limited fine-grained data (fine domain). We further introduce an expertly validated dataset of 219 images with precise boundary annotations across diverse geographies and commodities. Extensive experiments against state-of-the-art approaches, including domain adaptation and domain incremental learning methods, demonstrate that MineC2FNet achieves superior performance while effectively handling domain shift. The dataset and code are publicly available at https://github.com/risqiutama/MineC2FNet.
Authors: Zixu Li, Yupeng Hu, Zhiwei Chen, Zhiheng Fu, Xiaowei Zhu, Weili Guan, Liqiang Nie
Abstract: Video-text retrieval has witnessed remarkable progress driven by large-scale vision-language pretraining, yet most existing approaches inherit an implicit assumption from image-text retrieval: that visual semantics can be captured frame-by-frame. This assumption overlooks the temporal dynamics of egocentric videos. The EPIC-KITCHENS-100 Multi-Instance Retrieval (MIR) challenge further raises the bar by providing soft-label relevance matrices rather than binary labels, demanding models that can resolve graded semantic correspondences across modalities. In this report, we present our solution, termed TempRet, to the CVPR 2026 EPIC-KITCHENS-100 MIR challenge. Our approach builds upon a CLIP-based dual-encoder backbone and introduces two key components to address the temporal and cross-modal challenges. First, a temporal transformer operates exclusively on the video side, modeling inter-frame dependencies through learnable positional encodings and multi-head self-attention over frame-level CLIP features. Second, a two-stage reranking pipeline first retrieves Top-K candidates via the dual-encoder, then refines their scores using a cross-encoder equipped with an Image-Text Matching (ITM) head. The entire system is trained with Symmetric Multi-Similarity Loss to exploit the soft-label relevance matrices provided by the challenge. Our method achieves 67.97% average mAP and 82.92% average nDCG on the EK-100 MIR benchmark, demonstrating the effectiveness of temporal modeling and cross-modal refinement for egocentric video retrieval.
Authors: Siyuan Duan, Yuan Sun, Dezhong Peng, Yingke Chen, Xi Peng, Peng Hu
Abstract: Trusted multi-view classification aims to deliver reliable fusion for accurate predictions and has recently attracted substantial attention in both academia and industry. However, existing TMVC methods typically assume strict alignment across different views during both training and testing phases, which is often impractical in real-world scenarios. This limitation motivates us to revisit TMVC and extend it to a more challenging setting: how to mitigate the impact of view conflict (VC) during both training and inference. To tackle this setting, existing TMVC methods suffer from three critical limitations: underestimated uncertainty, misleading decisions, and overfitting to VC. To address these issues, this paper proposes a novel Robust Fuzzy Multi-View Learning (R-FUML) framework grounded in Fuzzy Set Theory. Specifically, R-FUML models network outputs as fuzzy memberships to quantify category credibility and uses an entropy-based method for reliable multi-view fusion. To this end, we present a Robust Multi-view Fusion (RMF) strategy that accounts for both view-specific uncertainty and inter-view conflicts, thereby alleviating the adverse impacts of VC on decision-making. To identify and conquer VC during training, we further design a Robust Learning Against VC (RLVC) framework. RLVC isolates conflicting samples by leveraging neural networks' memory effects and then retrains the model by applying a penalty to these conflicting views. Extensive experiments across eight public datasets demonstrate that R-FUML consistently outperforms 15 state-of-the-art baselines in robustness and uncertainty estimation. The code will be released upon acceptance.
Authors: Zixu Li, Zhiwei Chen, Zhiheng Fu, Wenbo Wang, Yupeng Hu, Weili Guan, Liqiang Nie
Abstract: The 1st Cross-Domain EgoCross Challenge at EgoVis, CVPR 2026 evaluates whether multimodal large language models can reason over egocentric videos across surgery, industry, extreme sports, and animal perspective. We achieved second place in both the Source-Limited and Open-Source tracks. In this report, we formulate EgoCross as a robust cross-domain embodied video reasoning problem rather than a simple multiple-choice visual question answering task. We identify three key challenges: (C1) temporal boundary ambiguity, where critical state transitions are sparsely sampled and often occur between frames; (C2) cross-domain semantic granularity mismatch, where the same capability requires different domain-specific visual grammar; and (C3) decision instability under close options, where long multimodal reasoning can select unsupported distractors or produce malformed outputs. To address them, we propose OmniEgo-R$^2$ (Omnidomain Egocentric Routed Reasoning), a unified routed reasoning pipeline consisting of temporal-evidence normalization, domain-agnostic capability routing, structured perception--dynamics--decision reasoning, boundary-aware option verification, and defensive answer calibration. OmniEgo-R$^2$ uses the Qwen3-VL-4B-SFT checkpoints on each EgoCross domain as the visual-language backbone, and wraps them with lightweight test-time reasoning and parsing programs. Our final submissions obtain 66.35% overall accuracy in the Source-Limited track and 66.77% in the Open-Source track, ranking second in both leaderboards.
Authors: Jaehoon Ahn, Jeonghan Kong, Moon-Ryul Jung
Abstract: Content moderation in online multiplayer 3D virtual environments has recently been relegated to automated, AI-based pipelines. However, the field has mainly been involved in detection of illicit content in images, video, and audio, leaving blind spots in detection techniques for suggestive motion. We present a motion-only classification pipeline that detects suggestive and explicit movement from SMPL skeleton trajectories using Laban Movement Analysis (LMA) descriptors. On 20,514 motion fragments (17+ hours) spanning four ordinal tiers -- everyday, artistic, suggestive, explicit -- logistic regression over 110 LMA features achieves 57.3% four-way accuracy (2.3x chance), 72.1% three-way, and 78.7% binary SFW/NSFW. Confusion concentrates on adjacent tiers, confirming that classification errors are concentrated between adjacent tiers over non-adjacent ones. Moreover, different movement qualities dominate at each level of the taxonomy -- no single feature drives the classification, suggesting that the four-tier structure reflects genuinely distinct motion regimes.
Authors: Wen Ma, Fucheng Niu, Zhiting Fan, Zikai Xiao, Jiaxiang Liu, Zuozhu Liu
Abstract: Vision-language models have demonstrated impressive capabilities in general medical visual question answering, yet due to limited interpretability, it remains unclear whether their predictions reflect evidence-grounded clinical reasoning or reliance on spurious priors. We introduce Med-R2 Bench, a hierarchical benchmark aligned with the clinical workflow to evaluate adversarial robustness with visual grounding. We design stepwise QA tasks to assess whether reasoning chains are strictly grounded in visual evidence across the four clinical stages, and employ adversarial perturbations to test robustness against misleading cues. Med-R2 comprises 42,432 images, 31 task categories, and 110,406 QA pairs. Evaluation across 14 VLMs reveals a sequential performance degradation along the four-stage clinical workflow. Adversarial experiments show that models rely heavily on correct prompts to guess answers. Even when provided with explicit visual cues, the models struggle to accurately align textual descriptions. Finally, we demonstrate stepwise fine-tuning using our hierarchical data significantly improves reasoning robustness, highlighting its potential to drive future improvements in evidence-based medical AI.
Authors: Zhiheng Fu, Zixu Li, Zhiwei Chen, Fangxu Liu, Yupeng Hu, Weili Guan, Liqiang Nie
Abstract: The EPIC-KITCHENS-100 Action Detection challenge evaluates whether a model can localize the start and end of each action in long untrimmed egocentric videos and assign the corresponding verb--noun action label. In this report, we formulate our submission as EgoAction (Egocentric Action Composition with Reliability-Aware Temporal Fusion), a unified decoupled detection and fusion pipeline. The pipeline uses EPIC-finetuned VideoMAE-L features, trains separate noun and verb temporal detectors with causal temporal modeling, composes action hypotheses from top noun--verb pairs, and introduces a confidence-adaptive boundary fusion rule at post-processing time. The key observation is that verb and noun streams often fail differently: verb scores are sensitive to motion transitions, whereas noun scores are sensitive to hand-object visibility and object clutter. A fixed arithmetic mean of their predicted boundaries can therefore amplify localization errors when one stream degenerates. We replace this hard-coded mean with Dynamic Weighted Fusion (DWF), which normalizes the maximum noun and verb classification confidences into proposal-wise boundary weights and linearly combines the two intervals. This lightweight tensor-only operator shifts boundary authority toward the more reliable stream while preserving the decoupled action scoring mechanism. Together with sliding-window inference, top-K noun--verb action composition, and class-wise Soft-NMS, EgoAction provides a compact and reproducible system for egocentric temporal action detection.
Authors: Zhiwei Chen, Yupeng Hu, Zixu Li, Zhiheng Fu, Guozhi Qiu, Weili Guan, Liqiang Nie
Abstract: This technical report presents our solution, EgoAdapt (Egocentric Adaptation via Category, Calibration, and Consistency), to the CVPR 2026 HD-EPIC VQA challenge. HD-EPIC evaluates whether a vision-language model can reason over realistic first-person kitchen videos, where the evidence for an answer may be a short hand-object interaction, a long recipe trajectory, a spatial relation to a fixture, or a subtle gaze cue. The benchmark contains 26K multiple-choice questions across seven macro-categories: recipe, ingredient, nutrition, fine-grained action, 3D perception, object motion, and gaze. We observe that the main difficulty is not only model capacity, but also the mismatch between a single generic inference recipe and the heterogeneous temporal, spatial, and semantic structure of the benchmark. Our method, EgoAdapt, introduces three inference-time components: (1) category-conditioned routing with per-category prompts, frame budgets, and sampling rates; (2) calibrated option scoring that evaluates all candidate answers with letter-token likelihoods and generation agreement instead of relying only on direct generation; and (3) test-time consistency adaptation that aggregates predictions across option permutations and verification-style prompts for ambiguous cases. This design substantially improves over the available HD-EPIC baselines.
Authors: Ruihao Xu, Xingming Shui, Jingxuan Niu, Yiqin Wang, Jilin Yu, Haoji Zhang, Yansong Tang
Abstract: As AI-powered compliance monitoring becomes increasingly important in public governance and industrial safety, the ability to provide verifiable evidence and traceable accountability signals is essential. However, existing video anomaly detection datasets focus on event-level binary classification, lacking the rule-driven, explainable analysis required for real-world compliance scenarios. We introduce FoodMonitor, a benchmark for explainable compliance analysis in commercial kitchen surveillance. FoodMonitor comprises 477 video clips with 3,307 violation annotations across a dual-channel design covering both person-level and environment-level violations. Each annotation specifies which rule was violated, what non-compliant behavior occurred, and who committed it with frame-level bounding boxes. We establish a unified evaluation protocol with a two-stage matching mechanism that separately assesses spatial localization and semantic understanding, along with a composite metric ($C_{\text{score}}$) that balances environment and person detection performance. Systematic evaluation of several state-of-the-art multimodal large language models reveals that the best-performing model achieves only 0.360 $C_{\text{score}}$, with spatial localization and fine-grained rule understanding emerging as the primary bottlenecks. Our analysis identifies two distinct failure modes: localization-dominated errors and semantics-dominated errors, providing diagnostic insights for future model development.
Authors: Ruihao Xu, Yong Liu, Yansong Tang
Abstract: Food defect detection is critical for automated quality control, yet existing studies lack unified benchmarks and suffer from data scarcity. We introduce FDD-48, a comprehensive dataset with fine-grained annotations across 13 food types and 48 defect categories under diverse real-world conditions. To improve detection with limited labeled data, we propose FDDet, a semi-supervised framework featuring two key components: (1) BBoxMixUp, a data augmentation technique that mixes same-category defect regions to reduce spurious feature associations, and (2) CGPC (Consistency-Guided Pseudo-Label Calibration), which filters pseudo-labels based on intra-sample consistency. Experiments show FDDet significantly outperforms mainstream detectors on FDD-48, demonstrating its effectiveness for food defect detection under data-limited scenarios.
Authors: Ofir Abramovich, Nadav Z. Cohen, Adi Rosenthal, Ariel Shamir
Abstract: Latent video diffusion models generate videos by progressively transforming Gaussian noise into realistic samples conditioned on text or visual inputs. However, existing conditioning methods often require additional training and computational overhead. Motivated by recent findings on the importance of frequency components in generative models, we propose a simple, training-free approach for motion-conditioned video generation by injecting low-frequency phase information from a reference video directly into the diffusion noise latents. Our method transfers motion cues without modifying the model architecture or inference pipeline. Using several applications, we demonstrate effective control over both appearance and dynamics in generated videos, while achieving competitive or superior results compared to more complex conditioning approaches.
Authors: Chieh-Chi Yang, Yu-Hsiang Chen, Yi-Ting Chen
Abstract: Natural-language instructions promise controllable end-to-end driving, but their benefit can be hidden when planners already receive reliable high-level commands. We propose NudgeVAD, a frozen-planner residual framework that uses language as a calibrated nudge to a VAD trajectory. With identity-initialized FiLM and a zero-initialized residual head, NudgeVAD is equivalent to the frozen planner at initialization, so learned deviations arise only from language-conditioned residuals. We evaluate NudgeVAD along a command-reliability axis. With reliable commands, language improves the initial planner but becomes nearly redundant once compared against VAD-FT (UNCOND), a compute-matched VAD model fine-tuned without language. With random commands, however, language becomes essential: detaching text degrades ADE6s to 3.166 m, while NudgeVAD with text recovers 2.806 m and outperforms VAD-FT (UNCOND) by 0.312 m. These results show that language is not universally additive; it is most valuable when the categorical command channel is unreliable.
Authors: Biaoyu Ren (School of Computer Science, Northwestern Polytechnical University, Xi'an, China), Qingsheng Wang (School of Computer Science, Northwestern Polytechnical University, Xi'an, China), Cun Xu (School of Computer Science, Northwestern Polytechnical University, Xi'an, China), Dingkang Yang (College of Intelligent Robotics and Advanced Manufacturing, Fudan University, Shanghai, China), Wenxuan Wang (School of Computer Science, Northwestern Polytechnical University, Xi'an, China, Shenzhen Research Institute of Northwestern Polytechnical University, Shenzhen, China)
Abstract: Referring Remote Sensing Image Segmentation (RRSIS) is a situated, task-driven cross-modal task related to the embodied perception paradigm, requiring models to align visual-spatial features with linguistic intentions for precise target perception. Recent research has focused on refining the granularity of textual features and optimizing image-text feature fusion to better guide target feature representations. However, insufficient descriptive granularity and sensitivity to semantic shifts can cause bottlenecks in cross-modal feature fusion. To address these issues, we propose the Image-Conditioned Instance Prompt Network (ICIPNet) with Bilateral Information Fusion, which is designed to alleviate bottlenecks in cross-modal feature fusion. ICIPNet introduces an Image-Conditioned Instance Prompt (ICIP) module to generate self-adaptive visual and semantic representations without external knowledge. The Bilateral Information Fusion (BIF) module enhances feature fusion along the token and channel dimensions. Experiments demonstrate that the proposed ICIPNet outperforms existing RRSIS models.
Authors: Fufan Zhang, Jingxiang Wang, Xiangjie Ye
Abstract: Amodal instance segmentation aims to predict the complete object mask including occluded regions that lack pixel-level observations and must be inferred with the aid of shape priors. Existing methods acquire shape priors through fixed-capacity encoding spaces or expensive generative models, and inject them uniformly across all spatial positions without adapting to the varying prior demand between visible and occluded regions. In this paper, we propose a gated reliability-adaptive shape prior framework, which introduces a shape prior memory module that combines learnable prototypes via cross-attention to produce instance-adaptive shape priors through weighted prototype combination rather than generation. A spatial adaptive reliability gate then employs the signed distance field of the visible mask to modulate injection intensity at each position according to its occlusion depth, preserving reliable features in visible regions while directing shape compensation toward occluded areas. Experiments on two mainstream amodal instance segmentation benchmarks demonstrate that the proposed method outperforms existing approaches under multiple evaluation settings, improving the mean intersection-over-union over occluded regions by over 11 percentage points on one of the two benchmarks under the standard setting, while using approximately one-third of the total parameters. Linear probing analysis further reveals that the visible-mask cross-attention module implicitly encodes occlusion geometry into visual token representations, explaining the effectiveness of the proposed module decomposition.
Authors: Xinge Peng, Yiting Lu, Xin Li, Zhibo Chen
Abstract: We present IQA-Spider, the first image quality assessment (IQA) framework that unifies reasoning, grounding, and referring into a single LMM-based framework for multi-granularity quality understanding. Existing LMM-based IQA methods typically support only partial perception dimensions, such as quality description and question answering~(\textit{i.e.}, reasoning) or pixel-level grounding. This limitation largely stems from the absence of (i) a unified task and data formulation and (ii) effective optimization paradigms for multi-granularity learning. To address these limitations, we formulate a rigorous four-task paradigm covering global and local quality description, pixel-level grounding, and region-level referring. Based on this formulation, we construct a corresponding IQA dataset with a scalable and automatic annotation pipeline, thereby providing a solid foundation for unified multi-granularity learning. To further enable unified perception, we adopt a conflict-free two-stage design that progressively extends text-level multi-granularity understanding to pixel-level grounding: (i) the first stage equips the model with fine-grained text-level reasoning across multiple IQA tasks, and (ii) the second stage introduces a training-free text-to-point grounding paradigm, which bridges textual semantics and pixel-level perception by mapping token logits to spatial coordinates. Based on these efforts, we achieve IQA-Spider with unified multi-granularity explainable image quality assessment. Extensive experiments across multiple benchmarks demonstrate strong performance, validating the effectiveness and versatility of the proposed formulation and framework.
Authors: Naman Mishra, Shankar Gangisetty, C. V. Jawahar
Abstract: Pedestrian intention and trajectory prediction are critical for the safe deployment of autonomous driving systems, directly influencing navigation decisions in complex traffic environments. Recent advances in large vision-language models offer a powerful new paradigm for these tasks by combining high-capacity visual understanding with flexible natural language reasoning. In this work, we introduce PedestrianQA, a large-scale video-based dataset that formulates pedestrian intention and trajectory prediction as question-answering tasks augmented with structured rationales. PedestrianQA expresses richly annotated pedestrian sequences, in natural language, enabling VLMs to learn from visual dynamics, contextual cues, and interactions among traffic agents while generating concise explanations of their predictions without needing specialized architectures tailored for each task. Empirical evaluations across PIE, JAAD, TITAN, and IDD-PeD show that finetuning state-of-the-art VLMs on PedestrianQA significantly improves intention classification, trajectory forecasting accuracy, and the quality of explanatory rationales, demonstrating the strong potential of VLMs as a unified and explainable framework for safety-critical pedestrian behavior modeling.
Authors: Joshua Siy, Huakun Liu, Yutaro Hirao, Monica Perusquia-Hernandez, Hideaki Uchiyama, Kiyoshi Kiyokawa
Abstract: Human motion diffusion models can synthesize action sequences from text, but controlling motion intensity remains challenging. Existing approaches rely on effort-related adverbs, which are ambiguous and fail to capture quantitative aspects such as pacing, often resulting in flat and monotonous dynamics. We propose an intensity-control framework based on Effort Metric Attention (EMA), a cross-attention module that conditions diffusion on numerical effort signals. Inspired by Laban Movement Analysis (LMA), the framework focuses on the Time and Weight effort factors. We approximate these factors using two kinematic metrics: peak joint positional change for pacing and collective joint positional change for motion amount. EMA enables fine-grained, region-wise control without costly post-hoc optimization. We introduce two evaluation tasks, metric-to-motion consistency and body-part-level effort modulation, to assess numerical fidelity and localized control. Experiments and a user study show near-monotonic alignment between specified effort levels, generated motion dynamics, and established LMA descriptors. These results indicate effective and interpretable control of effort dynamics in practice.
Authors: Zijie Wang, Wei Zhang, Weiming Zhang, Fanqi Zhang, Xiao Tan, Yipeng Qin, Guanbin Li
Abstract: Video world models have achieved strong visual realism, but this does not ensure that their dynamics are truly governed by actions. In this work, we argue that action faithfulness should be understood through the compositional structure of actions, which in many embodied settings follows a group structure (e.g., SE(2) for navigation). Based on this insight, we formalize action-conditioned world modeling as realizing a group action on the state space, providing a principled criterion for evaluating dynamics beyond visual quality. To operationalize this framework, we propose a unified approach that enforces identity, inverse, and composition consistency via latent-space regularization with synthesized supervision, avoiding additional data collection. We further introduce two metrics: Group-Action Consistency (GAC) and Group-Action Robustness (GAR), to evaluate structural correctness and rollout stability. Extensive experimental results show that our method consistently improves both GAC and GAR in state-of-the-art video world models without degrading perceptual quality.
Authors: Ziyan Huang, Lang Wu, Hongji Wang, Yifei Liu, Dongliang Tang, Hongqiao Wang
Abstract: Low-light, long-exposure defocus deblurring remains a challenging problem due to the simultaneous presence of severe blur and complex biased noise. Existing methods typically rely on simplified noise assumptions, which limits their effectiveness under realistic imaging conditions. In this work, we propose Physen-Noise2Noise, a self-supervised deblurring framework guided by the physical model of defocus imaging, which leverages noisy multi-frame observations without requiring clean reference images. Unlike conventional Noise2Noise-based approaches that assume zero-mean noise, we derive a frequency-domain constraint inherent to the defocus imaging process and incorporate it into the learning framework via a learnable noise bias parameter. In addition, a multi-frame noisy initialization strategy is introduced to suppress complex biased noise prior to deblurring, providing a more stable starting point for reconstruction. This formulation explicitly models biased noise and enables joint bias correction and high-frequency detail recovery during training. Furthermore, we develop a pretrain-finetune variant to enhance robustness and generalization under challenging noise conditions. Extensive experiments on both simulation and real-world datasets demonstrate that the proposed method consistently outperforms state-of-the-art self-supervised approaches for defocus deblurring in the presence of complex biased noise.
Authors: XiaoWan Hu, Jing Yang, HeNan Liu, HuaQiu Li, Mai Xu
Abstract: Zero-shot image restoration provides a flexible way to handle diverse degradations without task-specific training. However, existing methods typically rely on stacked layers or pre-trained features to enhance degradation expression, while overlooking physically consistent priors. The insufficient degradation prompts impose the heavy training burden and high sampling costs during zero-shot diffusion. Moreover, the fixed inference trajectory often collapses to suboptimal solutions under complex corruptions. We observe that heterogeneous degradations can be reparameterized into a minimal set of physically coherent parameters for compact representation. Based on this insight, we first propose a unified physical zero-shot image restoration (UP-ZeroIR) framework that explicitly models heterogeneous degradations into a homogeneous all-in-one distribution. The distribution can be optimized directly in the latent space, enabling principled solution exploration and effective prompt adaptation. Besides, we introduce a dynamic quality-refinement strategy that adaptively adjusts the diffusion trajectory for robust globally optimal convergence. Extensive experiments demonstrate that our method achieves state-of-the-art performance across both single and mixed degradations. Our code is available at https://github.com/yangjinglyy/UP-ZeroIR
Authors: Quanjiang Li, Zhiming Liu, Wei Luo, Tingjin Luo, Chenping Hou
Abstract: Multimodal large language models (MLLMs) frequently suffer from object hallucinations, yet the visual perceptual mechanism underlying this failure remains poorly understood. In this work, we reveal that hallucinations are strongly associated with a human-like attention distraction phenomenon, where humans under divided focus experience degraded visual clarity and produce inaccurate descriptions, while in models the same mechanism manifests as spatial inconsistency in multi-head attention and temporal fading of attention to image tokens during decoding. We further provide theoretical insights that attention dispersion increases model complexity and degrades classification generalization. Motivated by these findings, we propose an Attention-Focused Approach for Improved Image Perception (AFIP), which corrects attention distraction via cross-head attention enrichment and reinforces visual grounding through dynamic historical attention enhancement. Extensive experiments on multiple benchmarks and models validate the effectiveness of AFIP without additional training.
Authors: Gunwoo Jeon, Chaesong Park, Jongwoo Lim
Abstract: Event cameras capture brightness changes asynchronously with microsecond resolution, yet existing optical flow methods fail to fully exploit this temporal continuity. Frame-based approaches impose artificial accumulation latency and suffer from domain overfitting, while model-based local methods operate statelessly, discarding temporal history between predictions and yielding inaccurate flows. We propose \textbf{LC-Flow}, the first temporally continuous, learning-based optical flow estimator that operates purely from local events. At its core, a Continuous Local Recurrent Network maintains persistent hidden states per spatial grid, incrementally accumulating temporal context as events arrive. Unlike frame-based methods constrained to fixed accumulation windows, and unlike stateless model-based methods that recompute motion from scratch at each step, LC-Flow produces sparse local flow estimates at arbitrary timestamps with full motion history. To address the inherent ambiguity of local observations, we jointly learn a confidence score that quantifies the reliability of each prediction, explicitly handling event sparsity and the aperture problem. This confidence serves a dual role: filtering unreliable estimates for downstream tasks such as visual odometry, and providing principled weights for a multi-scale confidence-guided aggregation that reconstructs globally consistent flow from the sparse local outputs. LC-Flow achieves state-of-the-art performance among local methods on both MVSEC and DSEC, while the confidence-guided aggregation establishes a new overall state-of-the-art on the MVSEC benchmark, surpassing heavy frame-based networks that rely on global spatial priors.
Authors: Ghassen Marrakchi, Basarab Matei
Abstract: Scattering transforms achieve Lipschitz stability and translation invariance, but dense prediction tasks require preserving spatial structure lost in global averaging. We propose Phase-Aware Scattering Encoder-Decoder, which restores this information by explicitly preserving phase in skip connections. On image denoising (BSD68), breaking translation invariance improves PSNR by $+2.17$~dB; phase preservation adds $+1.03$~dB. A novel spatial shuffling ablation ($-1.26$~dB penalty) demonstrates phase encodes location-dependent structure. We conduct a preliminary extensibility study on a second dense prediction task (ISIC skin lesion segmentation), with full cross-validation as ongoing work. This work advances principled wavelet-deep learning integration, showing how phase information complements scattering's stability-expressiveness trade-off in pixel-level prediction.
Authors: Chris Ge, Rohit Gandikota, Antonio Torralba, Tamar Rott Shaham
Abstract: In-context image generation models such as FLUX.2 take a text prompt and an optional reference image as visual conditioning for the output. Internally, all three inputs -- text, reference image, and the noise tokens -- are concatenated and processed through a single attention stream, where all tokens can attend to one another. This leaves open how reference information flows through the model to produce the output image. We show that an implicit cross-modal binding emerges between the text tokens and the reference image: the text tokens absorb visual reference content during the forward pass, and that absorbed content causally influences the generated output. We surface this binding with three causal interventions on FLUX.2: T2I Lens, which decodes intermediate text-token activations through a text-to-image path; Attention Knockout, which severs specific attention edges; and I2I-to-I2I Patching, which copies text token activations between editing runs. Across 2,875 editing tasks on various images, including SUN397 and DreamBench++ datasets and images collected online, we observe a consistent division of labor: properties of the reference image, like color, style, and scene setting, are first written into the text tokens, which carry them to the generated image; pixel-exact properties like a specific face or instance identity bypass the text tokens and flow directly from reference to image through image-to-image attention. We further localize the reference-text binding to the padding tokens of the text sequence. These results show that text tokens in a multimodal DiT are not just prompt holders, but a structured channel for reference image content. More broadly, they suggest that even in unified-attention multimodal generative models, token modality structures how conditioning information is represented and routed across the network.
Authors: Toufiq Musah, Salvatore Calcagno, Federica Proietto Salanitri, Xiaomeng Li, Maruf Adewole, Marawan Elbatel
Abstract: Ultra-low-field (ULF) MRI offers portable and accessible neuroimaging but suffers from reduced signal-to-noise ratio and limited spatial resolution compared to high-field (HF) systems. Acquiring paired ULF-HF data for supervised enhancement is often difficult, particularly in resource-limited settings. We introduce ULF-Synth, a framework that combines: (i) acquisition-based synthesis of realistic ULF images from HF volumes to create large-scale paired training data, (ii) a spatial-frequency domain objective that prioritizes recovery of high-frequency anatomical detail. This formulation is architecture-agnostic, consistently improving structural similarity and perceptual fidelity across encoder-decoder, adversarial, and diffusion-based translation models. When trained exclusively on synthetic data, the resulting models generalize effectively to real 64mT ULF acquisitions, improving downstream multiclass brain segmentation and achieving higher radiologist preference and diagnostic acceptability in a blinded reader study. These findings demonstrate that synthetic paired supervision provides a practical and scalable pathway for enhancing ULF MRI without requiring real paired acquisitions. Code, Models and Dataset: https://github.com/toufiqmusah/ULF-Synth
Authors: Adam Lee
Abstract: Recent progress of video diffusion models have enabled extensive simulation of the physical world. While simulation with hand object interaction has been less explored. We propose DexSIM, a dexterous simulation framework for simulating dexterous manipulation in real-time. While previous works utilizing video diffusion and 3D reconstruction focus on navigation, dexterous manipulation has been limited while it has extensive applications for creating interactive experiences with the simulated world and for generating synthetic data for robotics. Existing methods lack real-time interactivity and long-term spatial consistency and memory. We propose a 2-stage training framework for DexSIM. First we train a bi-directional video diffusion model by jointly embedding the hand action trajectory and video in a unified feature space. We utilize gaussian heatmap hand encoding for more accurate hand representation. Then we conduct a roll-out based autoregressive training with updated spatial cache as attention sink for spatial memory, which improves long-term consistency and 3D aware dexterous manipulation simulation. DexSIM outperforms the baseline on pixel and semantic similarity, motion fidelity, and hand projection accuracy. It also allows new applications such as hand motion transfer and runs at 15.24 FPS real-time interactivity.
Authors: Amsisan Tran, Baogh Le, Tuan Kiet Pham, Sui Yang Guang
Abstract: Composed image retrieval (CIR) searches a corpus with a reference image and a text describing how to modify it. Despite rapid progress from triplet-trained compositors to zero-shot and generative methods, essentially all systems share one assumption: that a query maps to a single target, scored by Recall@K against one annotation. We argue this is fundamentally at odds with the task. A query such as make it more formal does not name an image but a region of the corpus, and which member the user intends is genuinely underdetermined. This underspecification is the root of the well-known false-negative problem and leaves current models unable to tell a precise query from an ambiguous one. We reframe CIR as calibrated intent resolution under uncertainty: a retriever is wrapped in a conformal prediction layer that returns a candidate set with a coverage guarantee and whose size is a principled measure of ambiguity; when the set is large, an expected-information-gain policy asks the single most useful clarifying question, drawn from interpretable ambiguity axes, and the set contracts. We introduce AmbiCIR, a benchmark and human-validated user simulator that revive the dormant auxiliary and dialogue annotations of CIRR and extend the multiple-positive setting of CIRCO. Across open-domain and fashion benchmarks our method matches single-turn state of the art, confirming calibrated resolution is cost-free on precise queries, while reaching the intended target in a fraction of the interaction budget required by naive conversational baselines, and it is the first to report valid coverage and calibration for the task.
Authors: Ruihao Xu, Yong Liu, Yansong Tang, Sule Bai, Xubing Ye, Bingyao Yu, Yutao Guo, Jiwen Lu, Jie Zhou
Abstract: With the widespread application of drones in recent years, object detection of aerial images has attracted increasing attention, especially open-vocabulary aerial detection which is not restricted to predefined categories. Due to the scarcity of drone's viewpoint images and their significant differences from natural images, it is difficult to achieve satisfying results by directly applying vanilla open-vocabulary detection methods designed for natural scenarios. Some studies propose to transfer knowledge from pre-trained models by using lightweight networks or generating pseudo labels, but they tend to rely on models trained on natural images, neglecting the potential of foundation models specifically tailored for remote sensing and aerial imagery. To address this limitation, we propose DisDop, a unified framework that systematically distills multi-level domain priors from remote sensing foundation models (e.g., RemoteCLIP and DINOv3) into a lightweight detector. Specifically, we first distill visual priors through a teacher fusion strategy that combines RemoteCLIP's cross-modal alignment capability with DINOv3's fine-grained local feature extraction ability, transferring their complementary strengths to the detector's backbone. Second, we distill textual priors embedded in RemoteCLIP's text encoder by explicitly modeling inter-category semantic relationships, while incorporating global contextual priors to enhance local feature representation for small objects. Through this multi-level prior distillation framework, our DisDop achieves new state-of-the-art performance on open-vocabulary aerial detection benchmarks. Extensive ablation analysis also demonstrates the rationality and effectiveness of our proposed modules.
Authors: Yurou Yang, Muyuan Lin, Roberto Martin-Martin, Martin Labrie, Shreekant Gayaka, Cheng-Hao Kuo, Luca Carlone
Abstract: Recent work explores new opportunities at the intersection of vision-language-action models (VLAs) and geometric foundation models (GFMs) for 3D reconstruction, such as VGGT. While the resulting geometric VLAs often show improved performance, it remains unclear (i) if modern VLAs already have sufficient geometric understanding to start with, (ii) what is the best architecture to inject geometric understanding into a VLA, and (iii) what is the effect of other design choices that affect geometric VLAs. In this paper we provide a rigorous experimental analysis to shed light on these questions, for a specific choice of VLA (GR00T-N1.5) and GFM (VGGT). Our first contribution is to formalize prior work's intuition that current VLAs lack geometric understanding, by providing a rigorous analysis based on linear probing. The analysis quantifies, for the first time, the "geometric gap" between VLAs and GFMs. Our second contribution is to identify and compare different strategies to bridge GFMs with VLAs. We implement three different architectures, which differ in the way they inject geometry in the VLA, while keeping low-level implementation details as similar as possible, to ensure a fair comparison. Finally, we analyze the impact of non-architectural choices (e.g., training data, number of cameras, reconstruction quality) on the performance of the geometric VLAs.
Authors: Yan Li, Lin Liu, Xiaopeng Zhang, Qi Tian
Abstract: Instruction-based video editing requires transforming a source video according to a natural-language instruction while preserving irrelevant content and remaining temporally coherent. We argue that existing Diffusion Transformer (DiT) editors struggle with this task for two structural reasons. First, conditioning signals are fed undifferentiated into all transformer blocks, forcing a single token stream to encode both global editing intent and fine-grained visual evidence. Second, the cross-attention patterns that govern the edit are supervised only indirectly through pixel-level reconstruction, leaving the model's internal reasoning process under-constrained. To address both limitations, we propose RVEDiT, an implicit Reasoning Video Editing DiT framework built around two complementary components. The first, Granularity-Routed Token Conditioning, introduces learnable editing tokens distilled from a multimodal LLM and routes them to shallow blocks, while reserving native visual and textual tokens for deeper blocks, thereby inducing a coarse-to-fine editing process inside the backbone. The second, Reference-Anchored Attention Alignment, employs a parameter-sharing reference branch during training and maximizes the mutual information between the attention features of the editing and reference branches, regularizing the model's internal reasoning without incurring any additional inference cost. Experiments on standard instruction-based video editing benchmarks show that RVEDiT consistently outperforms state-of-the-art baselines, with particularly strong gains on localized and compositional edits.
Authors: Bo Li, Ronghao Chen, Ningyuan Deng, Huacan Wang, Shaolin Zhu, Lijie Wen
Abstract: Translating text embedded in Web images is crucial for improving content accessibility and cross-lingual information retrieval, particularly within social media and e-commerce domains. Although Large Vision-Language Models (LVLMs) have advanced multimodal understanding, applying them to Web image translation remains challenging due to the visual representation gap: standard encoders often prioritize high-level semantics over the fine-grained visual details required for recognizing diverse character morphologies. To address this challenge, we propose VaaWIT, an end-to-end framework that adapts Large Language Models for multilingual Web image translation. The framework introduces two key technical contributions: (1) a Dual-Stream Attention Module (DSAM), which facilitates bidirectional interaction between multilingual semantic features and detailed visual representations, thereby synthesizing unified features robust to textual variations; and (2) a Visual-Aware Adapter (VAA), a parameter-efficient fine-tuning strategy that dynamically injects these fused visual cues into the frozen LLM backbone. This design enables the model to align the visual context with linguistic reasoning effectively while minimizing computational costs. Extensive experiments on eight tasks on three public benchmarks demonstrate that VaaWIT significantly outperforms state-of-the-art (SOTA) open-source baselines and achieves competitive performance against proprietary models. These results validate the efficacy of integrating fine-grained visual perception into LLMs for complex Web content analysis.
Authors: Jiaxiang Liu, Jiawei Du, Xupeng Chen, Guoqi Li, Jiang Cai, Simon Fong, Mingkun Xu
Abstract: Cross-subject brain-to-visual decoding remains a core challenge in brain-computer interfaces due to severe inter-individual variability that induces systematic subject-specific functional misalignment. To address this issue, we propose MindAdapter, a parameter-efficient few-shot calibration framework for pretrained brain-to-visual decoding models. MindAdapter adopts a decoupled linear-residual cascade alignment paradigm by freezing a pretrained explicit brain functional alignment backbone (coarse) and introducing a lightweight nonlinear residual adapter (fine), thereby disentangling global cross-subject correspondence from subject-specific residual corrections for fine-grained spatial and semantic calibration. To further preserve global representational stability, we design a topology-anchored dual-stream manifold constraint, where a small set of shared stimuli serves as topological pins with voxel-level paired supervision, while a semantic stream enforces consistency through a frozen vision-language decoder on unpaired brain data. Together, MindAdapter efficiently injects subject-specific corrections while maintaining the global representational geometry learned during pretraining. Experiments on the Natural Scenes Dataset (NSD) demonstrate that MindAdapter substantially improves cross-subject visual reconstruction and retrieval accuracy using only a few shared stimuli, offering a practical and data-efficient solution for personalized brain-to-visual decoding.
Authors: Ruyi Chen, Lu Zhou, Xiaogang Xu, Chiyu Zhang, Jiafei Wu, Liming Fang
Abstract: Text-to-Image (T2I) models have made significant strides in visual realism and semantic consistency, yet they often perpetuate and amplify societal biases. Existing evaluation methods typically address only single-dimensional biases, lacking perspectives to uncover model biases at social-related deeper semantic levels. We introduce HoloFair, a comprehensive benchmark framework for multidimensional demographic bias analysis. Built upon our large-scale fairness-oriented dataset and the SpaFreq (Spatial-Frequency) attribute classifier, this framework proposes the Multi-attribute, Group-wise Bias Index (MGBI) metric, designed to assess both intrinsic diversity and conditional biases. Beyond evaluation, we further introduce Fair-GRPO, a reinforcement-learning-based debiasing method that alters the distribution of generative models through a designed multi-objective reward function. E.g., experiments on the SD3.5-Medium model demonstrate that Fair-GRPO significantly improves multidimensional fairness while maintaining high image quality. We also analyze potential reward hacking phenomena and provide corresponding mitigation strategies. Code and dataset are available at https://github.com/1059684669/HoloFair
Authors: Raju Imandi, Chethana B, Bharatesh Chakravarthi, Yong-Guk Kim, Manipriya S, Pavan Kumar B N
Abstract: Detecting objects reliably under extreme low-light conditions is an open problem in computer vision, with practical urgency in applications ranging from nighttime surveillance to search-and-rescue robotics. Conventional RGB cameras degrade sharply at low photon flux, while event cameras which record asynchronous per-pixel brightness changes at microsecond resolution and high dynamic range provide complementary structural cues that are largely illumination-invariant. We present AdaFuse-Det, a dual-stream framework that fuses CLAHE-enhanced RGB frames with voxelized event tensors through an Adaptive Cross-Modal Fusion (ACMF) module grounded in minimum-variance linear estimation theory. We formally show that the learned attention map asymptotically recovers the Gauss-Markov optimal fusion weights, and establish event conservation and temporal resolution bounds for the voxelization stage. On the LLE-VOS benchmark, AdaFuse-Det achieves a Recall of $65.54\%$, Precision of $53.85\%$, and F1-Score of $59.12\%$ under severe illumination degradation, outperforming single-modality detectors in recall by a margin that reflects the theoretically predicted illumination-adaptation behavior.
Authors: Yonghao Zhao, Zexin Yin, Jian Yang, Beibei Wang, Jin Xie
Abstract: Creating relightable urban scenes from images or videos is widely useful but highly ill-posed. Urban environments are typically unbounded and extend beyond the visible regions. As a result, many portions of the scene remain unobserved, yet these invisible regions can cast shadows onto visible areas. Reasonably modeling shadows cast by such invisible regions is challenging and poses a significant obstacle to creating relightable urban scenes. At the same time, sparse input views and complex illumination conditions further complicate relighting, as they introduce severe ambiguities in material decomposition. In this paper, we propose Shadow-guided Relightable Urban Scene with Generation model (SRUG), a novel framework designed to address relighting challenges in urban scenes. SRUG leverages shadows to guide a 3D completion model for recovering the geometry of invisible regions, promoting the synthesis of physically reasonable shadows. In addition, SRUG employs an iterative material decomposition scheme that applies the large material model (LMM) to provide material supervision and iteratively decompose the scene's material properties, enabling robust material decomposition. Building upon these components, we introduce a physically-based lighting model that captures the complex illumination of urban scenes and supports reliable relighting. Extensive quantitative evaluations and visual comparisons demonstrate that our method outperforms existing approaches in both novel view synthesis and relighting tasks.
Authors: Amit Agarwal, Hitesh Laxmichand Patel, Meizhu Liu, Jyotika Singh, Karan Dua, Hansa Meghwani, Matthew Rowe, Michael Avendi, Yassi Abbasi, Tao Sheng, Sujith Ravi, Dan Roth
Abstract: Reference-free image-to-text evaluators are now standard for scoring image-caption alignment, yet it is unclear whether they respect semantic invariances. We present an invariance probe on five popular evaluators (CLIPScore, PAC-S, UMIC, FLEUR, and a deterministic LLM judge) under semantics-preserving perturbations along three axes -- spatial (flips, context-preserving repositioning, light rotations), object (scale, category), and socio-linguistic framing (cultural/economic adjectives with neutral and length-matched controls). Across curated slices of three detection datasets and three caption evaluation suites, we find consistent non-semantic sensitivities, where benign spatial edits and simple phrasing changes shift scores by $\approx$6--9\% on average, and for systems separated by just 0.7\%, these shifts can cause ranking flips in up to $\sim$37\% of cases, particularly under spatial changes. A small human study also supports this finding and confirms that annotators generally judge perturbed pairs as equally correct, so these shifts reflect metric behavior rather than semantic change. We further propose invariance-calibrated scoring, a post-hoc adjustment that roughly halves median absolute sensitivity while retaining correlation with learned caption evaluators.
Authors: Swapna Pillai, Siddharth Singh Savner, Sujit Kumar Sahoo
Abstract: This letter introduces a physics-informed self-supervised framework for sonar image despeckling that reformulates despeckling as residual consistency in the homomorphic log domain. By constraining the log-ratio residual to obey multiplicative speckle statistics, the proposed method eliminates the need for clean supervision while preventing degenerate identity solutions. A variance-targeted statistical loss combined with edge-aware structural regularization and median-guided curriculum stabilization enables effective speckle suppression with preserved structural fidelity. This formulation along with a lightweight neural network achieves state-of-the-art performance across multiple real sonar datasets and demonstrates excellent cross-dataset robustness, while remaining suitable for real-time deployment.
Authors: Zhi Qin Tan, Owen Addison, Yunpeng Li
Abstract: High degrees of disagreement among annotators can exist for ambiguous objects, e.g. in medical images, underscoring the challenges of establishing ground truth annotations in object detection tasks. Despite this, all existing object detectors implicitly require access to ground truth annotations for either training or evaluation. The fundamental questions we target are: How can we learn an object detector with multiple annotators' annotations but without objective ground truth annotations due to object ambiguity, and how can we enable the learned detector to express meaningful model predictive uncertainties in detecting ambiguous objects? To answer these questions, we present an interpretable approach to calibrate probabilistic object detectors, where the calibration goal is to align the class confidence and bounding box variance estimates to the annotators' annotation distribution. We introduce an efficient yet effective framework to calibrate probabilistic object detectors by designing four evaluation metrics to measure calibration errors regarding classification and localization, and proposing a train-time calibration and post-hoc calibrator, all without the need to access any ground truth. This framework is generalizable to many existing probabilistic object detectors, such as the YOLO families and two-stage detectors. Empirical results with real-world and synthetic datasets of medical and natural images demonstrate the superior performance of the proposed framework with three popular object detectors.
Authors: Mohammad Alijanpour Shalmani, Alale Rezvani Boroujeni, Ali Amini, Jiann Shiun Yuan
Abstract: High-resolution printed circuit board (PCB) inspection suffers from resolution collapse when full-board images are resized to standard detector inputs: micro-scale defects shrink to a few pixels and are missed. Tile-based inference preserves local detail but introduces boundary artefacts at tile edges, causing split detections and false negatives. We present a systematic comparison of five inference strategies evaluated on two high-resolution PCB defect datasets, PCB-Defect (230 images, 1704 annotations) and HRIPCB (693 images, 2 953 annotations), spanning six defect classes. We show that training-inference scale consistency is critical: a detector trained on full images collapses to mAP@50 = 0.01 under tile inference, while the same architecture trained on 640*640 tile crops achieves 0.72 and 0.94 on the two datasets respectively. We further exploited Topology-Aware Tile Merging (TA-TM), a training-free post-processing method that builds a tile-adjacency graph and adjusts boundary-sensitive detection scores using neighbour-tile agreement before global NMS. Across both datasets, adding 128 px tile overlap raises boundary-zone recall from ~26-63% to ~70-100%, TA-TM achieves the best mAP@50 on both benchmarks, and tile inference recovers 46-100% of small defects missed entirely by full-image methods. Results are consistent across datasets, confirming the generalizability of the proposed strategy. TA-TM requires no retraining and is architecture-agnostic, making it directly applicable to existing PCB inspection pipelines.
Authors: Avery Gump, Connor Henley, Sungjin Cheong, Akarsh Prabhakara, Mohit Gupta
Abstract: Modern LiDARs are rapidly transitioning from bulky, mechanically scanned systems to ultra-compact, low-cost, solid-state arrays. This miniaturization-while enabling scalability, affordability, and camera-like data structures-introduces a new and severe failure mode: internal-multipath glare. When light from a bright or retroreflective surface reflects and scatters within the LiDAR, light that should reach a single pixel spreads across the pixel array. The resulting artifacts create phantom objects, obscure real ones, and produce safety-critical "ghosts in the point clouds." This paper introduces a physically grounded sensing model and algorithmic techniques for addressing this effect. We show that internal glare can be represented as a linear, scene-independent operator-the Transient Glare Spread Function (TGSF)-acting on the transient measurements. Building on this model, we develop a training-free approach that operates on low-level LiDAR detections (or echoes) prior to point-cloud formation, leveraging knowledge of the glare spread function to reason about the likelihood of each detection arising from glare. The resulting approach is compatible with existing LiDAR signal-processing pipelines, and deployable on unmodified commercial sensors. Using experiments with real single-photon LiDAR hardware, we demonstrate substantial suppression of severe glare artifacts while preserving true scene structure.
Authors: Ismail Lamaakal
Abstract: Neural network weights are increasingly a bottleneck for deployment, yet most compression pipelines treat layers independently and overlook cross-layer redundancy induced by function-preserving symmetries. We propose Motion-Compensated Weight Compression (MCWC), a weight-only codec that aligns permutation-symmetric blocks (e.g., hidden units and attention heads) to maximize cross-layer correspondence, turning depth into a predictable sequence. In the aligned coordinate system, MCWC uses a lightweight layer-sequential predictor with periodic keyframes and encodes only quantized prediction residuals using a learned entropy model trained under a rate distortion objective. A simple decoder reconstructs deployable weights by entropy decoding, dequantization, predictor-driven reconstruction, and inverse alignment, enabling fast weight materialization for inference. Across Transformer language modeling and vision classification, MCWC improves the rate accuracy Pareto frontier over strong quantization and learned weight-codec baselines, while maintaining competitive decode time. Ablations confirm that alignment, prediction, entropy modeling, and keyframe scheduling are each necessary for the full gains. Our code is available via https://github.com/Ism-ail11/MCWC.
Authors: Po-Chien Luan, Zimin Xia, Wuyang Li, Yang Gao, Alexandre Alahi
Abstract: We propose Drift-Resistant Navigation World Model, a generative model that mitigates both perceptual drift and geometric drift in conventional rollout-based navigation world models. Existing methods recursively feed generated content into subsequent steps, causing noise accumulation and degraded predictions, i.e., perceptual drift. Meanwhile, their predictions often deviate from the agent's motion, resulting in geometry drift. We address both types of drift by redesigning world-model prediction as an anchor-guided rollout. Instead of rolling out every frame sequentially, we first predict sparse future anchors that serve as stable long-range targets, and then generate intermediate frames within each chunk conditioned on both past context and future anchors. Importantly, these sparse anchors also provide geometric constraints, supported by bidirectional epipolar geometry, to localize where corresponding content should appear in the intermediate frames. Experiments on four benchmarks demonstrate consistent improvements over strong baselines in long-horizon visual quality, geometric consistency, and multi-view coherence. These gains further translate into improved downstream planning performance under the same planners, highlighting the importance of drift-resistant, geometry-aware prediction for reliable navigation world models.
Authors: Zihao Zhu, Kuan-Ru Huang, Zhaoming Xu, Renjie Li, Bo Wu, Ruizheng Bai, Mingyang Wu, Sayak Paul, Zhengzhong Tu
Abstract: High-resolution datasets are essential for advancing super-resolution (SR) and text-to-image (T2I) diffusion research. However, current publicly available datasets lack both the native 4K resolution and the extensive scale necessary for training state-of-the-art models. To address this gap, we introduce a 4K Large Scale Dataset and Benchmark (4KLSDB), a large-scale, diverse dataset consisting of 129,484 carefully curated 4K resolution images spanning multiple categories such as nature, urban scenes, people, food, artwork, and CGI, alongside distinct validation and test sets containing 2,000 and 1,984 images respectively. Images were sourced from established open datasets including Photo Concept Bucket, Laion2B, and PD12M. 4KLSDB underwent rigorous multi-stage automated filtering and annotation pipelines involving both human annotators and Large Multimodal Models (LMMs) to ensure high aesthetic quality and dataset consistency. We demonstrate 4KLSDB's effectiveness by training representative super-resolution and diffusion models, observing significant improvements in performance on native 4K benchmarks. Comprehensive experiments illustrate a positive correlation between training on true 4K resolution data and improved fidelity in image restoration task, especially on 4K resolution. We provide the research community a valuable resource to drive progress toward genuinely high-fidelity image synthesis and restoration by providing 4KLSDB. Our project page is available at: https://4klsdb.github.io/.
Authors: Daniele Picone, Mohamad Jouni, Mauro Dalla-Mura
Abstract: Hyperspectral image restoration faces several challenges, including limited training data, strong sensor specificity, and high spectral dimensionality. These limitations hinder the learning of robust hyperspectral priors, motivating the reuse of priors learned from large-scale RGB data. In this work, we propose a minimally trained, lightweight adapter that repurposes frozen pretrained RGB denoisers for hyperspectral restoration through a projection mapping. The method denoises low-dimensional spectral projections and reconstructs the hyperspectral cube through constrained linear aggregation, while preserving plug-and-play compatibility and the stability properties of the underlying RGB denoiser. Experiments on denoising, deblurring, and super-resolution across multiple datasets demonstrate consistent improvements over hyperspectral-specific baselines, showing the strong transferability of large-scale RGB priors.
Authors: Bruce Changlong Xu, Jose James, Alexander Ryu
Abstract: Classical noisy-label theory predicts that downstream performance under weak supervision is bounded above by the labeler's accuracy, implying a sharp crossover: once a gold-trained classifier matches the labeler, weak labels stop helping and start hurting. The prediction is theoretical; what is missing is a benchmark calibration that turns it into an instance-level statement for modern foundation-model labelers. We provide such a calibration for BiomedCLIP-generated weak labels on three medical-imaging benchmarks (PCAM, ISIC, NIH-CXR) and six downstream architectures spanning an 11x parameter range. The crossover predicted by theory appears at ng~100 on PCAM, 20-50 on ISIC, and 250-500 on NIH-CXR; weak labels above the crossover degrade AUC by up to -0.10. The location is architecture-invariant for four of five pretrained architectures, and a within-family DenseNet sweep (2.5x parameters, identical pretraining) supports the view that the labeler, not the student, is the dominant constraint. The calibration in turn produces a decision rule operable from 10-20 gold labels: compare gold-only AUC to VLM accuracy on the user's gold set. A structured-vs-random noise sign flip on NIH-CXR shows that the rate-only formulation of the bound is incomplete and identifies a concrete refinement (label-space projection) that future benchmarks can be designed to test.
Authors: Donghyun Kim, Chanyoung Kim, Eunseo Jeong, Youngjoong Kwon, Seong Jae Hwang
Abstract: Recent advances in monocular 3D human pose estimation enable accurate body tracking from video. However, translating these kinematic estimates into physical quantities, such as joint torques, remains challenging due to noise amplification through inverse dynamics. In this work, we provide a systematic analysis of how pose estimation noise propagates through the inverse dynamics pipeline. We present three key findings: (1) pose noise is amplified by approximately 1,000x when computing joint torques via numerical differentiation, (2) proximal joints (spine, hips) are up to 10x more sensitive to noise than distal joints (wrists, hands), and (3) low-pass filtering before differentiation substantially reduces this amplification. To enable this analysis, we develop SMPL-Dynamics, a fully differentiable inverse dynamics module for the SMPL body model that requires no external physics simulators. Our module supports end-to-end gradient computation, and we demonstrate this through differentiable pose refinement, which reduces torque error by 93% with negligible change in pose.
Authors: Yuli Wang, Hyewon Jung, Dongshen Peng, Yuwei Dai, Jing Wu, Haoyue Guan, Yoko Kato, Zhicheng Jiao, Yu Sun, Ihab Kamel, Joao Lima, Cheng Ting Lin, Harrison Bai
Abstract: Vision Transformer (ViT) models, utilizing self-attention mechanisms, have demonstrated robust generalization capabilities across various vision tasks, including image classification. However, these models, typically pretrained on general public datasets, often lack the specialized domain knowledge necessary for medical imaging applications. In this study, we investigate the adaptation of ViT models, specifically for cardiac magnetic resonance (MR) images, using an in-house dataset. We found that pretrained ViT features do not effectively transfer to the cardiac MR domain. To overcome this limitation, we introduce an adaptation strategy that utilizes image-based self-supervised contrastive learning, demonstrating superior performance compared to traditional supervised training approaches. Moreover, our adapted ViT model exhibits strong generalization to external MR datasets such as BraTS and ADNI. Through ablation studies, we further investigate the impact of batch size and dataset scale on performance. Ultimately, our adapted model achieves classification AUC exceeding 0.75 across the four most common cardiac MR sequences.
Authors: Ojonugwa Oluwafemi Ejiga Peter, Frederick Akor Ejiga, Fahmi Khalifa, Md Mahmudur Rahman
Abstract: The major limitations of gastrointestinal (GI) endoscopy AI systems arise from a shortage of annotated data, strict privacy policies, and significant bottlenecks in conventional model fine-tuning. Such limitations impede the successful application of sophisticated AI models in clinical practice, particularly affecting the reliability and scalability of diagnosis. In this paper, we present a dual-pipeline PEFT model that addresses two fundamental problems: medical Visual Question Answering (VQA) and the generation of privacy-preserving synthetic data. For clinical VQA, we adopt the Florence-2 vision-language model. Leveraging PEFT enhances model interpretability while substantially reducing the computational cost of training. Simultaneously, we employ Low-Rank Adaptation (LoRA) with Stable Diffusion 2.1 to generate high-quality GI images that enhance training databases without violating patient privacy. This research utilized the Kvasir-VQA dataset. Our Florence-2 VQA model achieved ROUGE-1 of 0.92, ROUGE-L of 0.91, and BLEU score improvements from 0.08 to 0.24. Fine-tuning on private datasets consistently showed better results than fine-tuning on public datasets. The rank-4 LoRA synthesis achieved optimal performance with a fidelity score of 0.290, an agreement score of 0.730, and a Frechet BiomedCLIP Distance (FBD) of 1450, reducing computational costs by almost 90 percent. This framework improves the clinical potential of AI in GI endoscopy. Compared to FLUX, MSDM, and Kandinsky 2.2, our model demonstrates superior FBD and strong semantic alignment. While other models lead in Fidelity or Agreement, our lower FBD indicates better image-text coherence. These results establish our approach as a robust solution for enhancing VQA and synthetic data generation in clinical AI.
Authors: Lin Qiu, Hanqing Zeng, Yao Liu, Bingjun Sun, Guangdeng Liao, Ji Liu
Abstract: Reinforcement learning (RL) has emerged as an effective paradigm for improving the reasoning capability of vision-language models (VLMs). However, RL-based optimization typically depends on costly high-quality annotations that are difficult to scale. Existing unsupervised alternatives may drift toward biased solutions due to weak visual grounding and the lack of reliable verification signals. We propose a self-evolving post-training framework, DUEL, where supervision emerges from adversarial interactions between two policies initialized from the same pretrained VLM. A Challenger generates an image-grounded true claim together with a minimally perturbed hard-negative counterpart, while a Solver verifies both claims against the image, encouraging fine-grained visual discrimination under near-neighbor semantics. To stabilize optimization, we introduce a length-normalized log-likelihood reward that preserves informative optimization signals beyond binary outcome supervision and improves learning stability under sparse feedback. Experiments show that DUEL consistently improves visual reasoning and robust discrimination without additional human annotations, external reward models, or image editing tools.
Authors: Jie-En Yao, Hong-En Chen, C. -C. Jay Kuo
Abstract: Deep neural networks trained with backpropagation have achieved outstanding performance in vision tasks but remain biologically implausible, computationally demanding, and difficult to interpret. The Forward-Forward (FF) algorithm offers a promising alternative by training each layer independently through local goodness objectives. However, its purely local optimization lacks hierarchical coordination across layers, and the decoupling of goodness from features leaves the representations unconstrained and semantically ambiguous. We propose a Hierarchical and Contrastive Learning FF framework (HCL-FF) to address these limitations. HCL-FF introduces (1) a coarse-to-fine hierarchical learning strategy that guides representations from low-level cues to high-level semantics, and (2) a supervised contrastive objective that enforces class-discriminative alignment after goodness decoupling. Experiments on CIFAR-10, CIFAR-100, and Tiny-ImageNet demonstrate that HCL-FF achieves new state-of-the-art performance among FF-based methods, with notable accuracy gains of +5.46%, +17.00%, and +12.51%, respectively.
Authors: Zhipeng Ye, Jiaqi Huang, Feng Jiang, Qiufeng Wang, Yikang Duan, Dawei Wang, Xihang Zhou, Qian Qiao
Abstract: Multimodal Large Language Models (MLLMs) have demonstrated strong capabilities across a wide range of vision language tasks. However, when applied to large scale image classification, their performance degrades significantly as the label space expands a phenomenon we define as Performance Collapse in Long Sequence Recognition. Through an information theoretic analysis, we reveal that this collapse stems from a fundamental conflict between the escalating information entropy and the prominent attention dilution and decay within attention mechanisms, which impairs the model's ability to maintain a sufficient signal-to-noise ratio when processing extremely long prompts. To mitigate this, we propose Divide-and-Conquer Inference (DCI), a novel test-time scaling strategy for visual recognition with MLLMs. DCI recursively decomposes complex global classification tasks into multiple simpler, localized subproblems and employs a dynamic pruning mechanism to compress the search space. This method effectively improves the local signal to noise ratio and model accuracy by mitigating the inherent weight dilution issues in long-sequence inference. Moreover, while traditional self-attention incurs a prohibitive quadratic computational complexity, DCI achieves more favorable scaling behavior and substantially accelerates inference in large scale classification scenarios. Extensive experiments on benchmarks such as ImageNet-1K and ImageNet-21K demonstrate that DCI consistently improves classification accuracy. This enables lightweight open-source models to rival or even surpass frontier closed-source giants without any additional training or fine-tuning. As a model-agnostic, plug-and-play paradigm, DCI offers an efficient approach for scaling the inferential precision of MLLMs in large-scale scenarios.
Authors: Yumeng He, Xiaoying Wang, Peihao Li, Yanjia Huang, Joe Masterjohn, Jiajun Wu, Leonidas Guibas, Yin Yang, Ying Jiang, Chenfanfu Jiang
Abstract: Large-scale controllable 3D assets are critical for computer graphics, embodied AI, robotics, and interactive content creation, yet creating diverse 3D assets remains challenging due to the high cost of manual modeling and rigging. Shape deformation offers a natural way to generate variations from existing meshes, but existing data-driven methods often rely on sparse user inputs, while parametric editing frameworks require manually designed control structures and category-specific configurations. Inspired by natural creatures, where a central spine governs global shape and cross-sectional ribs control local variation, we introduce Fishbone, a unified rib-spine representation for general shapes that supports controllable parametric mesh deformation, reduced-space dynamics, and animation. Given an input mesh, Fishbone computes a geodesic scalar field with an adaptive heat method, extracts iso-contours as cross-sectional ribs, constructs a smooth geometry-aware spine through rib centers, and associates surface vertices with nearby rib and spine structures using Gaussian-weighted skinning. The resulting representation enables real-time and predictable deformation: ribs control local profiles such as thickness, orientation, and cross-sectional variation, while the spine controls global bending, twisting, and stretching. The same structure also supports reduced-space simulation and keyframe animation. We further construct Fishbone-136K by augmenting Hunyuan3D with rib-spine structures, and demonstrate applications in controllable 3D generation, deformation-based data augmentation for robot learning, interactive mesh editing, and agentic generation. Experiments demonstrate the effectiveness, efficiency, and versatility of the proposed framework.
Authors: Shayan Jalilian, Abdul Bais
Abstract: Promptable foundation models such as the Segment Anything Model (SAM) produce high-quality masks but remain semantically blind, relying on external prompts to specify categories. Existing vision-language approaches address this limitation by using external prompt coupling, where a vision-language model generates spatial prompts for SAM as a separate stage. We propose CLIP-Guided SAM, a parameter-efficient segmentation framework built on internal semantic conditioning. Instead of using semantic signals only to generate prompts, we inject CLIP-derived text, vision, and similarity features directly into SAM's image encoder through lightweight multi-modal semantic adapters. These adapters condition SAM's internal feature representations, allowing semantic information to influence mask prediction while preserving SAM's original promptable interface. Our framework is designed for low labeled-data settings and applies to both general-domain benchmarks and specialized downstream tasks. It supports two operating modes: Manual mode, for interactive segmentation with both text and spatial prompts, and Semi-Automatic text-only mode, for applications that require concept-specific segmentation using only textual input. We show that robustness depends on aligning training with the type of prompts used at inference, making train-test prompt consistency an important design principle. Through extensive experiments and ablations, we evaluate our method against SAM+PEFT baselines without semantic conditioning, vision-language + SAM pipelines, SAM 3, and strong semi-supervised segmentation methods that rely on large amounts of unlabeled data. Across these settings, CLIP-Guided SAM consistently achieves superior or competitive performance while remaining parameter-efficient in both training and deployment.
Authors: Jian Lang, Rongpei Hong, Ting Zhong, Fan Zhou
Abstract: Deploying multimodal systems in real-world environments often entails handling modality-missing scenarios, where one or more modalities are unavailable. While recent studies address this challenge for the general Multimodal Transformer (MT) architecture via prompt tuning, we identify a fundamental limitation in these methods: the Implicit Modality-Reduction bottleneck. By conditioning prompts solely on the observed modalities, they inadvertently restrict the reasoning scope of MTs to the modality-reduced subspace, cutting off access to the latent information sources of the missing modalities. To overcome this limitation, we propose AOEPT, which pioneers a novel modal-contextualized prompting fashion. Specifically, we introduce lightweight Modal-Contextualized Prompts (MCPs) that distill global modality-wise priors from training data, serving as latent repositories of the information sources for missing modalities. Conditioned on the remaining modalities, these MCPs are instantiated into instance-aware prompts that selectively augment missing-modality information for each sample, thereby restoring the reasoning scope of MTs beyond the observed-modality-only subspace. Experiments across various multimodal benchmarks and backbones confirm the strong performance of AOEPT, with minimal computational overhead.
Authors: Chidera G. Oguine, Kanyifeechukwu J. Oguine, Obiozor M. Oguine, Ozioma C. Oguine
Abstract: Non-Maximum Suppression (NMS) remains a key post-processing step in many real-time object detection pipelines, but it can introduce latency variation and deployment complexity in resource-constrained settings. Recent NMS-free designs such as YOLO26 aim to reduce this dependence through end-to-end detection, yet their performance relative to established NMS-based models such as YOLOv8 remains underexplored beyond standard benchmarks. This paper compares YOLOv8 and YOLO26 on Pascal VOC and VisDrone, representing general object detection and dense aerial small-object detection, respectively. Both model families are evaluated across five scales using accuracy, localization, model size, GFLOPs, and CPU/GPU latency. Results show that YOLO26 achieves stronger detection performance and lower model complexity on Pascal VOC across most scales, while the performance gap narrows on VisDrone, where both models struggle with dense small targets. YOLOv8 remains competitive in GPU latency, showing that NMS-free design does not guarantee universal deployment superiority. Overall, the study shows that detector selection depends on dataset characteristics, object scale, model capacity, and hardware constraints.
Authors: Ligong Bi, Tao Huang, Jianyuan Guo, Chang Xu
Abstract: Visual Autoregressive (VAR) models have emerged as a powerful paradigm for image synthesis by performing hierarchical next-scale prediction. However, VAR models are inherently prone to cascading error propagation, where subtle coarse-scale mispredictions are amplified across the hierarchy, ultimately distorting the final synthesis. To mitigate this, we propose AID-VAR, a plug-and-play framework that enhances pre-trained VARs through Adversarially Injected Diagnosis. Instead of a standard passive generation, AID-VAR introduces a proactive error-correction mechanism inspired by the adversarial feedback in GANs. We deploy a discriminator to diagnose fidelity gaps at each scale transition, coupled with a lightweight guidance injector. This module operates as a non-invasive adapter that refines the feature manifold of a frozen VAR backbone, effectively steering the generation toward the distribution of real images without destabilizing the pre-trained latent space. Furthermore, to rigorously evaluate this cross-scale progression, we introduce the Inter-Scale Consistency Score (ISCS), a novel metric that quantifies the fidelity and structural alignment between consecutive resolution scales. Experimental results across various backbones demonstrate that AID-VAR delivers sharper textural details and fewer structural distortions with negligible overhead. For instance, AID-VAR-d20 achieves a 16% improvement in FID with only a 3% increase in parameters. These results establish AID-VAR as a highly efficient and scalable pathway for upgrading large-scale VAR generators, enhancing global coherence and local detail without altering training data, base architectures, or sampling schedules. Code is available at https://github.com/bijiw515/AID-VAR.
Authors: Mingyu Liang, Dingkun Xu, Jingwei Xu
Abstract: Diffusion Transformers require repeated denoiser evaluations during iterative sampling, making inference computationally expensive. Cache-based acceleration reduces this cost by reusing intermediate representations across denoising steps, but can introduce representation deviations and degrade generation quality. In this paper, we analyze these deviations and show that effective calibration should consider both the direct mismatch caused by reuse and the subsequent trajectory shift induced by earlier corrections. To address this challenge, we propose Trajectory-Consistent Calibration (TCC), a training-free method that calibrates cached representations toward their full-computation counterparts. Specifically, rather than estimating all calibration priors from a single uncorrected cache trajectory, TCC uses an offline iterative procedure so that each prior accounts for the trajectory shift induced by preceding calibrations. Experiments on PixArt-alpha and DiT-XL/2 show that TCC consistently improves FID across representative cache-based acceleration methods while preserving their underlying reuse policies. Notably, in a representative PixArt-alpha cache-acceleration setting based on FORA, TCC reduces FID from 29.83 to 27.35, slightly surpassing the full-computation baseline.
Authors: Xuan Wang, Yinan Wu, Haoran Duan, Jungong Han
Abstract: Vision-Language-Action (VLA) models commonly adapt pretrained Vision-Language Models (VLMs) to robot control by mapping visual observations and language instructions to continuous actions. Existing approaches typically take an action-insufficiency view, assuming that pretrained VLM latents either lack directly usable action information or should be shielded from action-learning signals. Against this view, our \textit{Quotient Theory for VLA} shows that pretrained VLM latents are not action-insufficient but action-sufficient: they already contain the information needed for control, yet remain overcomplete by distinguishing prompt-level variations that induce the same optimal action behavior. To operationalize this theory, we propose QuoVLA, a quotient-space framework for VLA that compresses pretrained VLM latents into action-sufficient representations. Specifically, QuoVLA instantiates this principle with a quantization module and a dual-branch design with relative temporal-complexity regularization, preserving action-relevant information while removing prompt-level redundancy. Extensive experiments across multiple benchmarks demonstrate that QuoVLA achieves strong performance, with particularly notable improvements in generalization under visual, linguistic, and environmental distribution shifts. Our code will be made publicly available.
Authors: Baolu Li (Victor), Jingyu Qian (Victor), Rui Guo (Victor), Yilun Chen (Victor), Hanpeng Liu (Victor), Yuan Lin (Victor), Junhong Zhou (Victor), Ruixin Liu (Victor), Willow Yang (Victor), Yutong Zheng (Victor), Zhenli Zhang (Victor), Tenglong (Victor), Gu, Zhuangzhuang Ding, Pengkun Zheng, Yu Zhang, Xianming Liu
Abstract: Physical world knowledge resides mainly in videos. Equipping Vision-Language-Action (VLA) models with such knowledge is fundamental for safe and generalizable planning. Predictive world modeling enables VLA to internalize physical dynamics and long-term causality by predicting future video from past observations. However, naive next-frame prediction faces two challenges: 1) unlike semantically distinct text tokens, video tokens are low-entropy and redundant, causing prediction to degenerate into trivial extrapolation. 2) world modeling poses a temporal dilemma: dense prediction captures instantaneous dynamics, but cannot efficiently model long-horizon causality. To learn world knowledge effectively, we introduce X-Foresight, a predictive world model integrated directly into the VLA architecture to jointly learn world modeling and real-time action control. At its core lies a long-horizon chunk-wise auto-regressive strategy that addresses both challenges: by predicting semantically distant chunks rather than adjacent frames, it escapes trivial extrapolation, while preserving dense intra-chunk frames for instantaneous dynamics and sparse inter-chunk transitions for long-term causality. A curriculum learning schedule progressively extends prediction horizons and stabilizes long-horizon training. To capture long-term causality effectively, we present temporal importance sampling, which concentrates supervision on safety-critical chunks identified by ego-motion and behavioral signals. We further delegate photorealistic synthesis to a diffusion-based multi-view renderer, improving photorealistic appearance. Comprehensive experiments demonstrate that X-Foresight significantly outperforms VLA baselines in planning performance while maintaining strong generative fidelity, establishing a robust paradigm for world-knowledge-driven autonomous systems.
Authors: Tyler Rust, Dara McNally, Kyle O'Donnell, Colin Kelly, Chandra Kambhamettu
Abstract: Building upon the SAM2 vision foundation model for downstream segmentation, this study introduces Boundary Enhanced Depth (BED)-SAM2. The SAM2 Hiera encoder architecture is modified to directly encode monocular depth information from RGB images, thereby providing geometric cues that enhance object boundary delineation and facilitate the extraction of camouflaged object shapes. BED-SAM2 demonstrates competitive state-of-the-art performance across multiple salient and camouflaged object detection tasks with as few as five training epochs.
Authors: Kyoungkook Kang, Gyujin Sim, Sunghyun Cho
Abstract: As generative models expand the possibilities of visual content creation, layered image synthesis has emerged as a promising direction for controllable and creative editing. However, existing methods struggle to fully realize this potential. Decomposition-based methods often struggle with clean separation, while generation-based methods suffer from difficulty in training data acquisition, reducing quality and scene diversity. In this paper, we propose BFS, a novel generation-based framework for layered image synthesis. Specifically, given a background image and user guidance, BFS synthesizes a foreground layer that incorporates not only a foreground object but also its associated visual effects, such as shadows and reflections, while seamlessly harmonizing with the background to produce a coherent composite. To enable diverse and high-quality foreground layer synthesis while overcoming data scarcity, we leverage the comparatively easy-to-learn knowledge of unlayered image synthesis for the foreground synthesis. To this end, we adopt a dual-branch diffusion framework in which two interconnected branches generate a composite image and a foreground layer, respectively, enabling bidirectional knowledge transfer. Based on this framework, we propose a two-stage training scheme that utilizes a high-quality unlayered composite image dataset to effectively enhance foreground quality. Extensive experiments, including a user study, show that BFS produces high-quality layered images, consistently outperforming prior methods.
Authors: Zijie Cao, Weijie Tu, Yao Xiao, Weijian Deng, Liang Lin, Pengxu Wei
Abstract: Detecting AI-generated images (AIGI) remains challenging because detectors often fail to generalize to unseen generators. Although existing methods are trained on large datasets, their performance still degrades when generation settings change, indicating that data scale alone is insufficient and that limited coverage of generative variations during training is a key factor. Studies on generative model editing show that small changes in internal representations can produce diverse and meaningful image variations, many of which are not explored under standard sampling. Leveraging this insight, we propose PROBE (Probing Robustness via Boundary Exploration), a framework that improves detector generalization by actively exploring challenging regions of the generative process. Instead of treating the generator as a fixed data source, PROBE uses the detector as a critic to steer the generator through manifold-level modifications, producing realistic samples that are difficult to classify. These samples expose failure cases that are uncommon under standard data sampling strategies and are used to refine the detector. Experimental results across multiple benchmarks indicate that PROBE enhances generalization to unseen generators, resulting in more generalizable AIGI detection performance. Code and models are available at https://github.com/Amamiya-C/PROBE-AIGI-Detection
Authors: Hui Lin, Jiayi Li, Jing Wang, Shenghui Rong
Abstract: Sonar imaging is the primary modality for underwater target detection, yet small targets remain difficult to detect due to insufficient pixel coverage, low acoustic contrast, and scale ambiguity across imaging ranges. CNN-based detectors extract local features efficiently but cannot suppress noise-induced false alarms without global acoustic context. Transformer-based methods capture long-range dependencies at quadratic computational cost. Existing Mamba-based vision models offer efficient linear-cost scanning but lack multi-scale semantic alignment across pyramid levels, multi-receptive-field fusion, and small-target-aware training supervision needed for reliable sonar detection. This letter proposes Mamba Dilated-Scale Fusion (MambaDSF), a hybrid framework addressing these limitations through three contributions: a Mamba Enhanced Feature Pyramid (MambaEFP) backbone that jointly captures local echo cues and global acoustic context at linear complexity; a Dilate Fusion Mamba (DFMamba) encoder that enforces multi-scale feature alignment across pyramid levels; and Scale-Adaptive Weighted IoU (SA-WIoU) and Cross-Scale Coherence (CSC) losses that stabilize small-target training. MambaDSF achieves 91.5% mAP50 on the UATD forward-looking sonar benchmark with 28.7 million parameters, surpassing all compared detectors. On a small-target subset the gain reached +2.2 percentage points, and cross-domain evaluation on FLS and MD-FLS confirms the generalization of the proposed architecture. The codes are publicly available at https://github.com/IDontKnowAAA/MambaDSF.
Authors: Yuanye Liu, Siyuan Zhou, Ke Zhang, Lei Li, Wei Chen, Xiahai Zhuang
Abstract: Pre-trained Vision Transformers (ViTs) are increasingly deployed for medical image classification. However, correcting their inevitable failure cases in dynamic clinical scenarios poses a critical challenge. Conventional fine-tuning approaches inherently suffer from catastrophic forgetting, severely degrading previously acquired diagnostic capabilities. Such instability fundamentally compromises clinical safety. Addressing this vulnerability requires an active, controllable, and reliable intervention mechanism that is both theoretically grounded and inherently interpretable. To this end, we propose X-Edit (eXact, eXplicit, and eXplainable Editing), an efficient null-space model editing framework. X-Edit transitions the editing process from iterative gradient-based optimization to a theoretically grounded, closed-form solution. Specifically, we first explicitly localize the influential layers via causal tracing governing the erroneous prediction. Subsequently, we construct an orthogonal null-space projection matrix from a curated anchor set. By geometrically constraining the exact parameter update strictly within this null space, we provide mathematical guarantees that the intervention rectifies targeted errors without perturbing established diagnostic representations. Extensive evaluations on six medical imaging benchmarks demonstrate that X-Edit comprehensively suppresses catastrophic forgetting while achieving superior edit success rates. Our code is available at https://github.com/HenryLau7/X-Edit.
Authors: Alexey Kravets, Da Li, Chuan Li, Da Chen, Vinay P. Namboodiri
Abstract: Recent advances in language model interpretability using sparse autoencoders (SAEs) have yet to effectively translate to the visual domain, mainly due to the difficulty and ambiguity of labeling visual concepts. In this paper, we introduce Visual Interpretability via SAE Transfer Alignment (VISTA), a framework that transfers interpretability from language to vision in a LLaVA-style vision-language model by constraining a visual projector to map visual tokens into an LLM's pre-existing, labeled textual SAE space. This approach enables visual interpretability without training dedicated vision SAEs. By regularizing the projector using the LLM's SAE reconstruction loss, VISTA achieves a threefold increase in the matching rate, which measures how accurately the most activating textual concepts in the SAE space correspond to semantic elements in the image. Using this framework, we further analyze spatial localization properties of different vision encoders and show that DINOv2 features have stronger localization abilities than other encoders. Leveraging this precision, we validate VISTA's cross-modal alignment through fine-grained, localized concept interventions, where specific objects are removed or replaced in the model's perception while preserving the surrounding scene. This results in improvements of 35% in object removal and 47% in object replacement tasks over vision-only baselines, providing causal evidence that visual tokens inhabit the text SAE manifold. These contributions are validated across multiple LLM architectures.
Authors: Qihong Zhao, Shaokang Yan, Zhimin Qiao, Jinjia Wang, Bo Xiong
Abstract: Light-field microscopy (LFM) enables single-shot capture of multi-angular information from biological samples, supporting real-time volumetric imaging. However, traditional physics-based algorithms often suffer from limited spatial resolution, severe artifacts, and high computational costs. Existing learning-based methods improve inference efficiency but still face limitations in reconstruction accuracy and generalization capability. To address these challenges, this paper proposes a high-fidelity Three-Step Conditional Diffusion (TCD) 3D reconstruction method for LFM. Although conventional diffusion models have achieved remarkable success in generative modeling, their slow sampling process and the inherent trade-off between quality and efficiency hinder their application in real-time 3D imaging. We redesign the diffusion process through a deterministic three-step sampling strategy coupled with a lightweight conditional U-Net, establishing a new paradigm for fast and accurate volumetric reconstruction. Furthermore, an Inter-Class Detection (ICD) module is incorporated to identify out-of-distribution or anomalous inputs during inference, thereby enhancing model stability and reliability. Extensive experiments and cross-dataset evaluations demonstrate that TCD significantly outperforms state-of-the-art methods in both reconstruction fidelity and generalization, providing an efficient and practical 3D reconstruction solution for light-field microscopy.
Authors: Manjin Kim, Suha Kwak, Minsu Cho
Abstract: Despite remarkable advances in video generative models, they still struggle to generate physically realistic videos, frequently exhibiting appearance drift, implausible motion, and temporal inconsistencies. In this work, we address this limitation by transferring relational knowledge encoded in spatio-temporal self-similarity (STSS) from visual foundation models into video generative models. STSS represents pairwise similarities among features across space and time, revealing the relational structure of how objects interact with other entities throughout a video, effectively capturing real-world dynamics, including object motion and semantic transformations. To transfer this relational knowledge, we propose Tempered Self-similarity Alignment (TSA) loss, which transforms STSS into probabilistic correspondence distributions and trains the video generative model to align its correspondence distributions with those of the visual foundation model on dynamically changing regions. Evaluated on VideoPhy and VideoPhy2 benchmarks, our method demonstrates substantial improvements in physical plausibility across diverse interaction scenarios, validating the effectiveness of transferring relational knowledge for physically realistic video generation.
Authors: Jiaxiang Li, Zongtan Zhou, Zhen Tan, Yadong Liu, Dewen Hu
Abstract: Reconstructing high-quality 3D scenes from low-resolution multi-view images remains challenging for 3D Gaussian Splatting (3DGS), because insufficient high-frequency observations often lead to blurred textures, weak boundaries, and view-inconsistent details. Existing approaches either apply super-resolution guidance uniformly or localize enhancement regions based mainly on geometric sampling. However, they typically do not distinguish between two fundamentally different questions: where additional detail is needed, and whether the corresponding candidate high-frequency content is reliable enough to be internalized into a multi-view consistent 3D representation. In this paper, we propose a reliability-aware frequency modeling framework for low-resolution 3DGS reconstruction. The framework first estimates a geometry-guided detail-demand prior to locate regions that are likely under-detailed under low-resolution supervision. It then computes a frequency-aware reliability map to determine whether candidate high-frequency details are structurally supported, spectrally unresolved, and cross-view stable. Combining these signals yields a detail-injection map that guides where super-resolved details should be introduced during optimization. Based on this map, we design a unified optimization scheme comprising spatially selective supervision, coarse-to-fine frequency regularization, and reliability-aware Gaussian densification. This scheme controls where reliable details are injected, when high-frequency supervision is activated, and how unresolved yet reliable details are internalized into the Gaussian representation. Experiments on multiple benchmarks show improved fidelity and perceptual quality while suppressing unstable or view-inconsistent details.
Authors: Ibrahim Delibasoglu
Abstract: The rapid evolution of generative models has enabled the creation of hyper-realistic facial deepfakes, exposing a critical vulnerability in modern digital forensics: the inability of detectors to generalize to unseen manipulation techniques. Traditional networks suffer from representation collapse, overfitting to localized artifact fingerprints of specific training generators. This work investigates whether modern Vision Foundation Models can serve as generalizable, out-of-the-box feature extractors capable of tracking forensic anomalies across entirely unseen generative manifolds. We conduct a systematic cross-domain evaluation comparing three foundational learning paradigms: fully supervised macro-semantic features (RoPE-ViT), pure self-supervised geometric features (DINOv3), and multi-teacher agglomerative representations (NVIDIA C-RADIOv4-H). By deploying frozen backbones subjected to downstream linear probing, we map the performance limitations of these architectures on the challenging DF40 benchmark. Our empirical findings expose the intrinsic trade-offs between pre-training paradigms and parameter scale, proving that while foundation models retain high discriminative capabilities for entire face synthesis, localized face editing techniques expose fundamental boundaries in linear probe evaluation structures. Source code and model weights are available in http://github.com/mribrahim/deepfake
Authors: Bangrui Xu, Ziyang Miao, Xuanhe Zhou, Yiming Lin, Zirui Tang, Xiaomeng Zhao, Fan Wu, Cheng Tan, Fan Wu, Bin Wang, Conghui He
Abstract: VLM-based OCR models have become the de facto choice for document parsing, as they can accurately extract page-level elements (e.g., paragraphs within individual pages) together with their bounding boxes and textual content. However, downstream applications such as RAG require coherent document-level information, whereas these models often break cross-page continuity and fail to recover disrupted structures, such as paragraphs and tables truncated by page boundaries. Such relationships are not confined to a single page; instead, they require joint analysis of titles, paragraphs, tables, and images spanning multiple pages. A natural solution is therefore to reuse existing OCR outputs and reconstruct document-level logical structures through post-processing. To this end, we propose MinerU-Popo, a lightweight and universal framework for POst-Processing OCR outputs, which converts page-level results from diverse parsers into coherent document-level structures. MinerU-Popo decomposes the problem into four focused subtasks: text truncation recovery, table truncation recovery, title hierarchy reconstruction, and image-text association. To address these effectively, we build a task-oriented data engine with task-specific input filtering, and use the generated data (30K) to fine-tune a lightweight post-processing model (Qwen3-VL-4B). To support long documents, we introduce dynamic chunking with overlap-based synchronization, which aligns chunk-level outputs from the fine-tuned model and preserves global consistency. Finally, we assemble the aligned outputs into a tree-structured document representation, further enriched with node chunking and summaries for downstream retrieval and analysis. Empirical results show MinerU-Popo improves title-hierarchy TEDS by at least 20% across all five tested OCR models, improves RAG accuracy and reduces per-query latency.
Authors: Farhad Nooralahzadeh, Benjamin Gundersen, Nicolas Deperrois, Hidetoshi Matsuom, Mizuho Nishio, Thomas Frauenfelder, Ahmed Allam, Christian Bl\"uthgen, Michael Moor, Michael Krauthammer
Abstract: Medical vision-language models (VLMs) often hallucinate findings when generating chest X-ray reports: they fabricate findings that are not present in the image, miss important ones, or locate them incorrectly. We mitigate this without weight updates by decoding-time residual steering on a per-token sparse autoencoder (SAE) basis: Top-$K$ SAEs on late layers, causal steering against clinical errors, then combined suppress/boost intervention at inference time. On the MIMIC-CXR test split, our inference-only method improves the quality of generated reports for three radiology VLMs (RadVLM, LLaVA-Rad, and CheXOne), with relative improvements of +5.4%, +7.2%, and +17.0% in the clinical composite metric, and statistically significant GREEN gains on all backbones. A cross-model feature alignment shows that the quality-promoting (boost) directions overlap strongly across architectures, whereas hallucination-linked (suppress) directions are model-specific. Therefore, transferable steering must treat suppression per-backbone, rather than sharing a universal suppress list. The same recipe transfers zero-shot to IU-Xray (Green $+7.7\%$ rel.) without retraining, confirming that the identified features are properties of the model, not of the training corpus. We release causal feature sets and an interactive feature dashboard: https://cxr-sparse-feature-dashboard.netlify.app/.
Authors: Huangsen Cao, Hongkang Chu, Yuxi Li, Ying Zhang, Chen Li, Jing Lyu, Yongwei Wang, Yu Zhao, Fei Wu
Abstract: The rapid advancement of generative models has made synthetic images increasingly realistic, challenging reliable detection. Existing methods are often limited to end-to-end classification or monolithic reasoning, and thus fail to model structured forensic reasoning and heterogeneous visual evidence. We revisit synthetic image detection from a cognitive perspective and propose a \textit{Heuristic-to-Reasoning} cognitive skill learning framework for evidence-based forensic analysis. Given an input image, our framework first extracts heuristic perceptual clues, selects the optimal forensic skill, and then performs skill-conditioned reasoning for evidence extraction and decision making. To support this paradigm, we introduce \textbf{ClueAegis-Bench}, which decomposes synthetic image detection into explicitly annotated forensic cognitive skills for structured evaluation beyond binary classification. Based on this benchmark, we propose \textbf{ClueAegis} (\underline{C}ognitive-skill \underline{L}earning for \underline{U}nified \underline{E}vidence-based Synthetic Image Detection), a two-stage agentic framework that conducts heuristic skill selection followed by evidence-guided reasoning through skill-conditioned toolchains. This design reformulates synthetic image detection as a configurable multi-skill reasoning process that bridges perception, skill selection, and forensic reasoning. Extensive experiments show that ClueAegis achieves state-of-the-art performance while improving cross-domain generalization and robustness. It also provides transparent reasoning trajectories and structured forensic evidence, offering a more explainable alternative to conventional end-to-end detectors.
Authors: Imanol G. Estepa, Jes\'us M Rodr\'iguez-de-Vera, Bhalaji Nagarajan, Petia Radeva
Abstract: Discriminative and generative vision models excel in their respective domains but remain semantically misaligned, hindering progress toward unified visual learning. We introduce LEASE (LEArning from SEmantic Dictionaries), a self-supervised framework that bridges this gap using a paired generative-discriminative codebook design. LEASE operates entirely in a discrete token space produced through a one-time precomputation step, enabling efficient training without data augmentations, teacher models, or online tokenizers. LEASE integrates two complementary objectives: a masked token reconstruction loss that captures fine-grained generative detail, and a codebook contrast loss that aligns encoder features with discriminative semantics via adaptive centroid weighting. This dual supervision yields a unified latent space that supports both high-quality generation and strong representation learning. On ImageNet-1K, LEASE achieves state-of-the-art unified performance, outperforming prior VQGAN-based methods such as MAGE and Sorcen across linear probing (up to +1.7%), unconditional generation (-1.26 FID and +10.19 IS w.r.t MAGE), few-shot learning (+0.56% on average against Sorcen), transfer (+0.75% average improvement against MAGE and Sorcen), and robustness benchmarks (+5.86% and +4.25% average improvement against MAGE and Sorcen, respectively). It also competes favorably with domain-specialized contrastive and generative models while surpassing previous MIM methods. The unsupervised LEASE model can also be extended to conditional generation by building upon its learned representations, proving competitive with specialized baselines. Overall, LEASE provides an efficient and effective step toward general-purpose vision models that jointly understand and generate visual content.
Authors: Sasidhar Parvathireddy, Vamsidhar Saraswathula, Rama Krishna Gorthi
Abstract: In recent times, diffusion models have achieved remarkable performance in image restoration tasks. Their core mechanism relies on the restricted presumption of degradation prior to the additive noise operation. However, the blur model, one of the most widely studied degradation formulations, violates this assumption, as it is inherently based on convolution rather than addition. In this paper, we introduce ConvDiff, a novel diffusion based framework that substitutes the additive operation with convolution for the task of image deblurring. In the forward process, we construct a meaningful trajectory from the clean image to its blurred counterpart by exploiting the frequency domain characteristics of convolution, rather than progressively corrupting the image with additive noise. While the current work instantiates this framework for Gaussian blur, where frequency-domain decomposition yields closed-form and physically valid intermediate states, the underlying principle of constructing degradation trajectories from the blur operator extends naturally to other blur families. This formulation bridges the gap between the mathematical principles of blurring and the iterative design of diffusion-based restoration algorithms, enabling more physically grounded and effective image restoration models.
Authors: Wenjie Zheng, Haoji Hu, Jiali Lu, Xingze Zou, Jing Wang
Abstract: Dataset distillation (DD) aims to compress large-scale datasets into compact synthetic sets while preserving training efficacy. However, existing studies mainly focus on image classification, leaving dense prediction tasks such as semantic segmentation largely underexplored. In this work, we identify three key challenges for segmentation DD: (i) long-tailed class imbalance, (ii) the need for strict pixel-wise alignment between images and dense labels, and (iii) the high computational cost of optimizing high-resolution data with complex models. To address these challenges, we propose D3S2, a Diffusion-guided Dataset Distillation framework for Semantic Segmentation. Our method adopts a two-stage design. In Class-Balanced Mask Selection, we construct a representative mask set via a greedy strategy that prioritizes underrepresented classes. In Diffusion-Guided Image Synthesis, we employ a pretrained layout-to-image diffusion model to generate images conditioned on the selected masks, naturally ensuring spatial alignment. To further enhance the training utility of synthesized data, we introduce guided diffusion sampling with two complementary objectives: a segmentation-consistency loss for pixel-level alignment, and a class-wise feature matching loss for aligning per-class feature statistics across layers. Extensive experiments demonstrate the superiority of D3S2. Notably, at an extremely compression rate of 1%, our method achieves 24.99% and 35.49% mIoU on ADE20K and COCO-Stuff with Mask2Former (Swin-S), outperforming random selection by 9.34% and 5.70%, respectively.
Authors: Tianyu Liu, Heyu Ma, Aiduo Wang, Peiwen Li, Boyi Li, Ying Li, Dan Li, Chengcheng Liu, Dean Ta
Abstract: Ultrasound computed tomography (UCT) via full waveform inversion (FWI) enables high-resolution quantitative imaging for tissue characterization and disease diagnosis. However, UCT suffers from large computational burden and severe convergence issues due to highly nonlinear optimization. Deep learning can accelerate UCT reconstruction, but supervised training requires large-scale labeled datasets difficult to obtain in vivo. To address these limitations, we propose SDA-UCT, a two-stage self-supervised domain-adaptive framework for rapid and accurate UCT imaging of musculoskeletal tissues. SDA-UCT employs an attention-enhanced network (AttUCT) pre-trained on simulation datasets and transfers to in-vivo data via physics-informed self-supervised learning, effectively bridging the simulation-to-real domain gap. A Low-Rank Adaptation (LoRA) mechanism is integrated to enable efficient adaptation across diverse clinical scenarios. Results showed that AttUCT achieved high-quality SOS reconstruction for simulated human forearm with a PSNR of 29.23 dB and SSIM of 0.928, outperforming conventional FWI and existing deep learning methods. Validated on in-vivo data, SDA-UCT successfully reconstructed SOS images revealing complex anatomical structures (skin, fat, muscle, tendon, bone and bone marrow) for human forearm, in high concordance with MRI references. The LoRA mechanism adjusting only 3% of parameters achieved comparable performance to full fine-tuning. The rapid reconstruction (5 ms per frame) enables real-time 3D visualization, achieving five-orders-of-magnitude improvement over traditional FWI. This work represents the first self-supervised domain-adaptive deep learning for rapid, high-resolution in-vivo UCT imaging, showing potential for musculoskeletal disease diagnosis.
Authors: Zhifeng Wang, Jason Jingshi Li, Kaihao Zhang, Ramesh Sankaranarayana
Abstract: Large language models (LLMs) demonstrate strong performance in natural language processing but often generate factual errors when relying solely on parametric knowledge. Retrieval-Augmented Generation (RAG) mitigates these errors by grounding responses in external evidence, yet conventional retrieve-and-dump approaches frequently introduce irrelevant context that degrades answer quality. In this work, we present AstroRAG -- a PageRank-based retrieval-augmented generation (RAG) pipeline adapted for question answering in astronomy. The system performs token-aware chunking and per-instance, ephemeral indexing in Elasticsearch, then executes a two-stage retrieval: (i) Maximal Marginal Relevance (MMR) to obtain a small, diverse candidate set and (ii) a reader-driven PageRank (PR) re-ranking on a similarity graph to identify a compact, mutually supportive context under a strict token budget. Our design is training-free, privacy-preserving, and reproducible, as each instance is processed through transient indexing to prevent cross-task leakage. We evaluate the pipeline on the AstroQA benchmark for astronomy QA, and demonstrate competitive performance across all difficulty levels. In particular, the RAG-enhanced Mistral-7B achieves \textbf{79.49\% accuracy} and \textbf{79.49\% F1-score}, nearly doubling the performance of its non-RAG counterpart. These results highlight the effectiveness of disciplined retrieval and refinement in boosting domain-specific reasoning, establishing a robust foundation for extending RAG to other scientific fields.
Authors: Weimin Bai, Yuxuan Gu, Yifei Wang, Weijian Luo, He Sun
Abstract: Existing score-based methods for inverse problems often resort to approximate minimization of the KL divergence between the inversion distribution and the Bayesian posterior. Such an approximation leads to severe mode collapse and unreliable uncertainty quantification. In this paper, we propose Principled Posterior Matching (PPM), a framework that returns to the fundamentals of variational inference, rather than using tricky approximations. Instead of relying on heuristic approximations, we rigorously formulate the exact optimization of the KL divergence via the integration of Fisher divergence. We derive a tractable, equivalent gradient form of this integral, enabling precise optimization without the biases introduced by prior approximations. Our analysis clearly reveals that the mode collapse in previous methods stems directly from this approximation gap. Supported by our theoretical solution, PPM unifies two complementary paradigms: (1) In variational inference, PPM adopts mass-covering divergences that significantly improve the inversion diversity and uncertainty quantification; (2) In amortized inference, it enables the training of an efficient reconstruction network for rapid, single-step reconstruction. Furthermore, our formulation naturally extends to a broader family of divergence measures by generalizing the integral of the Fisher divergence. We validate PPM across challenging computational imaging tasks, including inpainting, super-resolution fluorescent microscopy, and radio interferometric black-hole imaging. In all experiments, PPM achieves superior reconstruction fidelity, faithful multimodal posterior recovery, and well-calibrated uncertainty estimates, establishing a robust framework for scientific imaging.
Authors: Jun-Wei Hsieh, Meng-Yu Kao, Ghufron Wahyu Kurniawan, Kuan-Chuan Peng
Abstract: YOLO-series and DETR-based detectors struggle with tiny-object detection. YOLO-style models benefit from efficient dense prediction, but their large-stride backbones may suppress tiny instances in deep feature maps and make grid assignment ambiguous. DETR-based models remove hand-crafted post-processing through set prediction, yet they reason over coarse token grids, where tiny objects occupy only a few weak tokens and are easily overlooked during matching. To address these limitations, we propose TinyFormer, a unified YOLO--DETR hybrid real-time detector that combines ViT representations, NMS-free set prediction, and a YOLO-style pyramid neck for accurate small-object detection. TinyFormer introduces a Parallel Bi-fusion Module (PBM), which builds high-resolution shortcuts from shallow stages to the feature pyramid, preserving fine spatial details during multi-scale fusion. We further design a Spatial Semantic Adapter (SSA) to compensate for the spatial loss caused by coarse tokenization. SSA extracts high-resolution cues from early stages and injects them into transformer token embeddings, improving tiny-object localization without sacrificing the global modeling ability of DETR. Experiments on MS COCO show that TinyFormer consistently outperforms recent YOLO-series detectors and the strong DEIMv2 baseline. TinyFormer-X achieves 58.4% AP even without PBM, while adding PBM improves the overall AP to 58.5% and brings a 1.6% AP gain on small objects. With Objects365 pre-training, TinyFormer-X-PBM reaches 60.2% AP, surpassing RF-DETR and other Objects365-pretrained detectors with fewer parameters and lower computation. These results demonstrate that TinyFormer bridges dense YOLO-style feature fusion and DETR-style set prediction, providing a strong accuracy-efficiency trade-off for real-time tiny-object detection. Code is available at https://github.com/mmpmmpmmpjosh/TinyFormer.
Authors: Ruoyu Wang, Yong Liu, Sheng Tao, Yuhang Lin, Yukai Ma
Abstract: Crucial for autonomous exploration, online 3D occupancy prediction and mapping incrementally constructs dense spatial representations on the fly. However, recent Gaussian-centric methods struggle with structural boundary fidelity and rely heavily on predefined scene-size priors, fundamentally limiting their operational efficiency. In this work, we present VEOcc, a voxel-centric framework formulated as a recursive perception-and-assimilation paradigm. By eliminating the need for initial scale estimation, VEOcc enables highly streamlined, open-ended map expansion. Furthermore, to robustly aggregate noisy temporal observations within the discrete voxel space, we propose a Spatio-Temporal-Aware Online Update Strategy. It integrates Cross-Temporal Logit Aggregation (TLA) for temporal consistency, Reliability-Aware Confidence Modulation (RCM) for spatial uncertainty calibration, and Confidence-Driven Incremental State Update (CSU) for robust global state assimilation. % Extensive experiments on Occ-ScanNet and EmbodiedOcc-ScanNet demonstrate that VEOcc establishes new state-of-the-art performance in both local and embodied settings, providing an accurate and efficient solution for real-world exploration. Extensive experiments on Occ-ScanNet and EmbodiedOcc-ScanNet demonstrate that VEOcc establishes new state-of-the-art performance in both local and embodied settings. Notably, zero-shot evaluations on self-collected video sequences further confirm its robust out-of-distribution generalization capability in completely unseen real-world environments. Ultimately, our framework provides an accurate and highly efficient solution for autonomous exploration. Code and supplementary visualizations are available on our project page: https://wryzju.github.io/VEOcc/.
Authors: Bohai Gu, Taiyi Wu, Yueyang Yuan, Jian Liu, Xiaocheng Lu, Dazhao Du, Jie Zhang, Jinxiang Lai, Shuai Yang, Xiaotong Zhao, Alan Zhao, Song Guo
Abstract: Recent video-based world models have made pixel-space environments interactive at the camera level: users can navigate viewpoints while the model generates coherent visual continuations. Yet their action spaces remain incomplete: users can move the camera, but cannot act on individual objects. Since real-world interaction is inherently object-centric, such models remain closer to passive scene observers than truly manipulable environments. We present WorldCraft, a framework that expands interactive video world models from camera navigation to object-level trajectory actions. Given a user click and a sketched path, WorldCraft generates future frames in which the selected object follows the prescribed trajectory while the camera continues to navigate the scene. WorldCraft achieves this through a trajectory-centric control pipeline: First, Normalized World Trajectory (NWT) represents user-drawn motion in a camera-invariant world coordinate system and dynamically re-projects it under the current camera pose, separating object motion from camera-induced screen-space displacement; Spatial-Pathway LoRA (SP-LoRA) then injects this world-space signal through the model's spatial-control pathway, adding object manipulation capability while preserving the pretrained camera controller; finally, Trajectory-Anchored State Persistence (TASP) treats the world trajectory as a persistent spatial state and refreshes autoregressive memory after trajectory-conditioned generation, allowing moved objects to reappear at their updated positions after leaving the camera view. Experiments show that WorldCraft enables accurate object control, preserves the video-based world model's camera fidelity under camera-only evaluation, and maintains object state across long autoregressive rollouts with off-camera excursions.
Authors: Lei Wang, Syuan-Hao Li, Yongsheng Gao, Piotr Koniusz
Abstract: Aligning structured data is a fundamental problem in computer vision and machine learning, underlying tasks such as time series analysis, human action recognition, and visual representation learning. Existing alignment methods, including Dynamic Time Warping (DTW) and its differentiable variants, rely on deterministic similarity measures and are therefore sensitive to heterogeneous and noisy features. In this work, we introduce uncertainty-aware alignment, a probabilistic framework that models pairwise correspondences with heteroscedastic uncertainty and performs structured matching along alignment paths. Our formulation, uncertainty-DTW (uDTW), assigns each correspondence a Normal distribution and parametrizes each alignment path by a Maximum Likelihood Estimate objective consisting of (i) a precision-weighted matching term that suppresses unreliable features, and (ii) a log-variance regularization that prevents degenerate solutions. This yields a probabilistic alignment mechanism that is robust to noise and interpretable, as uncertainty directly reflects the reliability of matches. We further generalize this framework from temporal sequences to tokenized visual representations, enabling structured matching over sets of visual tokens. The learned uncertainty can be interpreted as a reverse-attention: semantically relevant regions exhibit low uncertainty and dominate the alignment, while ambiguous/noisy regions have high uncertainty. This provides a connection between alignment, attention, and uncertainty modeling. We evaluate the proposed framework across diverse domains. The results demonstrate consistent improvements over state-of-the-art methods and show that learned uncertainty correlates with semantic importance. These findings establish uncertainty-aware alignment as a general, robust, and interpretable framework for learning from structured data.
Authors: Xi Ding, Lei Wang, Syuan-Hao Li, Yongsheng Gao
Abstract: Domain adaptation aims to mitigate performance degradation caused by distribution shifts between a labeled source domain and an unlabeled or sparsely labeled target domain. Most existing approaches estimate domain discrepancy either in feature space or in prediction space. However, these single-perspective strategies overlook a critical problem under domain shift: the reliability of the signals used for alignment. In practice, both learned representations and semantic predictions may become unreliable, and treating all target samples equally can lead to misleading alignment and suboptimal transfer. We introduce trust-aware domain adaptation, a principled framework that models domain discrepancy through the reliability of feature and prediction signals. Central to our approach is the Joint Feature-Prediction Discrepancy (JFPD), a unified formulation that jointly captures representation divergence and prediction divergence while weighting their contributions by sample-specific trust. Trust is quantified via two complementary mechanisms: uncertainty-aware trust, derived from prediction entropy to suppress unreliable predictions, and semantic-alignment trust, computed from prototype similarity in feature space to emphasize well-aligned representations. By prioritizing confident and semantically consistent samples while down-weighting noisy or ambiguous ones, JFPD provides a reliability-aware estimate of domain discrepancy. We further integrate JFPD into a training objective that guides adaptation toward trustworthy regions of the target domain. Experiments on standard benchmarks demonstrate that the proposed framework consistently achieves superior adaptation performance and yields discrepancy estimates that correlate with target-domain error. This work addresses, for the first time, the importance of modeling trust in the interaction between features and predictions for domain adaptation.
Authors: Haoqing Wu, Alexa Nawotki, Jochen Garcke
Abstract: Point clouds are a fundamental 3D representation in computer vision, enabling a wide range of perception tasks. However, real-world point clouds often suffer from degradations such as incompleteness, noise, outliers, and irregular density, caused by sensor limitations or occlusions. Recovering clean and detailed shapes from such degraded data is crucial for downstream applications. While existing learning-based methods achieve progress on individual tasks like completion or denoising, they typically rely on global bottleneck features, which lose fine-grained geometry and remain sensitive to varying input quality. We propose a unified 3D restoration network that directly takes point clouds as input and adaptively reconstructs high-quality geometry under diverse degradation scenarios. At the core of our approach is a Pseudo-Query module, implemented within a Transformer backbone, which reformulates geometric translation into two cooperative stages to enhance structural clarity, robustness, and local detail preservation. Extensive experiments on curated benchmarks demonstrate that our approach surpasses state-of-the-art performance in general 3D restoration. It effectively handles complex combinations of completion, deformation, and denoising degradations. With this work, we provide a novel unified, point-only backbone for robust 3D restoration, enabling more versatile 3D perception.
Authors: Ali Mikaeili Barzili, Behzad Moshiri, Hamid Azadegan, Mohammad-Reza A. Dehaqani
Abstract: Deformable medical image registration aligns anatomical structures across images but remains computationally dense at 3D resolution. Spiking neural networks (SNNs) offer sparse event-driven computation, yet have not been systematically studied for deformable medical image registration. We introduce SpikeReg, a spiking U-Net for 3D brain MRI registration. SpikeReg is initialized from an analog ANN registration teacher, converted by layer-wise weight transfer and activation-percentile threshold calibration, and fine-tuned with a surrogate-gradient objective combining local cross-correlation, diffusion regularization, and spike-rate sparsity. On the OASIS Learn2Reg validation split ($19$ image pairs), SpikeReg reaches Dice $0.7474 \pm 0.032$, with no significant paired Dice difference from the ANN teacher ($0.7480 \pm 0.037$, $p = 0.67$), at a $12.8\%$ mean spike rate and a $55.5\times$ projected arithmetic-energy reduction under an event-sparse SynOps/MAC proxy relative to the dense-ANN baseline. We additionally report two negative findings: displacement distillation from the ANN teacher hurts performance, and ANN teachers trained with a label-Dice loss fail to transfer through rate-code conversion. Together these results show that dense geometric prediction can be performed under sparse event-driven computation, opening a path toward neuromorphic medical image registration.
Authors: Bikram Keshari Parida, Abhijit Sen, Wonsang You
Abstract: A panoramic X-ray compresses a 3D jaw into a 2D strip; we aim to recover the missing depth cleanly and fast. Existing implicit neural representations render realistic volumes but are slow to train, sensitive to sampling and positional encodings, and costly in practice. Pure CNN baselines are efficient yet struggle with the dental arch's long-range geometry, blur fine enamel-dentin boundaries, and offer little interpretability. We present K-U-KAN, a three-stage pipeline that (i) lifts 2D features into depth-aware observables with Kolmogorov-Arnold Networks, (ii) advances these observables by a stable, phase-aware linear evolution via a Koopman token block, and (iii) places the predicted depth bins onto focal-trough rays before a lightweight 3D attention U-KAN refines the volume. This marriage of physics (Beer-Lambert image formation), geometry (horseshoe focal trough), and learned linear dynamics yields sharp anatomy, fewer artifacts, and robust behavior on native radiographic intensities with batch size one. On held-out data, K-U-KAN matches transformer/implicit baselines on signal and structure metrics, clearly improves perceptual quality, and trains in roughly half the time-making single-view PX $\to$ CBCT reconstruction more practical for clinical pipelines.
Authors: Ben Vardi, Dana Schonberger, Yuval Friedmann, Zohar Yakhini, Iris Barshack, Alexander Loebel, Ariel Shamir
Abstract: Pathology foundation models (PFMs) have advanced rapidly in recent years and support training classifiers for a range of histopathology tasks. However, their robustness across hospitals remains limited: performance often degrades when training a classifier on data from one hospital and evaluating it on another target hospital. We address this challenge by fine-tuning PFMs with a local maximum mean discrepancy (LMMD) objective that applies to two settings: domain adaptation, where unlabeled target-hospital data is available, and domain generalization, where target-hospital data is unavailable at all. Experiments at both the patch- and slide-level show consistent improvements across multiple PFMs and tasks.
Authors: Agata \.Zywot, Iason Skylitsis, Thijmen Nijdam, Zoe Tzifa-Kratira, Derck Prinzhorn, Konrad Szewczyk, Aritra Bhowmik
Abstract: Text-to-image diffusion models like Stable Diffusion generate high-quality images from text, but lack a way to inject visual guidance (e.g. sketches, styles) at inference without retraining. Existing methods either require computationally expensive fine-tuning or rely on style transfer techniques that risk semantic misalignment with textual prompts. We introduce Visual Concept Fusion (VCF), the first method offering dual conditioning on both an image and text prompt at inference time without any concept-specific training. VCF enables visual concept injection into Stable Diffusion by aligning CLIP image features with the text embedding space. VCF consists of three components: (1) a lightweight aligner that maps image tokens to the text embedding manifold using InfoNCE and cross-attention reconstruction losses, (2) a fusion strategy that preserves both textual and visual semantics, and (3) an optional Prompt-Noise Optimization (PNO) module for test-time refinement. Our experiments demonstrate that VCF successfully transfers visual attributes including style, composition, and color palette from reference images while maintaining prompt adherence. Quantitative results show a trade-off between text alignment (CLIP score) and visual correspondence (LPIPS), with VCF outperforming baselines in reference fidelity.
Authors: Sen Liang, Cong Wang, Fengbin Guan, Zhentao Yu, Yiting Lu, Yuanzhi Wang, Yuan Zhou, Xin Li, Zhibo Chen
Abstract: Visual and acoustic events in the physical world are inherently coupled, yet existing video editing methods typically adopt decoupled pipelines, lacking bidirectional modality interaction. This results in two key limitations: (i) audio-visual desynchronization and (ii) contextual conflicts between generated audio and preserved content. To address these, we propose SpongeBob, the first end-to-end audio-visual joint editing framework featuring bidirectional cross-modal interaction. For synchronization, a Sync-Aware Mechanism aligns visual edits with sound events via bidirectional attention, temporal alignment, and spatial constraints. For contextual consistency, a Context-Aware Module leverages acoustic and visual context attention to prevent semantic clashes. Additionally, we introduce Sync-Preserving Training and Guidance (SPTG) to enhance alignment without degrading quality. Due to the scarcity of paired data, we construct a scalable data pipeline and a large-scale subject-level dataset. We also propose SpongeBob-Bench for systematic evaluation. Experiments show SpongeBob significantly outperforms existing baselines, improving Sync-C by 30% and Ctx-F1 by 12.5%. Our project page is available at: https://hy-spongebob.github.io/.
Authors: Shuyuan Tu, Qi Tian, Zihan Yang, Yue Wu, Xintong Han, Weijie Kong, Jiangfeng Xiong, Jian-Wei Zhang, Zhao Zhong, Liefeng Bo, Zuxuan Wu, Yu-Gang Jiang
Abstract: Current open-source diffusion models struggle to generate stable and synchronized audio-visual content, particularly in scenarios demanding complex semantic reasoning. The root cause is that existing methods rely on coarse text embeddings from off-the-shelf encoders to guide audio-video denoising, which discards fine-grained semantics and, critically, lacks a shared long-horizon plan, leading to uncoordinated denoising trajectories and fragile cross-modal alignment. We propose Baton, the first framework that introduces explicit semantic planning into joint video-audio generation. Our key insight is that complementing coarse text guidance with semantically rich, modality-aware planned tokens, jointly reasoned and mutually aligned before denoising, can simultaneously restore fine-grained semantic detail and establish a shared blueprint that coordinates both audio and video denoising trajectories. Concretely, Baton first introduces the VA-Planner, a multimodal language model equipped with dual semantic alignment towers, where learnable queries cross-attend to both video and audio features to produce a pair of semantically aligned video and audio planned tokens as keyframe-level blueprints. These planned tokens are injected into the diffusion backbone via cross-attention layers, providing temporally grounded guidance complementary to coarse text embeddings. Since planned tokens do not share one-to-one spatial-temporal correspondence with diffusion latents, we further propose Relative Semantic RoPE, a relative positional encoding that maps planned tokens and latents into a shared spatial-temporal coordinate frame, enabling each latent to accurately attend to its positionally corresponding semantic cues. Experiments on benchmarks show the effectiveness of Baton both qualitatively and quantitatively.
Authors: Aviral Chharia, Fernando De la Torre
Abstract: High-fidelity 3D Gaussian head avatar generation is critical for applications such as AR/VR, telepresence, and digital humans. Existing methods depend on multi-view datasets, 3D captures, or intermediate 2D view synthesis. In contrast, we learn both conditional and unconditional 3D head models from randomly sampled 2D images alone, without using multi-view data, 3D supervision, or intermediate view generation. We introduce MVCHead, a single-shot state space model that enforces multi-view consistency (MVC) directly in the 3D representation while regressing 3D Gaussians under these constraints. At its core, we propose a Hierarchical State Space (HiSS) block that progressively refines Gaussians from coarse to fine, while capturing long-range dependencies. Within each HiSS block, we modify Mamba's standard unidirectional scan with the proposed Hierarchical Bi-directional State Scan (HiBiSS) that aligns recurrence with the axes along which multi-view inconsistencies are strongest. Finally, we design an SE(3) Multi-view Critic that judges whether a set of self-renders arises from a single underlying 3D configuration, rewarding cross-view pixel alignment without observing real multi-view pairs. MVCHead achieves state-of-the-art perceptual quality, surpasses prior methods in both texture and geometric consistency, and maintains comparable shape consistency. To demonstrate scalability, we release FaceGS-10K, the first large-scale dataset of ready-to-use 3D Gaussian head assets for training and evaluation of 3D head models. Project Page and code: https://humansensinglab.github.io/MVCHead/
Authors: Jasin Cekinmez, Ryo Mitsuhashi, Addison J. Wu, Yida Yin
Abstract: With unified model-generated images now widespread online, attributing their model of origin offers a path toward transparency and deeper insight into the characteristic behaviors of individual models. Prior work has explored provenance in LLM-generated text, diffusion model images, and datasets, but the separability of unified model-generated images remains an underexplored area. We address this gap by examining separability across corruption, domains, and prompt languages using images generated by seven unified models. We show that model attribution is highly feasible as our model achieves near-perfect accuracy with around 20K images per model. Corruptions and structural perturbations have only a modest effect on attribution performance, and cross-domain generalization reveals that semantic content contributes to separability but is not the dominant signal. Finally, we observe that for most models, prompt language attribution is around chance levels, suggesting minimal language-specific visual signatures. These findings highlight consistent model-specific visual characteristics in unified models outputs and open new directions for tracing and auditing generative image pipelines.
Authors: Prabuddhi Wariyapperuma, Rajitha de Silva, Marc Hanheide, Thomas Bohn\'e, Leonardo Guevara
Abstract: Accurate 3D bird's-eye view (BEV) object detection is essential for autonomous driving, and depends strongly on effective multimodal representations from complementary sensors such as cameras and LiDAR. Multimodal masked autoencoders have shown strong potential for learning such representations for downstream 3D BEV object detection. However, existing methods typically apply uniform random masking to camera and LiDAR inputs, treating all regions equally, and learn representations only through masked reconstruction. We propose a semantics-guided multimodal masked autoencoder framework that introduces semantic information during pretraining through two separate components: (i) semantics-guided LiDAR voxel masking, which preserves semantically important LiDAR regions more strongly, and (ii) an auxiliary point-wise LiDAR semantic decoder branch that injects semantic guidance in addition to reconstruction. On BEVFusion 3D object detection, our semantics-guided pretraining strategy improves performance on the nuScenes mini validation set compared to the standard UniM2AE baseline: semantics-guided LiDAR voxel masking yields +1.49% mean Average Precision (mAP) and +1.66% nuScenes Detection Score (NDS), while decoder-side point semantic supervision yields +1.39% mAP and +3.22% NDS over the baseline.
Authors: Debabrata Mandal, Zhihan Peng, Yujie Wang, Praneeth Chakravarthula
Abstract: Incorporating camera intrinsics into video generation models offers a principled way to control not only scene dynamics but also the imaging process that governs visual appearance. Prior work has primarily focused on extrinsic control, such as camera pose and motion, while treating intrinsic camera parameters as implicit or fixed. A key bottleneck is the lack of large-scale video datasets with accurate and diverse temporally varying camera metadata, which makes learning absolute camera parameterizations difficult. As a result, current models struggle to incorporate photographic camera behavior, including depth-of-field transitions, exposure variations, lens distortions, and color processing, in a controllable and temporally consistent manner. We introduce DeltaCam, a video diffusion framework that models camera behavior through $\Delta$-parameterized neural camera adaptors, operating on relative changes in camera motion and intrinsics instead of absolute states. By learning this differential formulation from synthetic video data, we mitigate reliance on precise real-world camera labels and enable smooth, consistent control over imaging factors such as focal length, aperture, ISO, color temperature, and lens distortion. We extend this framework to real-world footage through two mechanisms: finetuning the controls on real image-metadata pairs for precise shot matching, and extracting disentangled embeddings for implicit video-to-video style transfer without requiring explicit camera parameters. By effectively separating scene content from intrinsic imaging behavior, DeltaCam enables camera-consistent video generation and editing operations that are difficult to achieve with existing models. Ultimately, our results establish a practical and scalable approach for bridging synthetic control and real-world photographic emulation.
Authors: Sambit Mohapatra, Senthil Yogamani, Heinrich Gotzig, Patrick Mader
Abstract: Autonomous driving perception demands accurate and efficient processing of three-dimensional sensor data under strict power constraints. Traditional convolutional neural networks achieve strong detection accuracy but are computationally intensive, limiting their suitability for deployment on resource-constrained neuromorphic platforms. Spiking neural networks offer a compelling alternative through event-driven sparse computation, yet their application to complex real-world perception tasks such as three-dimensional object detection remains limited. In this work, we propose an end-to-end spiking encoder-decoder network for object detection in bird's eye view representations of LiDAR point clouds, trained using surrogate gradient backpropagation. We train two variants: a membrane potential variant that reads continuous neuron state at the output stage for maximum accuracy, achieving $92.05$/$87.04$/$86.51$ AP at $\mathrm{IoU}\!=\!0.5$ (Easy/Moderate/Hard), and, a fully binary spiking variant that operates exclusively on spike trains at every layer for direct neuromorphic deployment. We evaluate four input spike encoding strategies and demonstrate that allowing the network to learn spike representations directly from data outperforms hand-crafted Poisson, latency, and z-axis encoding schemes on the KITTI benchmark, where sequential frames are unavailable and the BEV input is presented repeatedly across timesteps as a proxy for temporal streaming. A block-wise energy analysis demonstrates a $3.33\times$ reduction in synaptic operation energy over an equivalent CNN under conservative loop-based operation. Together, these results demonstrate the viability of spiking neural networks for accurate and energy-efficient neuromorphic perception in autonomous driving.
Authors: Junho Lee, Kwanseok Kim, Joonseok Lee
Abstract: Recent advances in generative models highlight the power of geometry-aware modeling in manifold-constrained settings. Yet, for natural images, the field remains confined to Euclidean assumptions, failing to exploit the potential of intrinsic geometric structures within the data. In this work, we investigate the geometry of natural images and observe that semantic information is predominantly encoded in directional components, while norm components can be approximated by the global average. This property holds across both RGB and latent spaces, suggesting that natural images can be effectively modeled on a hypersphere. Building on this finding, we introduce Spherical Optimal Transport Flow Matching (SOT-CFM), which utilizes angular distance, and Spherical Flow Matching (SFM), which constrains dynamics directly on the manifold. Our experiments demonstrate that these geometry-aware methods achieve superior performance against Euclidean baselines. Ultimately, this work provides a novel perspective that bridges the gap between Riemannian manifold-based modeling and natural image generation.
Authors: Chaoyan Huang, Cheng-Han Huang, Ismail R. Alkhouri, Rongrong Wang
Abstract: Recently, Deep Image Prior (DIP) has demonstrated strong capabilities for solving inverse imaging problems (IIPs) by optimizing a randomly initialized convolutional neural network in a training-data-free regime. However, DIP suffers from overfitting to noisy measurements due to network over-parameterization, making early stopping (ES) essential. The most successful ES method tracks fluctuations in the running variance of the network output to detect overfitting. However, in many applications, these fluctuations may appear prematurely, leading to unstable reconstructions. In this paper, we first show that nearly optimal DIP early stopping can be achieved when two independent noisy copies of the degraded image are available. Motivated by this observation, and since obtaining two fully independent copies is infeasible, we propose an overfitting detection framework based on constructing pseudo self-referenced images, resulting in three IIP-specific algorithms. Our approach is further supported by theoretical results on single-reference validation, pseudo-validation estimation, and the impact of shared noise. Across different IIPs, ranging from natural image restoration to medical image reconstruction, and under varying noise levels and noise types, our methods consistently outperform existing DIP early stopping approaches, all without requiring an accurate estimate of the noise level.
Authors: Joao Leonardo Harres Dall Agnol, Luiz Fernando Puttow Southier, Jefferson Tales 0liva, Marcelo Teixeira, Rodrigo Mineto, Marcelo Filipa, Dalcimar Casanova, Erick Oliveira Rodrigues
Abstract: Image enhancement plays a crucial role in infant fingerprint matching, as child-specific characteristics such as smaller finger dimensions and thinner ridge structures often degrade image quality during acquisition. To address these limitations, enrollment typically depends on specialized highresolution scanners, which most existing enhancement methods are not designed to support. Consequently, identification rates for children remain significantly lower than those achieved with adult fingerprints. This study introduces Recursive Class Connectivity Classification (R3C), a novel framework that iteratively refines binary segmentation outputs from existing enhancement methods by extending ridge structures. R3C does not require modifications to the underlying classifier and operates without training data, which is not currently available for infant fingerprints. Instead, the method improves segmentation by repeatedly feeding the classified image back into the classification process, while combining each intermediate segmentation with the original input image. Experiments conducted on three fingerprint datasets using four different enhancement classifiers show that R3C can increase the True Acceptance Rate (TAR) by up to 4% for children and over 40% for newborns, compared to using the enhancement methods alone. A qualitative analysis further demonstrates that R3C reconnects fragmented ridge patterns, improving the visual quality of segmentation. Because it functions independently of the enhancement method used, R3C provides a flexible and broadly applicable solution for improving binary segmentation.
Authors: Xiaoyang Lyu, Muxin Liu, Xiaoshan Wu, Ruicheng Wang, Yi-Hua Huang, Yang-Tian Sun, Shaoshuai Shi, Xiaojuan Qi
Abstract: Consistent 3D geometry estimation from streaming RGB input is crucial for real-world applications such as autonomous driving, embodied AI, and large-scale reconstruction. While modern monocular geometry foundation models achieve strong single-image accuracy, they exhibit severe temporal inconsistency on continuous input, notably dominated by scale--shift drifting. Through targeted empirical analysis, we trace this instability to its root cause: fluctuations in latent feature statistics, whose mean and variance directly determine the predicted depth's scale and shift. Building on this insight, we introduce Dynamic Feature Normalization (DyFN), a lightweight, causal recurrent module that dynamically and robustly modulates feature statistics to maintain stable geometry over time. We adapt powerful pretrained monocular geometry models for streaming by finetuning only DyFN, a mere 2\% additional parameters, while keeping the backbone frozen, thereby achieving temporal consistency without compromising single-image accuracy. Extensive experiments across four benchmarks show that DyFN effectively eliminates temporal artifacts such as disjointed layering and positional jitter, and achieves state-of-the-art temporal stability, improving over prior streaming methods by up to 14\% and even outperforming heavier non-causal video baselines. Project Page: https://shawlyu.github.io/DyFN
Authors: Junwei Zhou, Yu-Wing Tai
Abstract: Building structured 3D scene layouts from a single image requires reconciling visual observations with physical and spatial constraints, a challenge that is difficult to address with direct prediction alone. In this work, we formulate monocular 3D layout estimation as a perceive-then-plan problem with vision-language models, where a Perceiver first grounds the 3D objects and then a Planner iteratively refines the scene hypothesis through actions that improve physical plausibility while preserving consistency with the input image. We propose Layout-as-Policy (LaP), which casts the planning stage as a policy learning problem: 3D layouts are represented as structured states, and refined via discrete actions such as translation, rotation, and rescaling. Starting from an observation-aligned initialization with the geometry-enhanced Perceiver, the LaP Planner is trained to produce action sequences that progressively resolve geometric inconsistencies and enforce realistic spatial relations. To enable effective learning, we combine supervised trajectory initialization with preference-based optimization, allowing the model to learn corrective behaviors without requiring explicit reward engineering. This formulation transforms layout estimation from a one-shot prediction task into an iterative refinement process, enabling better handling of global constraints and complex object interactions. Experiments demonstrate that our approach produces layouts that are more physically coherent and better aligned with visual observations, while naturally supporting downstream tasks such as scene editing and manipulation.
Authors: Renjie Lu, Xulong Zhang, Xiaoyang Qu, Shangfei Wang, Jianzong Wang
Abstract: Unified Multimodal models (UMMs) built on a single architecture have shown impressive performance in both understanding and generation. We identify a fundamental challenge that lies in inductive biases induced by distinct supervision signals: generation branch prefers high-fidelity, fine-grained representations capable of reconstruction, while the understanding favours semantically discriminative embeddings that remain invariant to task-irrelevant factors. Consequently, optimizing these complementary but non-equivalent objectives within a monolithic backbone leads to mutual impairment instead of enhancement. In this paper, we first analyze the root cause of this interference in unified backbones and reveal a complementary structure in their internal representations. Motivated by the observation, we propose DIVA, a self-improved post-training framework that transforms the representation divergence into interior synergy. By explicitly factorizing the visual representation into shared and unique components based on two complementary information flow, DIVA enables both the understanding and generation branches to achieve beneficial transferring while preserving the integrity of unique information from cross-flow interference via mutual information estimation. Despite its generality, our method consistently achieves improvements across visual understanding (+7.82%) and generation (+8.46%). The official code is available at: https://github.com/Jayyy-H/DIVA.
Authors: Tianshuo Xu, Yichen Xie, Depu Meng, Chensheng Peng, Quentin Herau, Bo Jiang, Yihan Hu, Wei Zhan
Abstract: Video world models should maintain evolving states when evidence is unobserved, yet current generators often freeze hidden states upon interruption. This is not simply a capacity problem: pretrained video diffusion transformers already possess KV-cache mechanisms capable of non-local retrieval, but they are rarely trained to use them as dynamic memory. We introduce ReMind, a framework eliciting dynamic memory behavior via memory-oriented data, event-aware training, and cache adaptation. Organized around a taxonomy of 100+ dynamic events, we build a camera-annotated training mixture combining VLM-filtered real videos, generated hard dynamics, synthetic camera loops, and memory-interruption augmentations. Each clip is converted into a frame graph with protected anchors, degraded intervals, and explicit temporal gaps. A node-structured curriculum, including node-drop, noisy memory, frontier continuation, and reference-cache training, forces the model to retrieve relevant past states across interruptions rather than relying solely on local continuity. PM-RoPE, an elegant camera-phase RoPE extension, unlocks spatiotemporal retrieval at a single-attention cost while preserving pretrained pathways. ReMind achieves the best overall scores on STEVO-Bench and recovery tasks. Furthermore, general image-to-video evaluations confirm this curriculum avoids catastrophic forgetting. We will open-source our code, data, and models.
Authors: Yufei Zheng, Xuhan Zhu, Zide Liu, Chunpeng Zhou, Chenfeng Wang, Yongchao Xu, Yunnan Wang, Jiawei Liu, Pengfei Yu, Wei Zhai, Yang Cao, Zheng-Jun Zha
Abstract: Spatial understanding of the physical world from 2D visual inputs hinges on two complementary forms of geometric knowledge: holistic 3D structural perception and fine-grained metric scale estimation. Existing multimodal large language models (MLLMs) typically address only one facet, ingesting either depth maps or point clouds as additional model inputs, which incurs substantial computational overhead and inherits the generalization limitations of upstream prediction models. We propose GAMSI, a dual-pathway Geometry-Aware MLLM for Spatial Intelligence that takes only RGB images as input while internalizing both forms of geometric prior within a unified autoregressive backbone. Specifically, we introduce Metric-Structure Decoupled Queries (MSDQ) which employ two groups of learnable queries to respectively extract dense metric signals and sparse structural cues from the shared visual context, with a task-decoupled attention mask further preventing the two pathways from contaminating each other. Building on this, an Expert-Guided Visual Grounding (EVG) module projects the aggregated cues back to frame-level visual features and aligns them with vision foundation models, which serve purely as training-time supervision, rather than as model inputs. We further build a multi-task spatial instruction-tuning dataset (MTS) comprising 152{,}776 samples spanning 13 task types and three visual modalities, consolidated from six public datasets. Trained with a two-stage curriculum, GAMSI achieves state-of-the-art performance on seven spatial intelligence benchmarks.
Authors: Siyu An, Junru Lu, Junnan Dong, Qiufeng Wang, Yinghui Li, Weizhi Fei, Zichao Yu, Zheng Yuan, Biao Liu, Haopeng Wang, Renzhao Liang, Yixuan Yang, Yunhang Shen, Bo Ke, Keyu Chen, Linhao Luo, Difan Zou, Xiao Huang, Di Yin, Ruizhi Qiao, Xing Sun
Abstract: Multimodal modeling represents a vital step from modality-agnostic reasoning toward world modeling. While early approaches predominantly rely on late-fusion that assembles encoders and frozen language backbones with output heads, recent efforts have shifted the paradigm toward native multimodal modeling (NMM) with the intrinsic integration of modalities for superior multimodal performance. Despite its potential, the design space of native architectures remains insufficiently defined. In this paper, we present the community with a formalized roadmap for this transition. Specifically, we formally define the architectural nativity, distinguishing mid-fusion and early-fusion from non-native paradigms. We further organize the existing native models through the lens of input-output duality into three categories: (i) Multi-to-Text for cross-modal comprehension with text-only output; (ii) Multi-to-Target for scenario-oriented generation, e.g., image, audio and video generation, and (iii) Multi-to-Multi for unified modeling with symmetric input-output. We deliver a comprehensive and industrial-grade investigation into the transition toward the definitive NMM framework, where understanding and generation seamlessly coexist within a unified transformer paradigm. We systematically unpack the end-to-end pipeline from industrial perspectives from architectural coordination, massive data curation, to full-stack training recipes, inference & deployment, and the comprehensive evaluation for truly native modeling.
Authors: Jiaxiang Liu, Zhida Feng, Pengyu Zou, Zhenyu Qian, Tianrui Zhu, Jun Xia, Yuehu Dong, Yanzheng Lin, Honglin Xiong, Anqi Chen, Yunpeng Ding, Jinghui Duan, Lin Gao, Chao Han, Tiechao He, Jiakang Hu, Ranjun Hua, Xueming Jiang, Qingli Kong, Yuting Lei, Tianyu Li, Yunlin Liu, Changling Liu, Yaxin Liu, Yi Liu, Xuguang Liu, Xiaolong Ma, Yan Pan, Yiran Ren, Nan Sheng, Yu Sun, Siyang Sun, Yixiang Tu, Yang Wan, Huanai Wang, Siqi Wang, Yang Wu, Youzhi Yang, Xiaowen Yang, Jianwen Yang, Yehua Yang, Quanwen Zhang, Xinmin Zhang, Haoxin Zhang, Xiang Zhang, Jun Zhang, Qian Zhang, Qiao Zhao, Qi Zhou
Abstract: We introduce ERNIE-Image, an open-source text-to-image generation model built upon an 8B single-stream DiT architecture. ERNIE-Image aims to bridge the gap between current open-source models and leading closed-source systems through more effective mining of large-scale pre-training data and improved supervision quality throughout training. During pre-training, we adopt a bottom-up data construction pipeline that combines fine-grained image categorization, rich caption annotation, aesthetic assessment, and hierarchical sampling. This strategy reduces data noise while preserving long-tail concepts and detailed real-world knowledge, providing a stronger foundation for complex generation tasks. In the post-training stage, we use a top-down data construction pipeline for high-demand scenarios, diversify prompt annotations to better match real user inputs, and apply a stabilized DPO strategy to align the model with human aesthetic preferences. We further train ERNIE-Image-Turbo for efficient 8-NFE generation and propose MT-DMD to mitigate capability drift during distillation. To make the model easier to use in practical scenarios, we equip it with a lightweight Prompt Enhancer that expands concise user intents into structured visual descriptions. In addition, we develop ERNIE-Image-Aes, an industrial-grade aesthetic model, together with ERNIE-Image-Aes-1K, a human-annotated benchmark for realistic aesthetic evaluation. Extensive qualitative and quantitative experiments show that ERNIE-Image achieves leading performance among open-source models and approaches top-tier commercial models in instruction following, text rendering, and aesthetic quality. We release the trained models and aesthetic resources to facilitate further academic research and technical progress in the AIGC community.
Authors: Xiaotian Hu, Mingxuan Liu, Junwei Huang, Kasidit Anmahapong, Yifei Chen, Yiming Huang, Xuguang Bai, Zihan Li, Hongjia Yang, Yingqi Hao, Hong Xu, Yu Jiang, Tian Tian, Yi Liao, Haibo Qu, Qiyuan Tian
Abstract: Automated fetal ultrasound interpretation requires a workflow from visual perception, including plane recognition and anatomical segmentation, to clinical understanding, including biometric measurement and diagnostic reporting. However, the prevailing "one-task, one-model" paradigm limits systematic integration of evidence across this multi-step process. Although multimodal large language models (MLLMs) show promising visual understanding, their limited domain-specific grounding and hallucination risks restrict reliability in fetal ultrasound analysis. To address these limitations, we propose FetUSAgents, a tool-augmented multi-agent system for comprehensive fetal ultrasound interpretation, supporting visual question answering (VQA), report generation, image captioning, and video summarization. FetUSAgents coordinates task-specific visual tools through collaborative LLM agents and decomposes clinical queries into subtasks that progress from anatomical recognition to quantitative measurement. We further introduce Dual-Path Evidence Arbitration (DPEA), which integrates LLM-based deliberative reasoning with structured computational evidence from specialized visual tools. A retrieval-enhanced evidence bank consolidates intermediate findings to support traceable and clinically grounded conclusions. In addition, we construct FetUS-VQA, a dedicated VQA benchmark for fetal ultrasound, comprising 1,892 images and 3,205 question-answer pairs across 10 clinical tasks. Extensive out-of-distribution experiments show that FetUSAgents outperforms general and medical MLLMs, exceeding the strongest baseline by more than 25 percent in VQA accuracy. These results suggest a scalable route toward evidence-driven clinical assistants for prenatal imaging. Code is available.
Authors: Yi Zhou, Thiara Sana Ahmed, Jacqueline Chua, Meng Wang, Qinrong Zhang, Alejandro F. Frangi, Huazhu Fu, Jun Cheng, Leopold Schmetterer, Bingyao Tan
Abstract: Vascular circulation follows fundamental biophysical principles that optimize mass transport and metabolic energy expenditure, which can be effectively modeled by Murray's law. However, contemporary deep learning methods for vascular segmentation often neglect these biophysical constraints. This leads to physiologically implausible branching and misclassification vascular trees, rendering. These automated segmentation results are unreliable unreliable for downstream clinical tasks such as blood flow simulation or disease quantification. In this paper, we introduce MARVEL (Universal MurrAy's law-infoRmed Vessel sEgmentation and topoLogy estimation), a backbone-agnostic framework that integrates biophysical priors into vascular tree extraction. MARVEL combines per-pixel supervision with explicit radius predictions to enforce local bifurcation constraints derived from an empirical width-exponent mapping. We implement these constraints as differentiable regularizers during training to guide models toward physiologically consistent reconstructions. We evaluate MARVEL on eight public datasets across multiple vascular modalities and segmentation backbones. Results demonstrate MARVEL's superior performance in segmentation accuracy, topological consistency, and physiological plausibility. By converting segmented masks into graph-based hemodynamic simulations, we demonstrate that MARVEL preserves the subtle pathological narrowing and topological connectivity required to distinguish hypertensive from normotensive eyes. Results show that MARVEL significantly improves the classification of hypertension via arteriovenous pressure differences in the eye (p < 0.001), outperforming baseline models in both topological consistency and clinical predictive value.
Authors: Longteng Guo, Yifan Wang, Pengkang Huo, Tailai Chen, Yuze Wu, Jing Liu, Xinxin Zhu
Abstract: Recent multimodal large language models (MLLMs) achieve strong performance on visual reasoning benchmarks, yet it remains unclear to what extent such performance reflects reasoning directly grounded in visual evidence. We introduce VisReason, a benchmark for vision-centric reasoning in everyday scenarios where perception and inference are tightly coupled. VisReason contains 1,505 questions across 10 categories spanning perceptual, structural, and conceptual reasoning. Our evaluation shows that VisReason poses a qualitatively different challenge from existing benchmarks, exposing substantial gaps between humans and current MLLMs and revealing limited benefits from test-time reasoning strategies. VisReason offers a focused diagnostic for evaluating vision-centric reasoning beyond language.
Authors: Feng Zhou, Jian Zhang, Yuhang Sun, He Wang, Qiong Wen, Debao Kong, Tieru Wu, Rui Ma
Abstract: 3D Gaussian Splatting (3DGS) has shown great potential in autonomous driving simulation and data generation, enabling photorealistic reconstruction and flexible scene manipulation. However, existing 3DGS scene editing methods have limited support for road geometry editing (e.g., inserting speed humps or sunken roads), and generally do not couple such edits with plausible vehicle-road interaction dynamics. Such editing is essential for generating training data under extreme driving scenarios or evaluating system reliability under these road irregularities. Moreover, many optimization-based methods require minutes of per-edit refinement, while existing efficient alternatives mainly focus on appearance-level or object-level manipulation rather than physics-aware road irregularity editing. To address these limitations, we propose RoVES, a Road-and-Vehicle Editing System for physics-aware 3D Gaussian editing in driving scenes. RoVES enables single-image-driven road geometry insertion and couples the edited road profile with a 4-DOF half-car vehicle dynamics model to achieve physics-aware vehicle pose correction in vertical displacement and pitch. RoVES inserts road elements in a one-shot, optimization-free pipeline (1.84s), and the full pipeline (including color transfer and vehicle-dynamics-based pose correction) completes in 6.24s; it edits dynamic vehicles via pose editing and corrects poses frame-by-frame to approximate dynamics-consistent vertical displacement and pitch responses. Experiments on the Waymo dataset show that RoVES provides practical efficiency and competitive visual consistency for physics-aware driving scene generation.
Authors: Ruoxi Cheng, Haoxuan Ma, Zhengfei Hai, Yiyan Huang, Ranjie Duan, Tianle Zhang, Xu Yang, Ziyi Ye, Xingjun Ma
Abstract: Large Vision-Language Models (LVLMs) have advanced multimodal understanding, yet their reliability is limited by hallucination, where generated content conflicts with visual facts. Existing mitigation methods either rely on costly external interventions, such as instruction tuning and retrieval, or use internal mechanisms that remain limited by flawed attention weights and entangled hidden representations. We propose Adversarial Orthogonal Disentanglement (AOD), a latent geometric framework for mitigating LVLM hallucinations. AOD learns a hallucination-related direction through a minimax objective: a classifier concentrates hallucination signals into the projected component, while an adversary removes them from the orthogonal residual space via a Gradient Reversal Layer. The learned direction enables a training-free dual-forward-pass contrastive decoding strategy that suppresses hallucinations while preserving general capabilities. Experiments on three LVLMs across four hallucination and four utility benchmarks show that AOD consistently outperforms strong baselines. It improves POPE accuracy by over 6\% on average, boosts AMBER by 6\%, and maintains strong performance on utility tasks such as MMMU. Further analysis shows robust transfer across datasets, suggesting that AOD captures general hallucination-related biases rather than dataset-specific artifacts. Our source code and datasets are available at https://github.com/Hunter-Wrynn/AOD.
Authors: Fangtai Wu, Hailong Guo, Shijie Huang, Jiayi Song, Yubo Huang, Mushui Liu, Zhao Wang, Yunlong Yu, Jiaming Liu, Ruihua Huang
Abstract: Customized image editing aims to equip pre-trained diffusion models with specific visual effects using limited paired data, typically via Low-Rank Adaptation (LoRA). As the number of desired effects grows, storing and dynamically loading numerous these effect LoRAs significantly increases deployment overhead. Furthermore, current pipelines typically cascade these effect LoRAs with acceleration modules for fast generation, which triggers severe parameter interference and results in concept bleeding and style degradation. We propose CollectionLoRA, a multi-teacher on-policy distillation framework capable of distilling the concepts of up to 50 different effect LoRAs along with few-step generation capabilities into a single LoRA. This fundamentally resolves the feature interference issue and significantly reduces deployment costs. Specifically, the method introduces (i) a Probabilistic Dual-Stream Routing mechanism that enables the model to randomly switch between data sources during training, effectively enhancing its generalization in unseen scenarios; (ii) an Asymmetric Orthogonal Prompting strategy to achieve concept isolation within the prompt space; (iii) a Coarse-to-Fine Distillation Objective to mitigate the distribution gap between the teacher and student models. Extensive evaluations show that CollectionLoRA distills all customized effects and few-step generation into a single LoRA, reducing deployment overhead while achieving concept fidelity comparable to or better than independently trained teacher models.
Authors: Xia Li, Xinran Liu, Lin Qi, Junyu Dong
Abstract: Camouflaged object detection (COD) from a single image is a challenging task due to the high similarity between objects and their surroundings. Existing fully supervised methods require labor-intensive pixel-level annotations, making weakly supervised methods a viable compromise that balances accuracy and annotation efficiency. However, weakly supervised methods often experience performance degradation due to the use of coarse annotations. In this paper, we introduce a new weakly supervised approach for camouflaged object detection to overcome these limitations. Specifically, we propose a novel network, MGNet, which tackles edge ambiguity and missed detections by utilizing initial masks generated by our custom-designed Cascaded Mask Decoder (CMD) to guide the segmentation process and enhance edge predictions. We introduce a Context Enhancement Module(CEM) to reduce the missing detection, and a Mask-guided Feature Aggregation Module (MFAM) for effective feature aggregation. For the weak supervision challenge, we propose BoxSAM, which leverages the Segment Anything Model (SAM) with bounding-box prompts to generate pseudo-labels. By employing a redundant processing strategy, high quality pixel-level pseudo-labels are provided for training MGNet. Extensive experiments demonstrate that our method delivers competitive performance against current state-of-the-art methods.
Authors: Chunzheng Zhu, Jianxin Lin, Feng Wang, Cheng Jiang, Guanghua Tan, Zhenyu Zhou, Shengli Li, Kenli Li
Abstract: Reliable quality control (QC) of ultrasound images is essential for both real-time acquisition guidance and retrospective clinical audit, yet existing approaches rely heavily on per-plane annotations, or employ pseudo-labeling prone to systematic bias under spatial deformations inherent in clinical acquisition. We present STRIQ, a registration-driven framework that recasts annotation-free US plane quality control as a subspace-guided consistency measurement problem. Specifically, STRIQ introduces a Latent Registration Aligner (LRA) to establish hierarchical feature space correspondences between query images and variance-driven anchors, which are autonomously distilled from unlabeled data via a variance spectrum criterion to serve as structurally stable prototypes. To further disambiguate anatomical planes and mitigate negative knowledge transfer, we propose an Orthogonal Knowledge Subspace (OKS) module. The OKS decomposes plane-specific representations into mutually orthogonal subspaces, enabling fine-grained expert collaboration while preventing inter-plane interference, ensuring that the quality metric is grounded in principled subspace proximity. Extensive experiments on the in-house US4QA and public CAMUS datasets demonstrate that STRIQ achieves state-of-the-art correlation with clinical quality scores, establishing a new paradigm for annotation-free, real-time reliable ultrasound quality control. Our code is available at https://github.com/zhcz328/STRIQ.
Authors: Chunzheng Zhu, Yijun Wang, Jianxin Lin, Feng Wang, Hongwei Wang, Lei Zhao, Shengli Li, Kenli Li
Abstract: Self-supervised pre-training paradigm has gained increasing prominence for learning transferable representations in medical imaging, yet existing methods for ultrasound (US) images operate at the image or frame level, overlooking the anatomical context for clinical-aligned representation learning. In this work, we propose an anatomy-anchored ultrasound self-supervision framework ANAUS that shifts representation learning from generic visual regions to clinically meaningful anatomical structures. Utilizing a learnable latent prompt engine alongside a one-time domain adaptation on existing public image--mask pairs, we empower the LP-SAM module to achieve annotation-free anatomy delineation at scale. Building upon this anatomical grounding, we propose a dual-policy self-supervised learning paradigm consisting of inter-view semantics-aware anatomy-separating alignment and contextual core-region prediction to enhance representation learning. Specifically, the former enforces feature invariance within identical anatomical regions while promoting discriminability across distinct structures; the latter compels the model to reconstruct corrupted regions, thereby capturing fine-grained structural details. Extensive evaluations on six public datasets demonstrate that \ours{} consistently outstrips current state-of-the-art methods while maintaining the computational efficiency essential for clinical deployment. Code is available at https://github.com/zhcz328/ANAUS.
Authors: Jiaxuan Liu, Yunkang Cao, Yufeng Chen, Chunyang Li, Yuhuan Du, Hui Zhang
Abstract: The deployment of zero-shot anomaly detection (AD) in embodied industrial inspection is severely bottlenecked by its reliance on passive, fixed-viewpoint 2D imagery. Such formulations inherently fail to accommodate the active, dynamic observations required in real-world environments. To break this limitation, we introduce Real-to-Twin Anomaly Detection, a novel task that evaluates physical observations directly against geometrically matched CAD Digital Twins. To tackle this new task, we propose AVATAR, a framework designed to learn robust semantic alignment between Real and Digital Twins. By bridging benign Sim2Real domain gaps using only defect-free pairs, AVATAR effectively transforms CAD priors into dynamic, anomaly-free references. This elegant formulation enables the model to localize diverse anomalies in a zero-shot manner as unalignable deviations, eliminating the need for defect annotations. Extensive experiments demonstrate that AVATAR substantially outperforms adapted state-of-the-art baselines, exhibiting exceptional robustness to severe viewpoint variations. The code and dataset will be made publicly available.
Authors: Eyal Hanania, Nadav Kirsch, Daniel Arkushin, Jonathan Benvenisti, Amos Bercovich, Elie Zemmour, Sahar Froim
Abstract: Detecting laughter in video is essential for affective computing and narrative understanding, yet existing approaches treat it as coarse clip-level classification, failing to capture precise temporal boundaries of brief, transient laughter events. We address this gap with two complementary contributions. First, we introduce UR-FUNNY-Temporal and SMILE-Temporal, fully annotated temporal laughter datasets extending two widely-used humor benchmarks. Our annotations cover over 11,053 videos (78.8 hours) and provide precise onset/offset boundaries for each laughter event, along with rich metadata distinguishing speaker vs. audience laughter, modality dominance (acoustic, visual, or both), and intensity levels. Second, we propose a lightweight weakly-supervised framework for temporal laughter localization. Our architecture combines fixed HuBERT and MAE encoders with temporal softmax pooling and adaptive modality gating, learning fine-grained temporal grounding from clip-level labels without requiring frame-level annotations during training. Experiments across three datasets demonstrate that our approach substantially outperforms multimodal foundation models including Gemini 3 Flash, achieving 99% F1 and 68.1% localization precision on sports broadcast data. Ablations validate each architectural component. Furthermore, our precise temporal tags improve downstream laughter reasoning by 227% on CIDEr, enabling GPT-3.5 to outperform GPT-4o. The code, UR-FUNNY-Temporal and SMILE-Temporal datasets are publicly available at https://github.com/WSCSports/MTLLFM-temporal-laughter-localization.
URLs: https://github.com/WSCSports/MTLLFM-temporal-laughter-localization.
Authors: Nancy Iskander
Abstract: Generating 3D models from face sketches is an active topic of research in Computer Graphics due to its potential to tremendously facilitate the modeling of faces for both professional 3D arists and novices. Motivated by the observation that facial expressions are responsible for significantly altering and shaping the contours in our faces, we combine both expression detection and 3D model generation in our approach. The result is a novel approach to generating 3D models from sketches which relies on three components: Convolutional Neural Networks, a parametric 3D face model (Valley Girl), and Active Snake Contours. For the first time in the literature, CNNs are trained (using our own generated dataset) to detect the expression in the given sketch through detecting the active FACS Action Units. The expression is then duplicated on Valley Girl to obtain a 3D model with a similar expression. Active Snake Contours are then used to find the transforms needed to close the gaps between that model and the given sketch.
Authors: Udith Haputhanthri, Declan Campbell, Rim Assouel, Jonathan D. Cohen, Taylor W. Webb
Abstract: Despite success on standard benchmarks, vision language models display persistent failures on tasks involving processing of multi-object scenes, including many tasks that are relatively easy for humans. Recent work has found that these failures may stem from a basic inability to accurately bind object features in-context, a challenge that is referred to as the "binding problem" in cognitive science and neuroscience. The human visual system is thought to solve this binding problem via serial processing, attending to individual objects one at a time so as to avoid interference from other objects. Recent work has proposed "pointing" -- the use of explicit spatial coordinates to refer to objects -- as an analogous solution for vision language models, and found that it improves performance on challenging multi-object tasks. However, it is unclear $\textit{why}$ (i.e., on a mechanistic or representational level) this approach improves performance, and how directly this relates to serial processing in human vision. Here, we investigate this question. We find that learning to point-via-text induces an internal visual search routine, and we characterize the mechanisms that support this procedure. We also find that pointing behavior can be generalized to new tasks via fine-tuning, and that doing so eliminates binding errors and enables compositional generalization. These results provide a proof-of-principle that serial processing can solve the binding problem for vision language models just as it does for biological vision.
Authors: Fanhu Zeng, Zhicong Luo, Zefan Wang, You Li, Chi Chen, Maosong Sun
Abstract: Visual reasoning through reinforcement learning with verifiable rewards (RLVR) has achieved remarkable progress. However, when dealing with multi-source inputs, existing approaches tend to treat them as a mere accumulation of information, lacking explicit mechanisms to distinguish whether integrating additional sources yields information gain or introduces interference. Therefore, they struggle to effectively model dynamic interaction when integrating multiple sources, particularly when they differ significantly in physical properties and semantics, e.g., infrared and depth, leading to inferior performance to mono-source reasoning when a certain source holds the dominant signal. To address this issue, we propose MARS, a novel mono-anchored multi-source reasoning framework that models each visual modality as an independent information source. Specifically, by treating mono-source rewards as dynamic anchors, our method explicitly incorporates the information gain introduced by multi-source fusion into advantage normalization and adaptively emphasizes mutual promotion between sources while suppressing potential noise or conflicts during RLVR. From theoretical analysis, our method effectively quantifies information gain introduced by multi-source integration in gradient estimation, enabling consistent modality regulation. Empirical results also show impressive 3.2% and 4.9% performance gains on GRPO and DAPO across diverse datasets, confirming effectiveness of our method.
Authors: Nitish Shukla, Arun Ross
Abstract: Face recognition systems are increasingly vulnerable to morphing attacks, where a composite image is crafted to match multiple identities, enabling unauthorized access and identity fraud. Existing detection methods identify morphed images but cannot recover constituent images or identities, limiting their forensic utility. This paper presents a novel reference-free facial demorphing framework that leverages Multimodal Large Language Models (MLLMs) to guide a coupled diffusion-based reconstruction process. Our key innovation lies in extracting semantic embeddings from intermediate MLLM layers to condition the demorphing, providing high-level reasoning about facial attributes and identity cues that complement low-level pixel information. We formulate demorphing as a coupled conditional generation problem, where both constituent faces are synthesized jointly through a denoising diffusion model operating directly in the RGB domain, ensuring inter-identity consistency while preserving fine-grained perceptual details. Unlike prior approaches that rely on compressed latent representations or assume identity overlap between training and testing sets, our method bypasses lossy text generation-reencoding cycles by directly utilizing MLLM hidden states as conditioning signals, enabling the denoising network to attend to subtle visual cues such as hair, background, and facial textures. Ablation studies further reveal that middle MLLM layers encode more identity-discriminative representations, RGB-domain demorphing outperforms latent-space approaches by 30--40\% at strict operating points, and full MLLM embeddings provide substantial advantages over raw ViT features through enhanced semantic structuring from multimodal pretraining.
Authors: Ting-Hsuan Chen, Ying-Huan Chen, Tao Tu, Jie-Ying Lee, Cho-Ying Wu, Fangzhou Lin, Hengyuan Zhang, David Paz, Xinyu Huang, Yuliang Guo, Yu-Lun Liu, Yue Wang, Liu Ren
Abstract: Generating complete digital twins from videos requires precise camera control, global scene coverage, and strict spatial-temporal consistency constraints that remain challenging for perspective video generators due to their limited field of view (FoV). Their narrow FoV forces long or multi-view trajectories, amplifying cross-view inconsistency and temporal drift. We argue that 360{\deg} video generation offers a natural solution: panoramic coverage simplifies trajectory design and provides a strong global context for maintaining coherence. We introduce Pantheon360: Taming Digital Twin Generation via 3D-Aware 360{\deg} Video Diffusion, a controllable 360{\deg} video generation framework that synthesizes high-fidelity videos from sparse 360{\deg} inputs. The key idea is an explicit 3D Cache, reconstructed from the input, which serves as a geometric scaffold for any user-defined camera path. This allows the diffusion model to focus on photorealistic texture refinement while the 3D Cache enforces global geometric consistency. Experiments show that Pantheon360 achieves superior visual quality and unmatched geometric coherence, enabling reliable and flexible 360{\deg} scene generation for downstream simulation and digital-twin applications.
Authors: Zhuoqun Li, Boxi Cao, Guiping Jiang, Fangrui Lv, Ruotong Pan, Jianan Wang, Xiangyu Wu, Hongyu Lin, Yaojie Lu, Yong Du, Ruyin Jia, Liyan, Tingting Gao, Han Li, Xianpei Han, Le Sun
Abstract: Metaphorical videos are prevalent across various real-world scenarios to convey complex ideas, and understanding them typically requires high-order cognitive capabilities. The lack of systematic studies on metaphorical video understanding not only constrains the real-world applicability of MLLMs but also impedes the thorough assessment of their high-order cognitive capabilities. To bridge this gap, we propose MetaphorVU-Bench, the first systematic and comprehensive benchmark dedicated to metaphorical video understanding. Through experiments, we find current MLLMs struggle with accurate metaphorical video understanding, lagging far behind human level, primarily due to defective cross-domain mapping. Motivated by this finding, we construct a metaphor knowledge graph as mapping augmentation and propose MetaphorBoost, an inference-time enhancement framework achieving consistent performance improvement. Our benchmark, analysis, and method provide useful insights and a foundation for future research on advancing MLLMs.
Authors: Kaixiang Chen, Pengfei Fang, Hui Xue
Abstract: Adapting large vision-language models (VLMs) such as CLIP to downstream tasks remains challenging, as full fine-tuning is computationally prohibitive and prone to overfitting in low-data regimes. Parameter-efficient fine-tuning (PEFT) alleviates these issues with lightweight prompt- or adapter-based modules, and cross-modal coupling has proven especially effective by strengthening interactions between vision and language. However, existing coupling mechanisms predominantly rely on external auxiliary modules, leading to indirect, coarse-grained interactions that are structurally decoupled from the original VLM and thus limit representational expressiveness. In this paper, we propose Multi-Modal Interactive Agent Layer (MAIL), a PEFT paradigm that embeds cross-modal coupling directly into the intrinsic computation modules of VLMs. MAIL freezes the backbone and inserts lightweight agent layers after core modules, such as LayerNorm, to approximate the parameter updates induced by full fine-tuning. To couple visual and textual streams at this level, we introduce a bottleneck-based text-to-image bridge that jointly optimizes paired agent layers across modalities, coordinating the adaptation of corresponding computation modules. We further present MAIL++, which enables bidirectional cross-modal exchange through a meta agent layer, a meta-text bridge, and a meta-image bridge. At inference time, all agent layers are re-parameterized into the frozen backbone, preserving the original computational efficiency. Extensive experiments on few-shot image classification and few-shot universal cross-domain retrieval demonstrate that MAIL and MAIL++ consistently outperform state-of-the-art PEFT methods.
Authors: Zhicheng Zhang, Lei Wang, Yu Zhang, Yongsheng Gao
Abstract: Audio-driven talking-head generation has achieved remarkable progress with recent models such as AniTalker, FLOAT, and Sonic. Despite their success, most existing approaches rely on a single static reference image to condition the entire video generation process at inference stage. This static conditioning paradigm often creates a mismatch between fixed identity features and dynamically evolving facial motion, leading to identity drift, temporal inconsistency, and degraded perceptual quality. We introduce Test-Time Self-Adaptive Conditioning (TT-SAC), a parameter-free inference framework that enables pretrained talking-head generators to adapt their conditioning representations during inference without retraining, gradient updates, or additional supervision. Instead of treating the reference portrait as immutable, TT-SAC composes the generator with its encoder in a feedback loop: the generator's own outputs are re-encoded to construct a refined conditioning representation that better aligns with the temporal dynamics of the synthesized sequence. A single adaptation step approximates a self-consistent equilibrium of the generative process, stabilizing identity and motion across time. We further provide theoretical analysis showing that test-time conditioning adaptation reduces feature variance and improves generative stability under mild Lipschitz assumptions, while exhibiting a principled bias-variance tradeoff that governs the optimal strength of adaptation. Extensive experiments on state-of-the-art talking-head generators and benchmark datasets demonstrate consistent improvements in lip-sync accuracy, temporal coherence, identity preservation, and perceptual fidelity. TT-SAC offers a model-agnostic and training-free strategy for enhancing generative video models, establishing test-time conditioning adaptation as an effective mechanism for stabilizing audio-driven portrait animation.
Authors: Tingxi Chen, Ke Hao, Yabo Chen, Zhengxue Cheng, Rong Xie, Li Song, Haibin Huang, Chi Zhang, Xuelong Li
Abstract: Generating 4D scenes from a single-view video is inherently ill-posed: a single viewpoint lacks the information needed to recover a complete, dynamic scene with full coverage. Existing methods are typically limited to monocular videos, simple 3D effects, or only small viewpoint perturbations around the original viewpoint, falling short of true 4D generation. Meanwhile, the lack of large-scale datasets capturing full-scope 4D scenes with synchronized multi-view videos further hinders progress in this direction. We propose a novel single-view video-to-4D framework that casts full-scope 4D generation as a multi-view video synthesis followed by optimization-based 4D reconstruction from the generated views. To instantiate this formulation end-to-end, we make three key contributions. First, we introduce Real-MV-4D, a large-scale dataset of synchronized multi-view videos captured in diverse real-world environments to provide the 4D supervision. Second, we train a multi-view video diffusion model driven by a novel fused time(T)-view(V) attention mechanism that directly embeds geometric reprojection priors and explicit camera conditioning into its view-time interactions. Unlike basic feature fusion, this direct binding strictly aligns the generation process with physical 3D priors to produce a dense, synchronized T$\times $V video grid. Third, rather than relying on non-interactive and inconsistent 2D video interpolations, we lift the synthesized multi-view videos into an explicit 4D representation (i.e. 4DGS), regularized by a Flow Matching Distillation loss that exploits the multi-view prior to improve novel-view rendering. Extensive experiments demonstrate that our method outperforms existing approaches in both visual fidelity and geometric consistency, enabling full-scope 4D scene generation from single-view videos.
Authors: Jiayi Kong, Xuhui Chen, Chen Zong, Fei Hou, Junhui Hou, Wenping Wang, Ying He
Abstract: Neural Signed Distance Functions (SDFs) excel at reconstructing watertight manifolds but fail on thin structures and open boundaries due to strict inside--outside constraints. Conversely, Unsigned Distance Fields (UDFs) accommodate general geometries but suffer from gradient singularities at the zero-level set, hindering optimization and extraction. We introduce Metric--Phase Fields (MPFs), a decoupled implicit representation that separates metric proximity from topological phase. Given an unoriented point cloud, MPFs learn (i) an unsigned metric field $r$ and (ii) a smooth phase field $\theta$, for which we derive a bounded phase indicator $P=\tanh(\beta\theta)$ that provides soft inside--outside cues where they are meaningful. We couple the two fields via a gated-metric formulation with a residual phase injection to obtain a signed implicit function with stable near-surface gradients. The phase coefficient $\beta$ is learnable, allowing MPFs to adaptively control the sharpness of the phase transition and the degree of saturation of the soft sign indicator. Experiments on both synthetic and scanned thin-shell and thin-plate shapes demonstrate that MPFs preserve thin and layered structures more faithfully than recent SDF-based methods, while also enabling more robust training and more reliable surface extraction than UDF-based approaches. Check out \href{https://github.com/JIAYI-Scarlett/ICML2026-MPF}{MPFs-GitHub} for source code and test models.
Authors: Xinyang Zhai, Chong Yang, Ruizhi Zhang
Abstract: Breast ultrasound imaging is an important noninvasive method for early breast cancer diagnosis, but automatic benign/malignant classification remains challenging due to tumor heterogeneity, blurred boundaries, and data imbalance. To improve feature representation and classification accuracy, this paper proposes the Cross-Stage Attention Mixture-of-Experts Network (CSA-MoE-Net). It adopts a Cross-Stage Attention-enhanced ResNet-18 as the backbone, in which the Cross-Stage Attention module adaptively recalibrates multi-level features, thereby enhancing key tumor features and suppressing redundancy. A three-branch Mixture of Experts (MoE) Block learns complementary features from the Whole Tumor Image, Tumor Core, and Boundary, and an Adaptive Gating Network fuses them to capture morphological, textural, and contextual information. The fused features are denoted as Fused Expert Feature (FEF) in the architecture. Experiments on a balanced dataset of 2,129 breast ultrasound images show that, averaged over 20 independent runs, the model achieves an accuracy of 96.33\%, precision of 94.09\%, recall of 98.53\%, F1-score of 96.25\%, and AUC of 99.50\%. Compared to the baseline ResNet-18, these metrics improve by 3.01, 0.70, 5.37, 2.98, and 5.42 percentage points, respectively. The proposed mechanism requires no invasive modification and can be seamlessly embedded into VGG-16, DenseNet-121, etc., yielding stable performance gains, thus providing reliable support for computer-aided diagnosis.
Authors: Jiangyang Li, Cong Wan, Changjie Wu, Songlin Dong, Lingjun Zhang, Linzhe Shi, Xu Wang, Zhiheng Ma, Hang Zhang, Mu Xu, Yihong Gong
Abstract: Reliable spatial reasoning remains a core bottleneck for vision-language models (VLMs). Existing mainstream training paradigms for spatial reasoning largely rely on outcome alignment or process imitation, lacking explicit constraints on the reasoning process, and therefore struggle to ensure genuine visual dependence and stable reasoning trajectories. In this paper, we construct a high-quality CoT dataset covering diverse spatial phenomena and diagnose the model's reasoning process, revealing two typical types of process degradation during reinforcement learning optimization: Spurious Grounding, which bypasses visual evidence, and Tail Instability, where uncertainty abnormally rises in the later stage of reasoning. To address these issues, we propose ProSR, a process-shaping optimization framework for spatial reasoning. Through a Counterfactual Invariance Penalty and a Tail Drift Penalty, ProSR extends the optimization objective from single answer correctness to two process-level dimensions: visual dependence and trajectory stability. Experiments on multiple complex and out-of-distribution spatial reasoning benchmarks show that ProSR improves answer accuracy while generating reasoning trajectories that are more stable and more dependent on visual evidence.
Authors: Xiang Xie, Xiaonan Liu
Abstract: Building height, the third dimension (3D) of urban spatial data, is absent in over 95% of structures in global geospatial databases. For the emerging low-altitude economy, this data gap forces each aerial platform to rely on real-time onboard sensing rather than pre-computed 3D scene geometry. We present the Location Prior Generation Framework (LPGF), a multi-source data fusion pipeline that integrates Sentinel-2 imagery, UAV telemetry, vehicle GPS trajectories, and OpenStreetMap footprints into structured, reusable urban location priors. LPGF assigns building heights through a three-tier priority hierarchy: (1) explicit OSM height tags where available, (2) floor count multiplied by 3.2 m per story where recorded, and (3) building-type default heights otherwise, yielding a worst-case error of approximately 5.5 m. An optional shadow-based height estimation module (SHEM) is activated only when a four-criterion quality gate is satisfied; when any criterion fails, the pipeline routes to structured fallback. On the MiTra A50 Milan dataset, the quality gate correctly identified two imaging failure modes: sub-pixel shadows at 10 m GSD and ground shadow merging at 0.93 m GSD, producing a consistent 27-building prior in both cases. Tier 3 type-default heights were validated against manual floor counts (n=15), achieving MAE=3.07 m within the 5.0 m uncertainty bound. The framework demonstrates that structured, quality-gated fusion of universally available data streams can bootstrap 3D scene coverage for low-altitude urban operations.
Authors: Chanwut Kittivorawong, Alena Chao, Charlie Si, Alvin Cheung
Abstract: Track materialization converts raw video into reusable object tracks that downstream queries can run against without rerunning tracking, but extracting those tracks efficiently and with high fidelity remains expensive. Prior systems reduce cost through temporal frame sampling, erasing the inter-frame motion that fine-grained tracking requires. In stationary video, however, large portions of each frame contain no objects of interest, and the remaining regions tolerate different sampling rates. We present Tetris, a track-extraction system that decomposes videos into a tile-based polyomino data model, enabling fine-grained spatiotemporal pruning that reduces detector calls with minimal fidelity loss. Tetris runs three operators upstream of the user-provided detector: a classifier identifies relevant tiles and groups them into polyominoes, an integer linear program (ILP) prunes redundant polyominoes under a user-specified accuracy constraint, and a packer assembles the survivors into canvases that minimize detector calls. Across 7 stationary-video datasets, Tetris stays within a 5% tracking accuracy loss of a full-frame, every-frame reference pipeline, whereas prior systems exceed this bound on 3 of the 7 datasets. At this 5% bound, Tetris achieves up to 17.4x higher throughput than prior systems and up to 68.8x higher than the reference pipeline. The project page is at https://tetris-db.github.io .
Authors: Huan Ren, Yihan Chen, Chuxin Wang, Nailong Liu, Wenfei Yang, Tianzhu Zhang
Abstract: Category-level object pose estimation aims to predict the pose and size of arbitrary objects in specific categories. Existing methods struggle with the inherent incompleteness of observed point clouds, which limits their ability to capture complete object shapes for robust pose reasoning. While point cloud completion offers a promising solution, naively treating it as a separate preprocessing step for partial observations introduces compounding errors and additional computational overhead, ultimately hindering both accuracy and efficiency. To address these challenges, we propose ComPose, a novel unified framework that tightly integrates shape completion to provide complete geometric cues for enhanced pose estimation. At the core of ComPose is a keypoint-based progressive completion module, which recovers full shape representations by progressively predicting a sparse set of keypoints and their surrounding dense point sets, empowering the keypoints to capture holistic object geometries. A geometric relation encoding module further enriches keypoint features with both local and global geometric context. In addition, we introduce a novel geometric relation consistency loss to enforce structural alignment between observed keypoints and their predicted NOCS coordinates, ensuring globally coherent coordinate transformations. Extensive experiments on standard benchmarks demonstrate that our method outperforms state-of-the-art approaches without relying on category-level shape priors.
Authors: Jun Li, Ziwei Qin
Abstract: Semi-supervised learning has become a dominant paradigm for reducing annotation costs. However, we argue that the current progress is clouded by a twofold overconfidence problem. Algorithmically, mainstream pseudo-labeling frameworks often conflate prediction confidence with uncertainty, leading to severe confirmation bias. Strategically, since multiple benchmark datasets lack dedicated validation sets, some studies use the test set for validation as well, leading to inflated performance estimates. Subsequent methods, compelled to employ the same strategy to surpass reported SOTA, trigger an arms race of overfitting. This raises concerns that the impressive numerical gains in the community may reflect overfitting rather than genuine progress. Thus, we propose a tri-space calibrated segmentation framework founded on a principled dual-axis reliability assessment engine. It explicitly decouples confidence from uncertainty and uses this signal to detect and correct confirmation bias across feature, probability, and image spaces in a collaborative manner. Across three benchmark datasets, TCSeg consistently delivers strong performance under existing evaluation protocols. More importantly, we advocate that the community report final-checkpoint results under multiple-run protocols, thereby establishing more rigorous benchmarks with a more realistic perspective. Code will be available: github.com/DirkLiii/TCSeg.
Authors: Pengpeng Yu, Runqing Jiang, Qi Zhang, Dingquan Li, Jing Wang, Yulan Guo
Abstract: While feed-forward 3D Gaussian splatting reconstructs renderable Gaussian primitives from sparse context views without per-scene optimization, existing pipelines do not provide a compact scene representation for storage or transmission. A natural solution is to apply existing 3DGS compression methods to the generated Gaussian primitives. However, this approach operates on the final irregular 3D representation and is decoupled from the internal feature-to-Gaussian generation process, which limits compression efficiency. To address this, we introduce CodecSplat, an ultra-compact latent coding framework for feed-forward 3D Gaussian splatting. CodecSplat first encodes an intermediate 2D Gaussian-generation feature into an entropy-coded scene bitstream. At the decoder, the latent feature is reconstructed and used to predict depth and Gaussian parameters, which are then mapped to 3D Gaussian primitives. Note that, by integrating compression into the feed-forward Gaussian generation pipeline, CodecSplat avoids inefficient compression over irregular 3D Gaussian primitives and allows the codec to exploit the structured intermediate feature representation. We instantiate CodecSplat on a feed-forward Gaussian splatting backbone with depth-guided multi-view feature refinement and a hierarchical learned feature codec. On DL3DV and RealEstate10K datasets, CodecSplat achieves 23.56-26.36 dB and 24.76-27.05 dB PSNR with only 20.00-107.77 KiB and 3.37-12.51 KiB per scene, respectively. This is roughly one order of magnitude smaller than compressing feed-forward generated Gaussian primitives, while preserving controllable rate-distortion behavior.
Authors: Mingyi Xu, Jinpeng Lin, Min Zhou, Tiezheng Ge, Ming Zeng
Abstract: Scribble-guided image editing allows users to combine simple scribble annotations with text prompts to specify both where and how an image should be edited, enabling flexible interaction with precise spatial control. However, existing models still exhibit unstable performance under this paradigm, especially in multi-task scenarios. To improve performance, we conduct empirical studies using an open-source editing model and reveal an asymmetry in generalization: instruction-level generalization, including across editing tasks and from single-task to multi-task settings, is more challenging than image-domain generalization, such as from synthetic to real-world images or from mosaicked to regular images. This suggests that the primary bottleneck lies in insufficient learning for diverse editing instructions rather than in the image domain gap. Motivated by this insight, we propose three strategies: (a) a Coverage-then-Realism Curriculum, a two-stage pipeline that first builds large-scale synthetic, instruction-rich data for broad task supervision, then curates a small set of real-world data to refine generation realism; (b) Multi-Task Mosaicking, which constructs multi-task training samples by concatenating single-task examples at nearly zero cost while enabling the learned capability to generalize to non-mosaicked images; and (c) an Edit-Focused Loss, which leverages the changed regions between input and output images in synthetic data to focus training on edited regions, improving both learning efficiency and editing accuracy. With these strategies, we substantially improve both single-task and multi-task scribble-guided editing on the VIBE benchmark, achieving state-of-the-art results. We will publicly release our dataset and model.
Authors: Yufeng Yang, Jianzhuang Liu, Jisheng Chu, Yuqi Peng, Xianfang Zeng, Jiancheng Huang, Shifeng Chen
Abstract: Existing deep learning-based low-light enhancement methods are typically trained on limited datasets with single enhancement targets, which restricts their generalization ability and controllability in real-world applications. To overcome these limitations, we propose ControlLight, a controllable, consistent, and generalizable framework for low-light enhancement. We first construct a large-scale dataset of real-world degraded images with continuous illumination-strength supervision. To further ensure consistent outputs under different control strengths, we introduce a misalignment-aware weighted flow matching loss that preserves image structure across continuous enhancement strengths. ControlLight allows users to edit real-world degraded low-light images toward satisfactory enhancement results by flexibly controlling the strength while preserving visual consistency and realism. Extensive experiments show that ControlLight achieves state-of-the-art performance against existing low-light enhancement approaches while demonstrating strong continuous controllability and generalization to real-world scenarios.
Authors: Rui Hu, Song Wu, Wen Yang, Jinjian Wu
Abstract: Estimating continuous optical flow is a fundamental yet challenging problem in dynamic visual perception. Event-based cameras, with microsecond latency and high dynamic range, capture brightness changes asynchronously, offering a unique opportunity to model motion with fine temporal precision. However, the scarcity of temporally dense ground-truth annotations limits the effectiveness of supervised learning, while contrast maximization (CM) frameworks, focused on sharpening the Image of Warped Events (IWE), often neglect temporal continuity and structural coherence, leading to distorted trajectories under complex motion. To overcome these challenges, we propose a hybrid-supervised framework for continuous-time optical flow estimation, grounded in the principle of Spatio-temporal Structural Consistency (STSC). This paradigm jointly enforces local structural stability and trajectory continuity, ensuring physically coherent motion across time. To further enhance representation and robustness, we design a bidirectionally complementary multi-scale architecture and employ a curriculum-guided hybrid training strategy, enabling a smooth transition from supervised point constraints to self-supervised manifold regularization. Comprehensive experiments across multiple benchmarks show that our method achieves state-of-the-art performance in both continuous-time and standard optical flow estimation, demonstrating the effectiveness of the proposed learning paradigm.
Authors: Zehao Wang, Yihan Zeng, Zidong Gong, Yuanfan Guo, Feng Zhu, Hongzhi Zhang, Wei Zhang, Wangmeng Zuo
Abstract: Post-training via Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) is crucial for enhancing reasoning in Multimodal Large Language Models (MLLMs), yet existing paradigms often reach a performance bottleneck due to the limitations of static data. While current methods leverage self-reflection or self-evolution to push these boundaries, they still suffer from cognitive drift and hallucinated reasoning paths caused by low-quality synthetic data. To address these challenges, we propose Anchor Evolution (AnE), a new paradigm that integrates truth-anchored data curation and model evolution, achieving faithful and steady performance gains at the reasoning frontier. Specifically, we propose Truth Anchor Expansion, which pinpoints the model failing frontier via trajectory rollouts and leverages ground-truth databases to retrieve high-fidelity anchors for faithful data curation. Subsequently, we introduce the Scaffold-Stripping Mechanism to internalize reasoning capabilities. This mechanism first anchors reasoning paths via scaffold-augmented supervision to mitigate the learning complexity and distribution drift of direct SFT on raw data, then leverages RL to strip the scaffold template, thereby effectively transitioning the reasoning paths into intrinsic model capabilities. Experimental results on multimodal reasoning benchmarks show that our method substantially advances the model performance frontier, improving the base model by 10.3\% across eight multimodal benchmarks and achieving state-of-the-art results. The code will be made publicly available.
Authors: Junseok Ko, Jungwoo Kim, Jong-Seok Lee
Abstract: Concept erasure has emerged as a key research direction for ensuring safe and ethical image synthesis in Text-to-Image (T2I) models. While existing studies have explored concept erasure across multiple concepts, they typically assume only a single target concept per image, a limitation increasingly exposed by modern flow-based T2I models, which can generate complex scenes with multiple concepts simultaneously. To address this gap, we introduce compositional multi-concept erasure, a new task that aims to simultaneously remove multiple target concepts within a single scene. We propose CoME-Bench, a benchmark for evaluating compositional multi-concept erasure, which covers both intra- and cross-category scenarios. We further propose Mosaic, a novel framework for multi-concept erasure in flow-based T2I models, which exploits the spatial locality of target concepts in the vector field by dynamically constructing concept-specific masks and selectively blending them without additional optimization. Extensive experiments demonstrate that Mosaic effectively removes multiple target concepts in complex compositional scenes while preserving non-target contexts.
Authors: Sisi Qiao, Yilin Yu, Tiecheng Lin, Yuhao Liu, Jiajia Sun, Xiaoling Li
Abstract: Purpose: Echo-planar imaging (EPI) in low-field (LF) and ultra-low-field MRI (ULF) suffers from severe Nyquist ghost artifacts due to odd-even k-space misalignment. This study develops a reference-free artifact correction pipeline that reduces reliance on conventional reference scans while achieving improved ghost suppression. Methods: Starting from the traditional reference-scan-based ghost artifact correction method, we first introduce a peak-alignment-based ghost artifact correction method to correct odd-even line displacement without reference data. To further reduce residual artifacts, an interpolation-and-resampling strategy is applied. The combined method was evaluated using EPI and diffusion-weighted EPI data in LF and ULF. Results: The proposed pipeline effectively mitigated Nyquist ghosts, improved structural continuity, and enhanced signal uniformity. Peak-alignment-based ghost artifact correction method alone provided comparable artifact suppression to reference-scan-based ghost artifact correction method, while interpolation and resampling further suppressed residual artifacts, enabling reliable visualization of brain structures under ULF conditions. Conclusion: A practical, reference-free correction pipeline is presented for LF and ULF EPI, combining peak-alignment-based ghost artifact correction method and interpolation-resampling to achieve efficient ghost suppression and expand the clinical applicability of low-field MRI systems, providing both theoretical guidance and practical experience for ULF EPI-based DWI imaging.
Authors: Yuanye Liu, Nannan Shi, Zhejia Zhang, Hanxiao Zhang, Boya Wang, Derong Yu, Nao Wang, Yuxin Jin, Yang Zhou, Kunhao Yuan, Siqi Wang, Lida Yang, Xu Qiao, Wentao Liu, Xuelei He, Xin Hong, Guoyan Zheng, Xin Chen, Guang-Zhong Yang, Le Zhang, Lei Li, Yuxin Shi, Xiahai Zhuang
Abstract: Despite years of methodological progress, how far AI has come in liver fibrosis staging has never been systematically evaluated under the heterogeneous, multi-center conditions that define clinical practice. To address this gap, we introduce LiFS, a large-scale dataset and benchmark derived from the MICCAI 2025 CARE-Liver challenge, comprising 610 patients across multiple centers and scanners with multi-sequence MRI. To the best of our knowledge, LiFS is the first benchmark providing complete gadoxetic acid-enhanced sequences with histopathology-confirmed annotations from diverse real-world scanners. Through systematic evaluation of 9 independently developed methods selected from 96 registered teams against in-cohort radiologist reference results, our findings address how far current AI has progressed toward clinical-level liver fibrosis staging from three complementary perspectives. First, against radiologists, the best AI methods were broadly comparable to the senior radiologist and significantly exceeded the junior radiologist in selected settings, while median AI performance generally approached junior-radiologist levels. Second, from a data perspective, cross-center heterogeneity, label imbalance, and contrast-enhanced sequence variability emerge as the dominant challenges for AI methods. Third, from a technical perspective, methodological design choices, including spatial registration, input dimensionality, multi-modal fusion strategy, and backbone architecture, appear to modulate cross-center robustness, although no single choice alone closes the gap. Overall, LiFS provides a rigorous real-world benchmark for positioning the current state of AI in liver fibrosis staging and for enabling future research on the key challenges that limit clinically reliable deployment.
Authors: Daiyun Shen, Shuojue Yang, Chang Han Low, Qian Li, Mengya Xu, Qi Dou, Yueming Jin
Abstract: Surgical instrument pose estimation provides crucial information for promising applications, including autonomous robotic surgery, skill assessment, and standardization of surgical workflow. However, this task remains highly challenging due to high precision requirements, frequent occlusions, textureless instruments, scarcity of depth information and very limited annotated data. These constraints often lead to unsatisfactory performance when employing general object pose estimation approaches to surgical scenarios. To address these issues, we first construct a new dataset SynSurg6D, to alleviate the data shortage in this task. We further propose SurfSurg6D, a dense-correspondence framework tailored for surgical instrument pose estimation. Experimental results on the SurgRIPE, EndoVis2018 and SurgPose datasets demonstrate that the introduction of our generated dataset SynSurg6D is able to diversify the pose distributions, thus enhancing the performance of existing approaches. Furthermore, SurfSurg6D outperforms existing methods, providing a robust solution for precise and efficient RGB-only pose estimation.
Authors: Yu Xia, Zhengbo Zhang, Shuaihu Zhang, Zhigang Tu
Abstract: UAV action recognition faces a deployment shift that standard benchmarks often obscure: a model trained on UAV footage captured from low-depression viewpoints may be required to recognize the same action classes from high-depression viewpoints. While the action labels remain unchanged, this shift alters body visibility, motion projection, and scene context, encouraging models to rely on viewpoint-specific shortcuts. We introduce UAV-OVO, an Out-of-Viewpoint generalization benchmark for UAV action recognition. UAV-OVO derives view scores from uncalibrated videos, uses a view-isolation band to assign low-depression videos to the training and in-distribution test splits while reserving high-depression videos for out-of-distribution testing, and constructs ID/OOD test sets matched by class distribution so that performance differences reflect viewpoint shift rather than label imbalance. Across representative video recognizers, UAV-OVO reveals a substantial ID/OOD gap: models that fit the low-depression training distribution well often fail to transfer to held-out high-depression views, exposing viewpoint shortcuts hidden by aggregate accuracy. We further propose LATER, LoRA-Anchored Test-time Re-centering, which first adapts the recognizer with Low-Rank Adaptation (LoRA) and then uses the learned LoRA subspace as a semantic anchor for online feature re-centering. Specifically, LATER projects target-domain displacement onto the orthogonal complement of the LoRA subspace before re-centering features, reducing viewpoint-induced drift while preserving task-relevant semantics. Together, UAV-OVO and LATER provide a controlled testbed and a practical adaptation method for viewpoint-robust UAV video understanding.
Authors: Ming Xie, Zizheng Huang, Xudong Tan, Chao Wang, Xiangyu Zeng, Wenxiao Wu, Tao Chen, Limin Wang, Yanwei Fu
Abstract: While streaming omni-video understanding demands continuous perception and proactive, real-time interaction, this crucial area remains largely under-explored. Current omni-modal methods are inherently designed for offline settings, limiting their applicability in streaming scenarios due to two fundamental flaws. First, they lack robust mechanisms to manage continuously growing audio-visual context over long horizons and cannot autonomously initiate responses at opportune moments. Second, existing benchmarks are predominantly confined to offline, single-turn question answering, failing to capture continuous, multi-turn streaming interactions. To bridge these gaps, we propose StreamOV, a novel Streaming Omni-Video understanding framework for efficient online audio-visual reasoning with bounded memory and proactive response triggering. Specifically, StreamOV introduces a multimodal evidence-guided long-short term memory that condenses historical audio-visual context into compact informative evidence under a fixed budget. It further employs a hidden-state-driven trigger to decide when to respond, avoiding explicit silence-token generation and external routers. We also curate SOVBench, the first comprehensive benchmark for online, multi-turn omni-modal evaluation. Extensive experiments show that StreamOV achieves state-of-the-art performance across diverse streaming and omni-video benchmarks, demonstrating its effectiveness for both online and offline video understanding.
Authors: Mingfeng Zha, Tianyu Li, Guoqing Wang, Yunqiang Pei, Chaofan Qiao, Jiening Zhang, Yang Yang, Heng Tao Shen
Abstract: Camouflaged object detection (COD) aims to localize targets that exhibit minimal perceptual differences from backgrounds through physical attributes. Existing methods, constrained by the static train-then-freeze paradigm, suffer from domain rigidity and annotation dependency, limiting their adaptability to scene variations and unseen camouflage patterns. To overcome these, we propose the hierarchical consistency learning (HCL) framework, which integrates test-time adaptation for dynamic representation recalibration. Specifically, we design the hierarchical representation reconstruction (HRR) to alleviate feature entanglement by synergizing spatial reconstruction with dual-stream frequency-domain decomposition, enhancing robustness against appearance homogenization. The pixel and spectrum inference provide structural and contextual priors. We further introduce task affinity guidance (TAG) to propagate knowledge across branches via channel-wise affinity, aligning local discriminative cues and mitigating semantic drift. To ensure semantic invariance, we formulate the prototype consistency calibration (PCC), which aggregates region features into compact prototypes and establishes prototype-feature similarity. This imposes implicit and hierarchical constraints that bridge task and representation gaps. Extensive experiments across four camouflaged and four underwater object benchmarks, under three degradation settings, demonstrate that our method consistently outperforms state-of-the-art approaches, highlighting its robustness and generalization under distribution shifts.
Authors: Ryotaro Ishida, Wataru Ikeda, Ryosei Hara, Akemi Kobayashi, Toshitaka Kimura, Mariko Isogawa
Abstract: Estimating the precise timing of batting impact is crucial for understanding the rapid sensorimotor control. However, this task is challenging for RGB cameras due to insufficient temporal resolution and motion blur. Similarly, Inertial Measurement Units (IMUs) are impractical for actual matches due to sensor intrusiveness and their limited temporal precision. To overcome these limitations, we propose a novel framework leveraging event-based cameras, which offer microsecond resolution and high dynamic range, to estimate impact timing based on the weighted centroid distance between the detected ball and bat. To address the domain gap between event frames and RGB images that degrades segmentation accuracy, we generate high-density event frames. We then introduce a mask refinement network that leverages these frames and bidirectional mask information, optimized using a novel loss function. Experiments on real-world datasets demonstrate that our method achieves superior accuracy under challenging conditions, including low-light environments and severe occlusions, outperforming baselines by reducing the Mean Absolute Error by approximately 63%.
Authors: VSS Tejaswi Abburi, Saurabh J. Shigwan, Nitin Kumar
Abstract: In biomedical and neurodegenerative disorders, accurate and early disease identification remains challenging due to the scarcity of labeled data and the complexity of imaging patterns. To address these challenges, we introduce ARMA-C3, a unified unsupervised and semi-supervised graph learning framework for node classification based on contrastive learning and graph-cut regularization to learn structurally meaningful and discriminative representations. By modeling samples or images as graph nodes and exploiting inter-sample relationships, the proposed framework captures subject-level dependencies that conventional machine learning methods typically overlook. We conduct extensive binary classification experiments across five clinically relevant datasets: the Alzheimer's Disease Neuroimaging Initiative (ADNI), the Neuroimaging in Frontotemporal Dementia (NIFD) dataset, and three medical imaging benchmarks (BreastMNIST, PneumoniaMNIST, and a liver ultrasound dataset). Experimental results demonstrate that ARMA-C3 achieves competitive and frequently superior performance compared to classical clustering techniques, state-of-the-art machine learning models, and existing graph-based deep learning approaches across multiple evaluation settings, particularly under limited supervision and severe class imbalance. The proposed framework further demonstrates robust representation learning and strong cross-modal generalization across diverse biomedical imaging modalities.
Authors: Linrui Tian, Qi Wang, Bang Zhang
Abstract: Real-time streaming joint audio-video generation for character animation requires a generator to speak the requested transcript, maintain visual identity across chunks, and run within a strict playback budget. These requirements are difficult to satisfy simultaneously: chunk-wise autoregressive generation can accumulate transcript-audio misalignment and visual drift, while the few-step distillation needed for low latency often degrades spatial diversity and temporal quality. We present StreamChar, a streaming framework that separates long-horizon orchestration from short-window audio-video denoising. An LLM-based orchestrator uses the transcript and historical context to produce frame-aligned audio conditions, and a joint audio-video DiT performs local bidirectional denoising with reference and motion-frame conditioning. For efficient deployment, we use a two-stage distillation pipeline that first compresses the sampler and then fine-tunes the student under online chunk rollouts. A progress-aware pointer aligns partial transcripts with generated audio during rollout training, and a sink-chunk memory provides a persistent visual anchor for reducing long-horizon drift. Experiments on short-clip and long-horizon protocols show that StreamChar runs in real time on a single H100 GPU and provides a favorable system-level trade-off among transcript fidelity, audio-visual synchronization, visual quality, and streaming stability compared with recent joint and audio-driven baselines.
Authors: Jaxon Zhang, Binxin Yang, Hubery Yin, Chen Li, Jing Lyu
Abstract: Current mainstream methods of aligning diffusion models with human preferences typically employ VLM-based reward models. However, these reward models, pre-trained for semantic alignment, struggle to capture the essential perceptual qualities-such as aesthetics, composition, and visual harmony. In this work, we argue that a model capable of high-fidelity generation must possess a profound understanding of these visual attributes. Based on this insight, we introduce the Diffusion-based Reward Model (DRM), a novel paradigm that use the pre-trained diffusion model as a powerful evaluative backbone. A key advantage of the DRM is its unique ability to assess not only the final image but also the noisy intermediate latents at any stage of the generative process. We leverage this step-wise evaluative capacity in two ways. First, we propose Step-wise GRPO, a reinforcement learning algorithm that provides dense, per-step rewards to resolve the imprecise credit assignment problem in GRPO algorithm, leading to more stable and effective alignment. Second, we introduce Step-wise Sampling, a novel inference strategy that employs the DRM as a dynamic guide to evaluate multiple generation paths at each step, steering the process towards higher-quality outcomes. Extensive experiments confirm that our approach significantly enhances the final quality of generated images. Code: https://github.com/jjaxonx/DRM.
Authors: Zongjian Wu, Lei Zhang
Abstract: Referring expression comprehension (REC) aims to localize a target object within an image based on a given expression. Although recent advances in vision-language models have led to substantial improvements in REC tasks, current REC benchmarks often hold simple scenarios and the assumption that each expression maps to a unique object. These limitations hinder the deployment of REC models in open-world environments. To fill this gap, we introduce OpenRef, a new benchmark for REC in complex visual and linguistic scenarios. OpenRef features three key advancements: 1) Diverse visual scenarios: spanning diverse visual domains, including ground views, drone views, dark scenes and adverse weather conditions; 2) Variable target counts: breaking the single-target limitation with multi-target and none-target samples; 3) Rich vocabulary types: incorporating proper nouns, polysemous words and ordinal terms to fit a wider range of expression needs. Furthermore, as traditional metrics are insufficient for open-world setting, we leverage F1 to measure grounding accuracy and propose N3R (Negative Relative Rejection Reliability) to assess relative rejection reliability against negative expressions. Finally, we introduce Multi-task Consistency Checker (MCC), a training-free but plug-and-play strategy that enhances model performance with one click by enforcing consistency self-verification. Extensive experiments demonstrate that this work significantly advances the performance of existing REC models in complex scenarios, paving the way for open-world REC. Project page: https://zongjianwu.github.io/openref
Authors: Sriram Mandalika
Abstract: Multi-domain task-incremental learning requires a model to sequentially acquire knowledge across visually diverse domains without forgetting prior tasks, and without access to task identity at inference. Parameter-efficient methods built on frozen vision-language models have made strong progress, yet all existing approaches rely exclusively on visual features for task routing, confidence estimation, and encoder adaptation, leaving CLIP's cross-modal text embedding space entirely unexploited. We address this gap through three contributions. Text-space task routing replaces visual Gaussian matching with cosine similarity to frozen CLIP text prototypes, giving order-independent routing robust to data scarcity at zero parameter cost. Multi-prototype visual-textual confidence replaces single-Gaussian class modeling with K-means visual prototypes and cross-modal alignment scores under task-calibrated thresholds. Symmetric cross-modal gating extends per-layer Gumbel gates to the text encoder conditioned on batch image features, preserving cross-modal alignment on out-of-distribution inputs. On the MTIL benchmark spanning 11 datasets and 1201 classes, our method achieves 74.2% Transfer, 80.5% Average, and 88.7% Last under Order-I, surpassing the prior state of the art by 5.0, 3.7, and 3.0 percentage points with only 2.5M trainable parameters and no external data.
Authors: Jinye Li (National Institute of Health Data Science, Peking University, Beijing, China, Institute of Medical Technology, Peking University, Beijing, China, Beijing University of Posts and Telecommunications, Beijing, China), Aidong Men (School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China), Yang Liu (Wangxuan Institute of Computer Technology, Peking University, Beijing, China), Qingchao Chen (National Institute of Health Data Science, Peking University, Beijing, China, Institute of Medical Technology, Peking University, Beijing, China, State Key Laboratory of General Artificial Intelligence, Peking University, Beijing, China)
Abstract: Cardiovascular diseases (CVDs) remain a leading cause of death globally, necessitating continuous, accurate non-invasive cardiac monitoring. While non-contact radar-based approaches show great promise, they often employ a single "distortion-driven" or "perception-driven" paradigm, frequently facing a trade-off between "low distortion but weak semantic information" and "high perceptual fidelity but poor interpretability." To address this, we propose a Three-stage Distortion-Perception Pre-Training Model (TriDP-PTM), a radar-based multi-scale fusion dual-path framework that systematically compares the "direct radar-to-task" path against an "indirect radar-to-ECG-to-task" path. By integrating an ECG generator with a feature discriminator to form a composite loss function, our approach effectively incorporates medical priors - such as ECG morphology and rhythm - into downstream tasks. Through empirical analysis, we reveal that this trade-off manifests in three distinct phases (Positive-Sum, Coopetitive, and Negative-Sum), showing optimal downstream clinical accuracy typically emerges in the coopetitive stage. Extensive experiments on a dataset involving 30 subjects across 5 physiological states reveal that the indirect path consistently outperforms the direct path in diverse tasks, achieving 0.80 mean IoU in waveform segmentation, 98.3% average classification accuracy across four tasks, and a 56% MAE reduction in blood pressure regression compared to the strongest baselines. These findings validate our framework and indicate that, within the indirect radar-to-ECG pathway, appropriately weighting distortion and perception losses to operate in the coopetitive regime is critical for achieving both clinically interpretable ECG morphology and strong downstream accuracy in non-contact cardiac monitoring.
Authors: H. M. Shadman Tabib, Md. Shamsuzzoha Bayzid, M Sohel Rahman
Abstract: Foundation segmentation models such as Segment Anything Model (SAM) are now routinely used in iterative pipelines, where each predicted mask is fed back as the next prompt. This practice turns segmentation into a closed-loop dynamical process, yet the decoder-level behavior of these systems remains largely unexamined. We show that this feedback loop can induce a previously overlooked failure mode, decoder coupling drift, in which the mask decoder's cross-attention progressively loses alignment with the target object, causing errors to accumulate across iterations. We study this phenomenon by instrumenting SAM's mask decoder and deriving ground-truth-free measures of prompt-image coupling, attention stability, and temporal consistency. On volumetric electron microscopy data, these decoder-internal signals reveal that standard iterative prompting systematically degrades attention alignment and temporal coherence relative to oracle-anchored feedback. We then formalize iterative prompting as a discrete-time dynamical system and show how proximal anchoring reduces error amplification in the feedback loop. Building on this analysis, we introduce DeCoDrift, a training-free inference-time stabilization framework that constrains prompt updates and preserves decoder coupling across iterations. Across extensive experiments, DeCoDrift consistently improves attention stability, temporal coherence, and segmentation quality over standard iterative prompting, without retraining or ground-truth supervision. More broadly, our results show that decoder-internal dynamics are not merely diagnostic: they provide actionable signals for stabilizing foundation segmentation models in closed-loop use.
Authors: Chuyu Zhong, Keyan Chen, Qinzhe Yang, Bowen Chen, Zhengxia Zou, Zhenwei Shi
Abstract: Pixel count and geographical coverage are two key characteristics of remote sensing images. Existing remote sensing image segmentation methods typically focus on images with either a small pixel count or a large pixel count but limited geographical coverage. In this paper, we introduce a novel segmentation task targeting ultra-wide area (UWA) remote sensing images, characterized by both a large pixel count and extremely wide geographical coverage. The core challenges of UWA segmentation lie in simultaneously handling ground objects with significantly varying scales and maintaining long-range contextual semantic continuity. To address these challenges, we propose the Scale-Frustum Representation Network (SFR-Net). Inspired by the viewing frustums of remote sensing images captured from different altitudes, we construct scale-frustum representations, enabling unified modeling of ground objects and contextual features at different scales. Furthermore, we design a cascaded cross-scale fusion mechanism to effectively integrate these representations, enhancing local semantic understanding while ensuring long-range contextual continuity. Experimental results on GID and FBPS demonstrate that SFR-Net achieves state-of-the-art performance, improving mIoU by 1.72% and 4.29%, respectively, over the strongest competing methods. In addition, the proposed scale-frustum representations can be integrated into generic segmentation networks to improve both segmentation accuracy and convergence speed. The implementation code will be publicly available at https://github.com/ChuyuZhong/SFR-Net.
Authors: Hongzhe Liao, Chuhua Xian, Hongmin Cai, Haiyang Liu, Fa-Ting Hong
Abstract: 3D Gaussian Splatting (3DGS) provides an efficient method for high-quality scene reconstruction using anisotropic Gaussians. Recently, 3DGS-based methods have significantly improved the rendering quality of human avatars while enabling real-time performance. However, existing methods suffer from a magnitude mismatch in the number of Gaussians generated by image-based and 3DMM-based approaches. This discrepancy results in reconstructed expressions that lack fine-grained detail. In this paper, we introduce a novel method for reconstructing an animatable head avatar from a single image. We propose a Graph splitting network to progressively generate Gaussians from coarse to fine using an autoregressive architecture. To address the graph inconsistency caused by split Gaussians, we employ a mesh topology extension method to align the GNN's connectivity with the increased Gaussian count. Furthermore, we introduce a novel density control method that includes a gating mechanism that generates soft masks for Gaussians, preventing over-densification after the splitting operation. This allows for dynamic control over Gaussian density across different facial regions. For smooth and rapid training, we employ a delayed filtering strategy to avoid re-computing the graph topology during training. Experimental results demonstrate that our autoregressive structure effectively improves expression representation ability by progressively splitting Gaussians. This process, enabled by the GNN-guided splitting, synthesizes more precise facial details and achieves higher reconstruction quality.
Authors: Suhyun Shin, Yunseong Moon, Ryota Maeda, David Lindell, Kyros Kutulacos, Seung-Hwan Baek
Abstract: Hyperspectral 3D imaging enables the capture of dense spectral information and scene geometry but has traditionally been confined to narrow spectral windows, typically the visible range. In this work, we introduce a broadband hyperspectral 3D imaging (BH3D) method to extend this capability across the full visible-near-infrared and short-wavelength infrared (SWIR) spectrum (450-1500 nm). This broad coverage is critical as it captures complementary physical cues: visible wavelengths reveal surface appearance, while SWIR bands provide insight into subsurface properties and material composition. However, realizing BH3D is challenging due to fundamental sensor constraints between visible-spectrum silicon and SWIR-spectrum InGaAs sensors, which necessitate complex multi-spectrograph designs. Here we propose a single-spectrograph BH3D system, using a stereo setup comprising visible and SWIR cameras, that reconstructs dense broadband hyperspectral reflectance together with accurate 3D geometry. Our key idea is to extend dispersed structured light to the broadband regime using a single spectrograph. We model the image formation of broadband dispersed structured light, and estimate hyperspectral reflectance and depth. We validate our approach on diverse real-world scenes, demonstrating accurate reconstruction with a mean spectral angle mapper of 0.13 rad, root mean square error of 0.03, and mean depth error of 4.5 mm. We further demonstrate identifying metameric materials, performing imaging through opaque layers, uncovering hidden features on banknotes, and revealing blood vessels.
Authors: Bao Li, Yuliang Xiu, Zhen Liu
Abstract: Large-scale text-to-image foundation models have achieved remarkable visual realism, yet generating human images with correct anatomical structures remains challenging. Existing approaches enforce anatomical constraints through part-specific modules or localized loss weighting during supervised fine-tuning on high-quality human photos, but such datasets are limited and often provide ambiguous optimization signals due to confounding factors such as lighting, pose, and background. Preference-based alignment offers an alternative, but standard Direct Preference Optimization (DPO) treats all pixels equally and therefore fails to exploit the localized nature of anatomical artifacts. To address this, we propose the framework of Alignment via Synthetic Anatomical Preference (ASAP), which constructs controlled preference pairs through a localized degradation mechanism applied to high-fidelity human images. This mechanism performs a controlled experiment on images by introducing explicit anatomical errors in targeted regions while preserving the remaining content. With this mechanism, we create the Human Anatomical Preference (HAP) dataset with over 10K curated pairs for effective anatomical alignment of text-to-image human image generative models. To better leverage the locality of these controlled preference pairs, we introduce a localized and margin-bounded variant of DPO that prioritizes optimization in targeted anatomical regions while enforcing a finite preference margin to prevent over-optimization and preserve global semantics. We further introduce HAF-Bench, a benchmark for systematic evaluation of anatomical fidelity. Extensive experiments demonstrate that ASAP consistently reduces anatomical errors across multiple foundation models while maintaining overall image quality.
Authors: Shipeng Cao, Biao Qian, Haipeng Liu, Yang Wang, Meng Wang
Abstract: Text-to-image synthesis has made significant progress, benefiting from the strong generative capabilities of diffusion models. However, these models struggle to achieve precise text-to-image alignment within cross-attention maps during the denoising process. Existing works primarily focus on inter-subject-token activations (i.e., cross-attention scores) overlap for different subjects, overlooking the intra-subject-token activations scattering issue for identical subjects. In this paper, we propose an Aggregating-and-Isolating cross-attention approach to diffusion models for Text-to-Image synthesis, dubbed AI-T2I. Technically, to address the scattering issue, we devise an aggregation loss to identify and consolidate the scattered intra-token activations, which implicitly helps mitigate the potential overlap issue. Upon that, an isolation loss is further introduced to push the inter-token activations apart, thus fulfilling precise text-to-image alignment. Extensive experiments on various benchmarks demonstrate the superiority of AI-T2I over the state-of-the-art works for text-to-image synthesis. Furthermore, our AI-T2I exhibits excellent generalization across other tasks, e.g., controllable layout generation and personalized generation.
Authors: Bokai Zhao, Yiyang Zhang, Yuanchi Zhu, Hanqing Chao, Long Bai, Tai Ma, Minfeng Xu, Ming Song, Tianzi Jiang
Abstract: Pathology foundation models (PFMs) have emerged as a core approach for learning transferable representations from whole slide images (WSIs), and they are typically benchmarked through downstream clinical endpoints. While such task level evaluations are indispensable, they offer limited insight into what the representations themselves encode, particularly whether PFM embeddings can distinguish meaningful tissue regions and capture their spatial relationships. We present SpaPath-Bench, a representation level benchmark designed to diagnose spatial representation capability in PFMs. SpaPath-Bench formulates spatial domain identification (SDI) on paired whole slide image and spatial transcriptomics (ST) data as a diagnostic task. It curates 42 public paired WSI and ST slides, enables large scale evaluation across 19 encoders and seven SDI methods, and measures partition quality using three complementary criteria: unsupervised spatial coherence, transcriptomics referenced agreement, and expert referenced agreement. Across 83K runs, SpaPath-Bench reveals that different pretraining paradigms capture distinct aspects of tissue spatial architecture, and it provides practical guidance for building the next generation of spatially aware computational pathology models. Code and data pipelines are publicly available at https://bokai-zhao.github.io/SpaPath-benchboard/.
Authors: Saemi Moon, Suhyeon Jun, Seoyeon Lee, Dongwoo Kim
Abstract: Concept unlearning aims to erase a target concept from a pretrained text-to-image diffusion model without retraining. Closed-form methods are attractive in this setting because they apply a single deterministic edit to the cross-attention weights and add no inference-time cost. Existing closed-form methods, however, represent the target concept through the text encoder's response to a few short anchor prompts that name it, and paraphrased prompts that evoke the concept without naming it consistently bypass the edit. We argue that the target should instead be represented in the cross-attention activation space. Text embeddings describe the user's prompt, while cross-attention activations describe what the model is about to render, and the latter generalize to paraphrase the anchor templates do not cover. Building on this observation, we propose PURE (Projection in U-Net Rendering for Erasure), a closed-form method that builds the forget and retain bases from per-layer cross-attention activations captured along a short denoising trajectory and applies a single linear projector to the cross-attention key and value weights. On a recent holistic concept-unlearning benchmark covering ten concepts across artistic style, intellectual property, celebrity, and NSFW categories, PURE significantly reduces target leakage under paraphrased and adversarial prompts while preserving retain concepts close to the unedited model, yielding the best overall forget-retain trade-off among evaluated methods.
Authors: Tianyu Zhang, Xinglong Liang, Jarek van Dijk, Luyi Han, Chunyao Lu, Antonio Portaluri, Xinghe Xie, Yaofei Duan, Nika Rasoolzadeh, Xin Wang, Yuan Gao, Muzhen He, Yue Sun, Jonas Teuwen, Tao Tan, Ritse Mann
Abstract: Synthesizing high fidelity contrast enhanced MRI is clinically valuable for safer and more efficient breast cancer screening, yet remains challenging due to complex lesion textures and heterogeneous enhancement patterns.
Authors: Xingyuan Li, Haoyuan Xu, Shulin Li, Xiang Chen, Zhiying Jiang, Jinyuan Liu
Abstract: Infrared and visible video fusion is essential for achieving comprehensive perception in dynamic scenes. However, maintaining temporal consistency remains a formidable challenge. Conventional methods relying on optical flow often suffer from geometric rigidity and ghosting artifacts. Moreover, standard diffusion-based fusion models typically operate in a frame-by-frame manner; when extended to autoregressive settings, they lack intrinsic temporal constraints and are prone to severe error accumulation and drifting, where minor artifacts amplify over time. To address these limitations, we propose a drift-resilient video fusion method that reformulates the task as history-conditioned motion generation. We introduce Stabilized History Guidance and Soft Temporal Anchoring to reframe temporal consistency as spectral filtering, implicitly aggregating motion dynamics without rigid alignment. Furthermore, our Decoupled Structure-Motion Adaptation strategy bridges pre-trained priors and structural constraints via two-stage training and latent refinement. Extensive experiments demonstrate that our method achieves state-of-the-art performance in both fusion quality and temporal stability.
Authors: Zitong Xiao, Yuda Qiu, Zisheng Ye, Xiaoguang Han
Abstract: We propose OMGTex, an end-to-end diffusion-based framework for reconstructing high-quality and editable facial UV textures from multi-style facial images. Existing texture reconstruction methods face two major limitations: (1) Fragility due to reliance on 3D geometry priors, which are difficult to estimate accurately, especially under facial occlusions or in stylized domains; and (2) A lack of semantic disentanglement, inhibiting region-specific texture editing and style transfer. Our work addresses both challenges simultaneously. Our core innovation is a geometry-free pipeline that directly maps a 2D face image to its corresponding editable UV texture. We introduce two key techniques: First, to address the challenge of UV misalignment common in diffusion generation, we introduce a gradient-guided refinement strategy at inference time, which explicitly corrects structural consistency. Second, we leverage the inherent semantic distribution capability of diffusion models and design a novel training paradigm to enhance this tendency, enabling semantic-aware editing of facial texture. Furthermore, to address the data scarcity in multi-style texture reconstruction, we construct CANVAS, the first comprehensive paired texture reconstruction dataset covering realistic and diverse stylized domains. To the best of our knowledge, OMGTex is the first geometry-free inference framework that achieves robust, style-consistent, and editable facial texture reconstruction across diverse domains. Our method achieves state-of-the-art performance on multiple facial texture benchmarks.
Authors: Jing Huang, Duanchu Wang, Junjie Yang, Zihang Cheng, Cheng Li, Lin Cui, Zhouyi Wu, Di Wang
Abstract: Multimodal Large Language Models (MLLMs) have recently shown promising progress in geospatial reasoning. However, existing remote sensing benchmarks remain largely 2D-centric, evaluating models primarily on optical appearance. In natural environments, this paradigm breaks down due to severe spectral confusion, where ecologically distinct regions share similar textures but differ fundamentally in vertical structure. In such cases, explicit 3D structural data, such as Canopy Height Models (CHMs), become essential geometric evidence for semantic disambiguation. Yet, it remains unclear whether current MLLMs can genuinely leverage vertical cues to resolve appearance-level ambiguity. To address this gap, we introduce VertiCue-Bench, the first diagnostic benchmark for CHM-grounded geospatial reasoning. VertiCue-Bench comprises 1,534 carefully curated instances across 17 tasks, explicitly disentangling low-level height perception from ambiguity-aware semantic reasoning. Evaluations on 14 state-of-the-art general and remote-sensing-specialized MLLMs, combined with counterfactual modality testing, reveal a striking perception-reasoning dissociation. While models exhibit emerging competence in reading raw CHM height cues, they largely fail to translate geometric perception into reliable semantic reasoning, often underperforming RGB-only baselines when joint constraints are required. Overall, VertiCue-Bench exposes a critical geometry-to-semantics gap in natural scene understanding, offering actionable insights for advancing geospatial MLLMs.
Authors: Shuai Yi, Yixiong Zou, Yuhua Li, Ruixuan Li
Abstract: Vision-language models (VLMs) like CLIP have shown impressive generalization capabilities, yet their potential for Cross-Domain Few-Shot Learning (CDFSL) remains underexplored, where the model needs to transfer source-domain information to target domains with scarce training data. While the attention sink phenomenon has been observed in VLMs for certain tasks, its role in CDFSL scenarios has not been studied. In this paper, we uncover a critical issue overlooked by prior works: standard target-domain few-shot fine-tuning in CDFSL significantly exacerbates the attention sink problem, leading to poor discriminability across classes. To understand this phenomenon, through extensive experiments, we interpret it as the model's shortcut learning for domain adaptation: to overcome the huge domain gap between the source and target domains, the model shows a high tendency to push tokens that are initially closer to target-domain classes (i.e., simple tokens) to be even closer to these classes, exacerbating the attention sink and wasting the capability of learning other discriminative but initially further tokens (i.e., hard tokens). To address this, we propose a novel approach to dynamically re-weight tokens according to their relevance with target-domain classes during the target-domain finetuning, which explicitly suppresses the model's reliance on these simple tokens and enhances the learning of hard tokens, reducing sink tokens and enhancing discriminability. Extensive experiments on four benchmark datasets validate the rationale of our method, demonstrating new state-of-the-art performance. Our codes are available at https://github.com/shuaiyi308/TIR.
Authors: Wenxue Li, Jingjing Ren, Peng Zhang, Tian Ye, Daiguo Zhou, Jian Luan, Lei Zhu
Abstract: High-resolution video generation faces a coupled bottleneck of optimization instability and prohibitive computational costs. The massive expansion of the token sequence not only biases optimization toward local textures at the expense of global coherence, leading to structural collapse, but also imposes prohibitive training costs and severe inference latency. To address this, we propose PixelWizard, a framework that hierarchically decouples global structure modeling from fine-grained detail synthesis. PixelWizard first establishes a compact spatiotemporal anchor to concentrate dense structural priors, which then guides fine-grained generation at high resolution. This mitigates the local optimization bias to ensure structural stability without compromising high-frequency details. Leveraging this structural stability, we introduce Noise-Span Aligned Shortcut Training to break the inference bottleneck. By explicitly modeling the step size, this mechanism allows the model to traverse the generation trajectory with large steps. Crucially, we incorporate Exponential Index-Biased Sampling and Adaptive Noise-Span Calibration to align optimization with the shifted noise schedules of high-resolution grids, ensuring robust few-step inference without incurring the heavy overhead of distillation. Extensive experiments demonstrate that PixelWizard achieves superior visual quality while accelerating the generative sampling of native 2K/4K videos by over 10x.
Authors: Weifeng Lin, Siyuan Huang, Hao Li, Tingwei Chen, Ruichuan An, Xinyu Wei, Jianbo Liu, Hongsheng Li
Abstract: Vision-Language-Action (VLA) models widely adopt pretrained Vision-Language Models (VLMs) as policy backbones, yet it remains unclear what kind of pretrained VLM representation is useful as a VLA initialization. In this paper, we study VLA initialization as a controlled representation-design problem along three axes: capability-level embodied VQA supervision, parameter-update strategy, and robot-data pretraining. Our experiments show that the original pretrained VLM representation is a key source of action performance. However, embodied VQA adaptation does not yield uniform gains: its benefit depends on downstream bottlenecks, and gains from different capability domains are not simply additive. For update strategy, LoRA provides a more reliable initialization than Full Finetune, indicating that overly reshaping the pretrained representation can weaken VLA initialization. Robot-data pretraining further improves VLA initialization, with the strongest variant obtained by staged LoRA-based training. Together, these findings suggest that effective VLM-to-VLA adaptation should inject action-relevant embodied and robot-trajectory signals while preserving the pretrained VLM representation that remains useful for action learning.
Authors: Hsin-Jui Pan, Sheng-Wei Chan, Meng-Qian Li, Chun-Po Shen
Abstract: Recent semantic segmentation research has increasingly moved toward stronger context modeling, dense attention, and transformer-based architectures. Although these models achieve impressive performance, classical CNN-based segmentation pipelines remain attractive because of their simplicity, efficiency, and ease of implementation. This paper revisits a practical question: how far can a ResNet-based segmentation model be improved by only modifying the segmentation head? We propose ATV-Net, an Adaptive Triple-View Network that strengthens a ResNet-101 backbone using three simple but complementary receptive-field views. The micro view captures point-wise semantic responses, the local view models neighborhood structures and object boundaries, and the scout view provides enlarged contextual cues. Instead of fusing these views with fixed weights, ATV-Net introduces an Adaptive Decision Gate that dynamically selects receptive-field responses according to input scene characteristics. A compact global coordination layer is further applied to improve spatial and semantic consistency. Experiments on the Cityscapes validation set show that ATV-Net achieves 80.31\% mIoU. This result suggests that classical CNN-based segmentation is still far from obsolete: with simple receptive-field views and adaptive fusion, a ResNet-based pipeline can reach a competitive accuracy level without relying on transformer-style global attention or overly complex context modules.
Authors: Ramna Maqsood, Paulo Nunes, Lu\'is Ducla Soares, Caroline Conti
Abstract: Event cameras offer significant advantages over conventional frame-based counterparts, including high temporal resolution, low latency, and energy efficiency. These characteristics make them suitable for high-speed and high-dynamic range scene acquisition scenarios; however, the lack of dense intensity frames limits the direct applicability of conventional computer vision methods for scene understanding. Event-to-video (E2V) reconstruction seeks to bridge this gap by converting asynchronous event streams into a sequence of synchronous video frames. Existing E2V reconstruction methods based on convolutional neural networks and transformers operate primarily in the spatial domain and often struggle to recover fine structural details while suppressing severe reconstruction artifacts. To address these issues, we propose MSFET-E2V, a novel multiscale frequency-enhanced transformer model. At its core lies a cross-domain attention module, which fuses spatio-temporal features with frequency-aware representations derived from the discrete wavelet transform. Unlike prior methods relying solely on spatial attention, our approach effectively captures both local and global structures by taking into account low- and high-frequency components, enhancing detail preservation and robustness across various motion scenarios. Furthermore, we propose a lightweight wavelet-enhanced skip block that serves as a skip connection, facilitating artifact suppression and structural detail refinement through joint spatial-frequency domain processing. Extensive experiments demonstrate that MSFET-E2V achieves superior performance over state-of-the-art methods on multiple real-world event datasets, offering significant gains in reconstruction quality. Moreover, compared to the existing transformer-based method, our proposed model significantly reduces the number of parameters, the GPU memory usage, and inference time.
Authors: Sangeeta, Maddikuntla Sai Prajwal, Debi Prosad Dogra, Kamalakar Vijay Thakare, Hyungjoo Jung, Ig-Jae Kim, Heeseung Choi
Abstract: Women's safety and security are paramount for a modern society. Crimes against women occur in daylight as well as in low-light conditions. Often, such events are captured through real-world surveillance cameras that operate at lower resolutions. Despite substantial progress in CV-related research, video anomaly detection (VAD) focused on women's safety has not yet been adequately addressed. Existing video anomaly datasets contain well-lit, high-resolution, close-shot videos, and fail to represent women-centric anomalies such as chain snatching, stalking, inappropriate touch, and other subtle forms of crime against women. To address these problems, we propose the ExtrAnom dataset, a new multi-modal benchmark containing 1001 videos with textual descriptions, 500 normal and 501 anomalous, classified into 5 different types of women-centric crimes. The dataset comprises low-light (8%), low-resolution videos (13%), long-shot (15%), along with daylight (64%) anomalous videos. And it covers anomalous events like stalking (3.9%), chain snatching (17.6%), kidnapping (7.3%), assassinations (2.3%), harassment (18.9%), and normal (50%). Each video is supplemented with 4 textual annotations, including one human-generated and three LLM-generated descriptions, enabling cross-modal and VLM-based validations. The aim of creating a women-centric dataset is to accurately detect the women-centric anomaly patterns, which are possible to observe visually. The dataset supplements the VLMs to accurately generate video-level descriptions. ExtrAnom has been benchmarked against popular unimodal and multi-modal VAD datasets (e.g., XD-Violence, UCF-Crime, and UCA) and SOTA methods. Experiments reveal that the existing datasets are insufficient to train models for detecting women-centric anomalies.
Authors: Xiaohan Liu, Yilin Wen, Yusuke Sugano
Abstract: We present the first data-driven approach to model temporal gaze-head coordination from large-scale in-the-wild facial videos. To obtain training data for generalizable learning, we propose an automatic pipeline that extracts natural yet diverse gaze and head motions with off-the-shelf appearance-based gaze estimators. To capture the probabilistic correlation and temporal dynamics of gaze-head coordination, we build our model on a generative conditional Variational Autoencoder for plausible yet diverse gaze-conditioned head motion generations. We further apply our framework to gaze-controlled facial video generation, where we enable video generation with natural and realistic head motion correlated to the input gaze - an aspect that has not been emphasized before. Human evaluation and quantitative comparisons demonstrate our method's effectiveness and validate our design choices, with evaluators showing statistically significant preference for our approach over baseline methods.
Authors: Akang Wang, Xili Deng, Zhanxuan Hu, Yi Zhao, Yonghang Tai, Huafeng Li
Abstract: Vision-Language Models such as CLIP exhibit strong zero-shot recognition capability by aligning images with textual concepts, yet they often underperform on multi-label recognition where multiple objects co-exist. A key bottleneck is that the [CLS] token, as a single global visual representation, is insufficient to faithfully encode diverse targets with varying scales, contexts, and co-occurrence patterns. To address this limitation, we present a new multi-label image recognition framework, termed PIAA, which formulates prediction as Patch-level Inference followed by Adaptive Aggregation. Specifically, we first enhance patch-wise predictions from two complementary perspectives: (i) mitigating semantic entanglement in the visual encoder to obtain more discriminative patch representations, and (ii) learning an unsupervised visual classifier to narrow the vision-language modality gap. We then introduce an adaptive aggregation module that consolidates patch-level scores into the final multi-label prediction. Notably, the entire pipeline is fully training-free, requiring no gradient updates or parameter fine-tuning. Experiments show that our method achieves strong improvements with minimal extra computation, exceeding a 6% mAP gain on the challenging NUS-WIDE benchmark over representative baselines. Code is available at https://github.com/akang-wang/PIAA.
Authors: Marcos Vinicius Mendes Faria, Thiago Borges Pereira, Isabella C. F. S. Condotta, Thiago Meireles Paix\~ao, Francisco de Assis Boldt
Abstract: Deep learning-based object detection has revolutionized Precision Livestock Farming (PLF), yet a critical barrier remains: high-performance Foundation Models (such as SAM 3) are too computationally intensive for edge deployment, while lightweight models (like YOLO) require prohibitive manual annotation efforts. This work proposes a fully automated knowledge distillation pipeline that leverages the Segment Anything Model 3 (SAM 3) to generate zero-shot pseudo-labels for training efficient YOLOv8 detectors. By treating SAM 3 as an offline auto-annotator, we eliminate the manual labeling bottleneck, producing models capable of real-time inference on resource-constrained hardware. We systematically evaluate this approach on the PigLife dataset, comparing SAM 3-supervised models against human-annotated baselines. Results demonstrate that a SAM 3-trained YOLOv8m achieves a mean Average Precision (mAP) of 79.4% without human intervention, while reducing inference latency by approximately 200$\times$ compared to the teacher model. Furthermore, stratified analysis reveals that in low-occlusion scenarios, the automated pipeline achieves detection rates comparable to human benchmarks ($AP_{50} > 99\%$). These findings indicate that foundation models can serve as effective, zero-annotation-cost supervisors, enabling scalable edge computing solutions for smart agriculture.
Authors: Yunqi Gao, Leyuan Liu, Yuhan Li, Changxin Gao, Jingying Chen
Abstract: 3D human mesh recovery and 3D clothed human reconstruction are inherently related, yet they have long been studied in isolation, thereby overlooking the potential gains of joint optimization. To overcome this limitation, we propose to address these two tasks within a unified framework, which allows their mutual dependencies to be effectively exploited. Building on this idea, we propose MuNet, a mutualistic network for joint 3D human mesh recovery and 3D clothed human reconstruction from single images. First, we adopt 2-manifold graphs as a unified representation for all 3D models, enabling consistent modeling across 3D human mesh recovery and clothed human reconstruction. Second, we design an end-to-end graph convolutional network that progressively deforms an initial graph into a 3D human mesh and refines it into a detailed 3D clothed human model. Third, we introduce a mutualistic mechanism that allows reciprocal interaction between the two tasks {during training}, where 3D human mesh recovery provides guidance for 3D clothed human reconstruction, and reconstruction feedback refines the 3D human mesh recovery. We extensively evaluate MuNet on six benchmark datasets for 3D human mesh recovery and 3D clothed human reconstruction, including Human3.6M, 3DPW, MPI-INF-3DHP, THuman2.0, CAPE, and RenderPeople. Experimental results demonstrate that MuNet achieves state-of-the-art performance on both tasks across all datasets. The code of MuNet is released for research purposes at https://github.com/starVisionTeam/MuNet.
Authors: Kaining Ying, Hengrui Hu, Siyu Ren, Jiamu Li, Fengjiao Chen, Ziwen Wang, Xuezhi Cao, Xunliang Cai, Henghui Ding
Abstract: Interactive world models are advancing rapidly, yet existing benchmarks cover only part of the required competencies, leaving no unified standard for systematic evaluation. To fill this gap, we introduce WBench, a comprehensive multi-turn benchmark for interactive world model evaluation along five dimensions, namely video quality, setting adherence, interaction adherence, consistency, and physics compliance. WBench contains 289 test cases and 1,058 interaction turns, where each case specifies a world setting and a multi-turn interaction sequence, covering diverse scenes, styles, subjects, and both first- and third-person perspectives, together with four interaction types, including navigation, subject action, event editing, and perspective switching. For navigation, WBench unifies text, 6-DoF pose, and discrete-action control, enabling evaluation of models with different native input interfaces. Evaluation uses 22 automatic sub-metrics that combine specialist vision models with large multimodal models, and all metrics are validated against human judgments. Across 20 state-of-the-art models, we find that no single model performs strongly across all dimensions. We provide detailed diagnostic insights into the characteristic strengths, weaknesses, and open challenges of each model. Code and data are available at https://github.com/meituan-longcat/WBench.
Authors: Jiaying Qian, Ziheng Jia, Qian Zhang, Zicheng Zhang, Jiayi Guo, Junqi Zhang, Guangtao Zhai, Xiongkuo Min
Abstract: With the continued advancement of text-to-image (T2I) generation, producing high-quality images is becoming increasingly attainable; consequently, user demands are shifting toward images that better satisfy their specific requirements. As reward models play an increasingly important role in assessing whether generated images align with user preference, this trend introduces an important challenge for reward modeling: rather than relying solely on static and general evaluation dimensions, reward models should account for the task-relevant and fine-grained criteria through which users assess whether generated images meet their specific requirements. To address this challenge, we propose DyCoRM, a dynamic, criterion-aware reward model that grounds task-relevant criteria and performs criterion-aware preference comparison. To support this setting, we construct DyCoDataset-20K, which provides dynamic criteria together with criterion-level annotations, and further derive DyCoBench-1K, a benchmark for systematically evaluating reward models under dynamic criteria. We further introduce DyCoPick, which applies criterion-aware reward modeling to selecting T2I images. Our contributions establish the first reward modeling framework for dynamic and fine-grained evaluation and practical application in T2I generation.
Authors: Wenbin Zou, Yawen Cui, Yi Wang, Lap-Pui Chau, Liang Chen, Jinshan Pan, Huiping Zhuang, Guanbin Li
Abstract: State space models (SSMs) have emerged as a powerful paradigm for efficient single-image super-resolution (SR) due to their linear complexity and long-range modeling capabilities. However, existing Mamba-based methods typically rely on data-agnostic rigid scanning, which reshapes 2D images into 1D sequences over a fixed grid, inevitably disrupting spatial-semantic topology and introducing artifacts. Inspired by the \textbf{Gestalt perceptual grouping theory}, we propose \textbf{SP-MoMamba}, a superpixel-driven mixture of state space experts designed for content-aware SR. Our core idea is to transform the traditional rigid scanning into a \textbf{semantic-level interaction} by treating superpixels as fundamental units. Specifically, we introduce the \textbf{Superpixel-driven State Space Model (SP-SSM)}, which compresses semantically homogeneous regions into high-order tokens to preserve global topological consistency. To address the conflict between fixed scanning scales and diverse semantic granularities, we develop the \textbf{Multi-Scale Superpixel Mixture of State Space Experts (MSS-MoE)}. This module utilizes a dynamic routing mechanism to adaptively assign scale-specific experts, effectively capturing multi-scale textures while reducing computational redundancy. Furthermore, to prevent the loss of high-frequency details during global abstraction, we introduce a \textbf{Local Spatial Modulation Expert (LSME)} to complement the global modeling, ensuring a precise reconstruction of sharp edges and fine structures. Extensive experiments on standard benchmarks demonstrate that SP-MoMamba achieves superior reconstruction fidelity and a more favorable efficiency-performance trade-off compared to state-of-the-art efficient SR methods.
Authors: Cuong Huynh, Maxim Popov, Denis Gridusov, Sergey Kolyubin
Abstract: 3D Visual Grounding (3DVG) is an essential capability for embodied AI, requiring agents to localize objects in 3D scenes based on natural language descriptions. Recent zero-shot methods leverage 2D vision-language models (LVLMs). However, they often rely on existing sets of multi-view images and struggle with the limited semantic and spatial details provided by standard 3D segmentation tools. We present $\textbf{AgentGrounder}$, a zero-shot 3D visual grounding framework that operates directly on colored point clouds without task-specific 3D training. Our approach follows a two-stage design: (1) an offline stage that applies 3D model to build an Object Lookup Table (OLT) with instance IDs, semantic labels, 3D bounding boxes; and (2) an online tool-driven agent that decomposes each query, retrieves only relevant candidates from the OLT, performs geometric scoring, and triggers image rendering on demand when additional visual evidence (e.g., color, material, or viewpoint-sensitive cues) is required. Compared with fixed anchor-target matching pipelines, this design reduces cascading matching errors and improves context-window efficiency by avoiding prompts overloaded with irrelevant objects. We evaluate on ScanRefer and Nr3D under a zero-shot setting and observe consistent improvements over SeeGround in our setup, including +2.5% Acc@0.5 on ScanRefer and +6.3% on Nr3D, with a notable +6.3% gain on Nr3D view-independent queries. These results show that combining selective retrieval, geometric reasoning, and adaptive visual inspection yields a practical and robust foundation for open-vocabulary 3D grounding. Our code is available at https://github.com/be2rlab/AgentGrounder.
Authors: Denis Gridusov, Maxim Popov, Sergey Kolyubin
Abstract: Reconstructing and predicting dynamic 3D scenes from multi-view videos is a foundational task for robotics, AR/VR, and digital twins. Recent physics-informed Gaussian Splatting methods achieve impressive future frame extrapolation but lack semantic awareness and suffer from large computational overhead. We introduce $\textbf{R5DGS}$, a framework that augments a physics-driven 4D Gaussian representation with compact Identity Encoding vectors, enabling precise Gaussian-to-object association. By constructing an offline CLIP-based object lookup table, we support open-vocabulary text prompting to retrieve and render object-specific Gaussians across arbitrary timestamps and viewpoints. Furthermore, we propose a rigid-body inference constraint that predicts and integrates physical dynamics exclusively for object centroids, propagating motion to associated Gaussians via relative transformations. This optimization yields a 11 FPS speedup during extrapolation without compromising trajectories plausibility.
Authors: Xiao Liu, Jiaxiang Liu, Boci Peng, Boren Hu, Yusong Wang, Xiwen Chen, Prayag Tiwari, Liming Zhang, Mingkun Xu
Abstract: Vision Language Models adapt well to downstream tasks but are highly vulnerable to adversarial perturbations that disrupt cross-modal semantic alignment. Existing defenses are largely unidirectional or structural, failing to exploit bidirectional cross-modal complementarity and instance-wise adaptive protection. To overcome the limitations of unidirectional and static defenses in adversarial settings, we propose Closed-Loop Bidirectional Prompting, casting robust adaptation as cross-modal agreement recovery via a dynamic feedback loop on frozen encoders. A Semantic Anchor is introduced as a stable prior to constrain cyclic updates and mitigate perturbation-induced feature corruption. Through anchor-based bootstrapping, textual semantics denoise visual representations, while the refined visuals enable instance-adaptive prompt updating, yielding a rectified and robust consensus. Extensive evaluations across 11 datasets validate state-of-the-art robustness and strong base-to-new generalization, while maintaining a favorable trade-off between computational cost and accuracy.
Authors: Yiwei Xie, Ping Liu, Zheng Zhang
Abstract: Text-to-video diffusion transformers encode semantic information unevenly across model depth, which constrains effective concept erasure. We identify a representational bottleneck, termed concept-layer topological alignment, under which target concepts exhibit higher separability at certain representational depths. Outside these depths, concept and non-target signals remain strongly entangled, limiting the effectiveness of depth-specific erasure. This observation reframes concept erasure as the problem of identifying representational depths where concept-non-target separation naturally emerges. Motivated by this structural constraint, we introduce CLEAR, a separability-driven optimization framework for concept erasure that explicitly enforces concept-layer alignment. CLEAR operationalizes this principle by formulating layer selection as an optimization problem over concept-non-target separability, rather than relying on layer-agnostic or heuristic choices. To enable this, we introduce a separability-aware objective that favors layers exhibiting stronger concept-non-target separation. Experiments on large-scale text-to-video diffusion models demonstrate that enforcing concept--layer alignment leads to more precise concept suppression while preserving overall generative quality.
Authors: Knut Peterson, Zaid Mayers, Azmain Yousuf, Priontu Chowdhury, Asher Zaczepinski, Solmaz Arezoomandan, Reihaneh Maarefdoust, David Han
Abstract: Unmanned Aerial Vehicles (UAVs) have quickly become common in various airspaces, representing a wide range of applications from recreation flying to commercial photography and package delivery. With the increasing prevalence of UAVs, it becomes critical that both manned and unmanned aircraft can detect UAVs and other flying objects from long range to effectively track movement and ensure safe operation in shared spaces. While several datasets have been introduced for drone detection, the need for expanded high-quality data persists, especially in the area of high-resolution long-range drone data. To address this, we introduce a high-resolution dataset of 102,532 long-range RGB images of drones, sampled at 5 FPS from 128 distinct video clips taken mid flight during 17 different data collection days spread over 8 months to ensure a wide variety of lighting scenarios, flight locations, and background elements. The dataset boasts comprehensive drone range information across the dataset, as well as 29,630 IR images, all paired with RGB counterparts from the base dataset. As one of the first drone detection datasets to leverage 4K image resolution and paired 640x512 IR images, our work represents a significant advancement to enable the detection of drones at long range. For access to the complete dataset, please visit https://research.coe.drexel.edu/ece/imaple/lrddv3/
Authors: Ruiqiang Xiao, Zhaohu Xing, Yijun Yang, Zhenyan Han, Weiming Wang, Kaishun Wu, Lei Zhu
Abstract: Ultrasound video segmentation is clinically valuable yet difficult due to speckle noise, weak boundaries, and rapid anatomical deformation. Recent promptable foundation models enable point-guided segmentation, but their direct deployment in ultrasound remains unreliable: a single point provides insufficient spatial context to resolve scale ambiguity, and greedy memory updates amplify early errors into severe temporal drift. We present EchoPilot, a training-free framework for ultrasound video segmentation under sparse first-frame interaction, requiring only a single point click and an anatomical category name. EchoPilot orchestrates a frozen medical vision-language model (VLM) for semantic localization, a vision foundation model (VFM) for dense geometric feature extraction, and a promptable video segmentor for mask prediction and propagation. To resolve initialization ambiguity, we propose Scale-Space Semantic Prompting, which first selects an optimal contextual view via a parameter-free S.E.E.D. (Semantic Energy-Entropy Density) criterion, and then synthesizes geometrically precise auxiliary point prompts from dense foundation features without additional user interaction. To reduce propagation drift, a Reliability-Gated Memory update is further introduced to selectively freeze the segmentor's memory bank under uncertain predictions, preventing error accumulation. We also contribute the first dynamic fetal placenta ultrasound video segmentation dataset with 671 annotated frames. Across three ultrasound video datasets, EchoPilot achieves state-of-the-art performance under the sparse-interactive setting, consistently outperforming training-free baselines and finetuned specialists.
Authors: Haoyang Peng, Qian Hu, Songan Zhang, Ming Yang
Abstract: Predicting the interaction between pedestrian and vehicle is essential for autonomous driving safety in unstructured and semi-structured scenarios; however, this task is severely hindered by the scarcity of public datasets that feature dense pedestrian-vehicle interactions. Most current studies rely on structured road data, leaving the complex, heterogeneous interactions found in unstructured environments insufficiently represented and researched. In this paper, we propose a dataset annotation framework based on video data from uncalibrated surveillance cameras and present PINNS (Pedestrian-vehicle Interaction dataset from uNcalibrated cameras in uNstructured Scenes). The dataset covers multiple countries and regions, includes diverse typical traffic scenarios, and considers variations in seasons, lighting conditions, and weather. It focuses on complex scenes with dense pedestrian-vehicle interactions and is designed to be easily extensible. The dataset is constructed and annotated according to the standard issued by the Chinese Association of Automation, providing both trajectory data and corresponding scene-level information. Furthermore, this paper analyzes current challenges and research directions in heterogeneous agent trajectory prediction, shows the necessity and usefulness of the proposed dataset. We hope our framework and dataset will facilitate research on trajectory prediction and autonomous driving in complex mixed traffic scenarios. PINNS is publicly available at https://github.com/Songan-Lab.
Authors: Yinghao Wu, Zhuoyan Luo, Yiyao Yu, Zhaojian Yu, Yujiu Yang, Xiao-Ping Zhang
Abstract: Despite the remarkable progress achieved by recent efficient methods in accelerating multimodal understanding, they still suffer from noticeable performance degradation. Their emphasis on the high compression ratio of a single visual clue and reliance on the heuristic pruning strategy with coarse attention alignment incurs a bottleneck on the information capacity and density of visual tokens. Addressing this limitation, we propose VEN-VL, a visual ensemble MoE framework for effective and efficient perception following the enrich then compact principle. Specifically, we first enrich the information capacity by unifying the visual representations of different perspectives, and then progressively compact it with adaptive routers in specialized visual experts to enhance the information density. Furthermore, we incorporate the reconstruction ability of vanilla structure via explicit visual supervision, facilitating crucial information preservation. Experimental results demonstrate our superiority in complex visual tasks with few information-condensed tokens, which effectively bridges the gap between performance and efficiency.
Authors: Sofiat Abioye, Ufaq Khan, Shazad Ashraf, Anusha Jose, Benjamin Wallace, William Poulett, Adam Byfield, Lukman Akanbi, Muhammad Bilal
Abstract: Urgent suspected colorectal cancer (CRC) referrals create operational bottlenecks because semi-structured clinical documents often require manual review and transcription. The original RAPTOR system used Large Language Models for structured extraction but relied on a separate OCR stage, making it vulnerable to handwriting, layout variation, and loss of visual evidence linkage. We present RAPTOR+, a multimodal extension that uses Vision-Language Models (VLMs) for end-to-end referral understanding. We evaluate fine-tuned VLMs, commercial and open-source zero-shot VLMs, and the original OCR-based pipeline on 223 clinically curated CRC urgent referral forms. We also introduce a grounding-aware evaluation framework that measures both extraction accuracy and evidence localisation. Results show a clear grounding gap in zero-shot models. Gemini 2.5 Flash achieved 92.6% Reading Accuracy but only 1.2% Strict Safety. In contrast, fine-tuned Qwen3-VL-8B achieved 96.1% Reading Accuracy and 60.6% Strict Safety, substantially improving verifiable evidence grounding. These findings show that task-specific fine-tuning is essential for reliable, auditable clinical document understanding. RAPTOR+ enables extracted referral decisions to be linked to visual evidence, supporting safer and more efficient cancer referral triage.
Authors: Tianling Liu, Lequan Yu, Tong Han, Liang Wan
Abstract: While multimodal data integrating diverse imaging and clinical tabular records is crucial for accurate medical diagnosis, the arbitrary absence of specific modalities is prevalent in clinical practice, severely degrading the performance of multimodal models. Existing methods either discard missing modalities, leading to information loss, or struggle to synthesize them without capturing complex inter-modal dependencies. To address these limitations, we propose a novel Context-driven Missing-Modality Learning (CMML) framework, which sequentially performs modality synthesis and semantic alignment to achieve robust diagnosis under arbitrary missing conditions. Specifically, we design a Cascade Residual Transformer-based Autoencoder (CRTA) that leverages learnable context tokens acting as dataset-level semantic prior to capture inter-modal dependencies and synthesize key missing representations. These representations are further enriched by modality-specific memory banks. To resolve the discrepancy between original available and synthesized representations, we transform the learned context tokens into instance-adaptive semantic references by infusing multimodal representations from the CRTA's outputs. This reference guides the alignment of heterogeneous modality representations into a unified space, where class-aware contrastive refinement is finally applied to explore discriminative diagnostic cues. Extensive evaluations on skin lesion (Derm7pt), ocular disease (ODIR), and meningioma (MEN) datasets demonstrate that CMML significantly outperforms state-of-the-art (SOTA) methods, yielding AVG AUC improvements of 1.26%, 0.97%, and 1.32%, respectively.
Authors: Sofiat Abioye, Ufaq Khan, Shazad Ashraf, Mohammed Adil Butt, Andrew D. Beggs, Adam Byfield, Anusha Jose, William Poulett, Ben Wallace, Junaid Qadir, Muhammad Bilal
Abstract: Clinical pathways are disseminated as visual flowcharts where spatial topology, arrow direction, colour coding, and font weight encode critical triage logic that remains inaccessible to computational systems. We present PathWISE, a five-phase pipeline combining four LLM-based agents with a deterministic depth-first search auditor and a Java compiler critic, transforming these non-computable artefacts into validated, executable HL7 Clinical Quality Language (CQL) libraries deployable as FHIR CDS Hooks services. Purpose-built agents extract flowchart structure into a typed directed graph, perform deterministic path enumeration, conduct a structured semantic audit of every node's computability, generate terminology-constrained CQL definitions verified by the official Java CQL-to-ELM compiler, and produce routing logic covering 100% of enumerated patient journeys. Demonstrated across five UK NHS cancer pathways (colorectal, lung, skin, upper GI, and breast), PathWISE audits up to 183 nodes (182 under the Hybrid configuration), identifies 544 structured governance findings across four issue categories, achieves 100% syntactic compilation success, with UNCOMPUTABLE nodes receiving false placeholders that preserve compilability while surfacing governance gaps for clinical review, and produces zero hallucinated terminology codes for dictionary-covered concepts. Critically, PathWISE confines non-deterministic LLM inference to knowledge extraction while deterministic graph mathematics and a standard compiler underpin every verification step.
Authors: Xiang An, Yin Xie, Feilong Tang, Yunyao Yan, Huajie Tan, Didi Zhu, Changrui Chen, Xiuwei Zhao, Bin Qin, Kaicheng Yang, Yifei Shen, Yuanhan Zhang, Kaichen Zhang, Wenkang Zhang, Zheng Cheng, Nansen Zhang, Chunsheng Wu, Chunjiang Ge, Zimin Ran, Dehua Song, Chunyuan Li, Shikun Feng, Ming Hu, Zhangquan Chen, Junbo Niu, Bo Li, Ziyong Feng, Ziwei Liu, Zongyuan Ge, Jiankang Deng
Abstract: We introduce LLaVA-OneVision-2 (LLaVA-OV-2), the most capable vision-language model in the LLaVA-OneVision series to date, achieving superior performance across a broad range of multimodal benchmarks. The model builds on a native OneVision-Encoder and incorporates Windowed Attention for efficient local computation while maintaining native resolution. Its key advance is codec-stream tokenization: it treats compressed video as a continuous bit-cost stream, where bit-cost dynamics determine adaptive temporal groups, and motion-residual cues select salient spatial evidence into compact visual canvases. This allocation concentrates a limited token budget on event-bearing content, enabling more stable long-video token compression than fixed groups of pictures. A shared 3D RoPE further places codec canvases, sampled frames, and images in a unified spatiotemporal coordinate system. Furthermore, we build the LLaVA-OV-2 data and training stack around large-scale open supervision: approximately 8M re-captioned video samples for pretraining, a 4M-sample spatial corpus for fine-tuning. We also introduce JumpScore, a temporal-localization benchmark targeting fine-grained grounding in high-frequency, densely repeated motion, a regime underrepresented by existing video evaluations. A standout capability of LLaVA-OV-2 is its unified perception across video understanding, temporal grounding, spatial grounding, and manipulation-trace reasoning. On JumpScore, LLaVA-OneVision-2-8B reaches 74.9 JumpScore mAP, surpassing Qwen3-VL-8B (30.1) by +44.8 points; under matched visual-token budgets on the same benchmark, codec-stream inputs improve temporal grounding over frame sampling by +9.7 points. Across standard benchmarks, LLaVA-OneVision-2-8B further outperforms Qwen3-VL-8B by +4.3 average points on video tasks, +5.3 on spatial tasks, and +15.6 average J&F on tracking tasks.
Authors: Jinye Li, Chenxi Fu, Minghang Zheng, Yang Liu, Xiahai Zhuang, Qingchao Chen
Abstract: Cardiac function evaluation necessitates continuous, non-invasive monitoring, a capability limited in MRI. Millimeter-wave (mmWave) radar and its Synthetic Aperture Radar (SAR) mode offer a privacy-preserving and portable point-of-care clinical applications. However, reconstructing high-fidelity 3D cardiac geometry from SAR remains an open challenge. Traditional radar methods generate sparse point clouds that lack continuous surface topology. Meanwhile, direct application of optical reconstruction networks performs poorly due to the severe speckle noise and ambiguous boundaries inherent in SAR images. To bridge this gap, we propose SAR2Mesh, a novel framework that reformulates the task as a coarse-to-fine mesh deformation process. By initializing with a topological template, our approach explicitly preserves anatomical connectivity through progressive mesh deformation.We introduce a geometry-aware feature projection module to extract multi-view features via 3D-to-2D sampling, and a physics-informed radar loss to enforce consistency between the predicted geometry and raw radar echoes. Furthermore, we present Cardiac Mesh-SAR, the first large-scale paired SAR-mesh dataset. Extensive experiments demonstrate that SAR2Mesh significantly outperforms existing image-based baselines, achieving accurate and physically consistent cardiac reconstructions.
Authors: Shristi Das Biswas, Kaushik Roy
Abstract: Instruction tuning of large vision-language models (LVLMs) increasingly depends on massive multimodal corpora, yet these datasets contain samples with substantial redundancy, low visual dependency, and highly imbalanced coverage of multimodal reasoning behaviors. As a result, uniform subsampling or naive score-based selection often yields suboptimal training subsets. We introduce MAGIC, a training-free, forward-only coreset selection method designed to construct compact yet behaviorally faithful subsets for multimodal instruction tuning. MAGIC is built on three intrinsic signals extracted from a pretrained VLM: Multimodal Gain, which measures the likelihood improvement obtained from visual input; Bridging Relevance, which captures the sharpness of answer-token grounding over visual tokens; and Skill-Neuron Signatures, which characterize the functional computation elicited by each sample via top-activated feed-forward neurons. MAGIC combines these signals in a three-stage pipeline: filtering low-gain examples, ranking candidates by a normalized quality objective, and performing bucket-wise budget allocation over discrete neuron signatures to preserve latent multimodal skill coverage. This formulation avoids backpropagation, auxiliary selector training, and expensive clustering in continuous activation spaces, while remaining efficient and easily deployable in existing VLMs. Across LLaVA-665K and Vision-Flan datasets, and transfer settings to large target models, LLaVA-1.5-7B and -13B, MAGIC consistently improves over strong baselines under matched 20% budgets: it achieves 100.3% relative performance to full finetuning on LLaVA-665K and 101.6% relative performance on Vision-Flan-186K, while yielding a 73.7% reduction in wall-clock run time.
Authors: Bin Li, Ruichi Zhang, Han Liang, Jingyan Zhang, Juze Zhang, Xin Chen, Jingya Wang
Abstract: Enabling physics-based humanoids to execute diverse behaviors from high-level textual commands remains a significant challenge. Existing methods typically follow either a two-stage paradigm that combines kinematic motion generation with physics-based tracking, or an end-to-end imitation-learning paradigm that directly generates actions from text. However, the former suffers from the inherent domain shift between kinematic generation and physics-based tracking, while the latter struggles with the substantial modality gap between textual commands and low-level actions, limiting effective semantic alignment. Notably, humanoid states encode rich motion dynamics that are more semantically aligned with textual descriptions than low-level actions, making them a natural basis for deriving behavioral intent. Building upon this insight, we propose MIND, a novel end-to-end diffusion framework for text-driven physics-based humanoid control that leverages behavioral intent as a semantic bridge between textual commands and low-level actions. At its core, MIND introduces a multi-scale intent diffusion mechanism, where a holistic intent predictor captures global behavioral dynamics to guide overall behavior synthesis, while an immediate intent predictor provides step-wise, fine-grained signals for local behavior refinement at each diffusion step. This hierarchical intent formulation imposes a structured inductive bias for humanoid control, improving semantic alignment and behavioral naturalness. Furthermore, MIND encodes humanoid states into a latent space to enable more effective semantic intent modeling. Extensive experiments demonstrate that MIND outperforms existing methods and synthesizes coherent, physically plausible, and semantically aligned humanoid behaviors from text commands. Our code will be released to facilitate future research.
Authors: Yiming Liang, Yixiao Chen, Yiyang Zhou, Yixuan Wang, Shoubin Yu, Andong Deng, Fuxiao Liu, Qin Zhang, Chen Chen, Mohit Bansal, Huaxiu Yao
Abstract: Many video reasoning tasks require tracking motion, temporal order, and evolving visual states across frames. Existing methods built on large vision-language models (LVLMs) often address this challenge by externalizing reasoning through textual chain-of-thought (CoT), keyframe selection, repeated frame reinsertion, or external tool use. While effective, such pipelines increase inference-time latency and engineering complexity, and they force temporal-visual evidence to be serialized into text or repeatedly re-encoded from frames. Inspired by the intuition that visual reasoning can occur implicitly before verbalization, we propose STORMS (Spatial-Temporal reasOning via inteRnalized Modeling), a two-stage framework that teaches LVLMs to reason through bounded continuous latent trajectories instead of explicit textual CoT. In Stage I, STORMS aligns latent tokens with thought-video representations derived from generated videos, grounding the latent states in dynamic visual evidence. In Stage II, the model is further trained with answer-only supervision, encouraging the reasoning process to be internalized without step-by-step annotations. Generated thought videos are used only during training; at inference, STORMS performs a bounded latent rollout without regenerating videos, reinserting frames, or invoking external visual tools. Experiments on VideoMME, MVBench, TempCompass, and MMVU show that STORMS improves video reasoning accuracy while substantially reducing inference overhead compared with tool or video-generation-based reasoning pipelines.
Authors: Adina Scheinfeld, Haotan Zhang, Shang Mu, Rudolf L. M. van Herten, Lucas Stoffl, Ali Erturk, Zhuhao Wu, Johannes C. Paetzold
Abstract: Light sheet fluorescence microscopy (LSM) enables high-resolution, three-dimensional (3D) imaging of biological specimens, providing rich volumetric data for studying cellular organization, pathology, and vascular networks. However, the size, dimensionality, and annotation burden of LSM data make supervised deep learning approaches costly and difficult to scale. Additionally, despite the abundance of unannotated LSM volumes, foundation models for this modality remain underexplored due to computational challenges and the complexity of volumetric representation learning. In this work, we introduce a 3D foundation model for LSM data, pretrained on a large curated collection of 3D images spanning multiple organisms, stains, and imaging protocols. We learn transferable volumetric representations by jointly optimizing for masked reconstruction and image-text alignment. The pretrained backbone drastically reduces the annotation burden, enabling efficient, few-shot adaptation for varied downstream tasks. We evaluate this approach on downstream segmentation, classification, and deblurring. Our results demonstrate consistent improvements over baselines, (1) when measured using standard evaluation metrics and (2) when rigorously assessed by domain experts. This highlights the potential of foundation model pretraining to reduce annotation requirements while improving performance across diverse LSM analysis tasks. Pretrained model weights and code for pretraining and finetuning are publicly available: https://github.com/AdinaScheinfeld/lsm_fm_public_repo.git.
URLs: https://github.com/AdinaScheinfeld/lsm_fm_public_repo.git.
Authors: Zixin Jessie Chen, Zhuo Chen, Archer Wang, Jeff Gore, William T. Freeman, Congyue Deng, Marin Solja\v{c}i\'c
Abstract: Creating images from noise is image generation; reconstructing fine details from coarse inputs is super-resolution. Despite their practical differences, both can be understood as reversing information loss across scales. We introduce $\textbf{SKILD}$, a $\textbf{S}$cale-invariant $\textbf{K}$-Space $\textbf{I}$mage $\textbf{L}$earning $\textbf{D}$iffusion model that unifies generation and continuous super-resolution within a single unconditional framework. Both natural images and critical physical systems exhibit scale invariance, and we leverage it to design a forward process that attenuates image content from fine to coarse scales while injecting spectrum-matched Gaussian noise, making scale an explicit coordinate of the diffusion dynamics. The same trained reverse process performs generation and continuous super-resolution by varying only the starting timestep: $\textit{no task-specific architecture, no conditioning branch, no classifier-free guidance, no retraining per scale factor}$. Empirically, SKILD reaches FID $2.65$ and Inception Score $9.63$ on unconditional CIFAR-10, performs $2\times$--$8\times$ super-resolution on ImageNet from a single unconditional checkpoint while outperforming conditional models across perceptual metrics, and reconstructs critical Ising models whose connected four-point correlations closely track the ground truth.
Authors: Xinrui Shi, Kai Liu, Ziqing Zhang, Jianze Li, Anqi Li, Yulun Zhang
Abstract: Lightweight vision-language models perform competitively on standard benchmarks yet fail systematically in dense-scene reasoning, where multiple objects, attributes, and relations must be jointly grounded and resolved through multi-step inference. Such capability is critical for real-world applications where models must reliably interpret cluttered environments. Yet existing training signals provide no explicit grounding between reasoning steps and the underlying visual entities and relations, leaving lightweight models free to generate fluent but visually unanchored reasoning chains. To address this gap, we first introduce DRBench, a benchmark of 14,573 questions across 2,943 images, organized into five task categories spanning three progressive reasoning layers. Building on DRBench, we propose DRScaffold, a supervised fine-tuning framework that decomposes the supervision target into four causally ordered stages, enforcing grounded reasoning without architectural modification. Experiments on three lightweight VLMs demonstrate substantial gains on DRBench while preserving or improving performance on general-purpose benchmarks. Notably, Qwen2.5-VL-3B trained with DRScaffold surpasses the frozen Qwen2.5-VL-32B on DRBench, demonstrating that structured supervision can substitute for a significant portion of model scale in dense-scene reasoning. Our code and models are available at https://github.com/irene-shi/DRScaffold .
Authors: Ali Rouzbayani, Bidhan Roy, Marcos Villagra, Zhiying Jiang
Abstract: We present Paris 2.0, the first video generation model pre-trained through decentralized computation. Its training recipe builds upon Paris 1.0 (arXiv:2510.03434), the first ever open-weight Decentralized Diffusion Model (DDM), which showed that image generation can be trained without a monolithic GPU cluster. However, temporally coherent video generation had remained an open problem under decentralized training, and Paris 2.0 closes it. In low-resolution text-to-video training, against a monolithic model trained on the same data under a matched total compute budget, Paris 2.0 cuts Frechet Video Distance (FVD) from 561.04 to 279.01, a ~2.0x improvement, and lifts CLIP text-video similarity and aesthetic score.
Authors: Wei Song, Tianhang Wang, Yitong Chen, Tong Zhang, Zuxuan Wu, Ming Li, Jiaqi Wang, Kaicheng Yu
Abstract: We present Channel-wise Vector Quantization (CVQ), a novel image tokenization paradigm that replaces patch-wise tokens with channel-wise tokens. Unlike conventional vector quantization, which assigns a discrete token to each patch feature vector, CVQ quantizes each channel of the feature map. This formulation represents an image as discrete levels of visual details, rather than as a grid of spatial patches. Based on CVQ, we introduce a new visual autoregressive framework with "next-channel prediction". Instead of rendering images patch by patch in raster order, our Channel-wise Autoregressive (CAR) model predicts image channels sequentially, producing progressively enriched visual details. Specifically, it first sketches global structure and then refines fine-grained attributes, akin to a human artist's workflow. Empirically, we show that: (1) CVQ achieves 100% codebook utilization with a 16K+ codebook size without any bells and whistles, and substantially improves reconstruction quality over conventional VQ; and (2) CAR attains a DPG score of 86.7 and a GenEval score of 0.79, demonstrating strong effectiveness for text-to-image generation.
Authors: Logan Dewick (University of Wisconsin - Green Bay), Bibesh Pyakurel (University of Wisconsin - Green Bay), Kong Pheng Yang (University of Wisconsin - Green Bay), Nazim Choudhury (University of Wisconsin - Green Bay), M. G. Sarwar Murshed (University of Wisconsin - Green Bay)
Abstract: Automated pavement distress assessment requires more than image-level classification or coarse bounding box detection, demanding precise localization of thin, branching, and irregular cracks to achieve the geometric precision necessary for maintenance-relevant quantification. This paper presents a vision-based pavement distress analysis system based on Mask R-CNN instance segmentation and evaluates it on UWGB-StreetCrack, a custom field-collected roadway image dataset acquired with a vehicle-mounted smartphone and manually annotated with polygon labels for longitudinal cracks, transverse cracks, alligator cracks, and potholes. Five Detectron2-based Mask R-CNN backbone variants were considered under a consistent fine-tuning protocol. The best-performing model, Mask R-CNN with a ResNet-101 FPN backbone, achieved 84.23% precision, 90.04% recall, and an F1 score of 87.04% under the project-specific bounding-box matching protocol. The same model produced an aggregate predicted crack-area fraction of 2.164%, closely matching the 2.170% ground-truth crack-area fraction. To contextualize the segmentation system against a detector-oriented alternative, a CSPDarknet53-based YOLO detector was also adapted and retrained on the dataset, reaching 27.5% precision and 20.7% recall on the validation protocol. The results show that instance segmentation is a practical direction for field pavement imagery and aggregate crack-area estimation, while also exposing open challenges in annotation consistency, class imbalance, confounder rejection, and mask-level benchmarking.
Authors: Yuqian Yuan, Wentong Li, Zhaocheng Li, Yutong Lin, Juncheng Li, Siliang Tang, Jun Xiao, Yueting Zhuang, Wenqiao Zhang
Abstract: In this paper, we introduce InstructSAM, a unified and streamlined framework designed for multi-instance segmentation under arbitrary instructions. We formulates instruction-driven instance segmentation as a set-structured query prediction problem and propose an explicit reasoning-to-instance query interface that elegantly bridges a vision-language model (VLM) and SAM3. Specifically, a bank of learnable instance queries is injected into the VLM and contextualized with instruction and visual information, enabling each query to serve as an instance-aware slot. A hybrid-attention mechanism further promotes interaction among these queries, visual tokens, and instruction tokens, improving instance enumeration and reducing duplicate predictions. The resulting LLM-conditioned queries are projected into SAM3's detector query space to drive accurate multi-instance segmentation in a single forward pass. This design equips SAM3 with high-level instruction understanding, compositional reasoning, and instance-level set prediction without modifying its core architecture. To support training and evaluation, we further construct Inst2Seg, a high-quality and large-scale instruction-based instance segmentation dataset and benchmark that couples free-form instructions with instance-level masks. Extensive experiments show that only 2B-scale InstructSAM achieves strong results across complex instruction-driven and phrase-level referring segmentation benchmarks, outperforming prior end-to-end methods and SAM3's agentic pipeline while enabling efficient single-pass multi-instance prediction.
Authors: Linfei Pan, Johannes Sch\"onberger, Marc Pollefeys
Abstract: Structure-from-Motion -- the process of simultaneously estimating camera poses and 3D scene structure from a collection of images -- remains a central challenge in computer vision, with many open problems yet to be solved. Recent advances in feedforward 3D reconstruction have made significant strides in overcoming persistent failure cases of classical SfM methods, particularly in scenarios characterized by low texture, limited overlap, and symmetries. However, while feedforward approaches excel in these challenging conditions, they often face limitations regarding scalability, accuracy, or robustness, and typically fall short of classical methods in standard reconstruction settings. In this work, we systematically analyze these limitations and propose a new Structure-from-Motion pipeline by combining the respective strengths of classical and feedforward methods. Extensive experiments across multiple datasets show the benefits of our approach, achieving state-of-the-art results across a wide range of scenarios. We share our system as an open-source implementation at https://github.com/colmap/gluemap.
Authors: Geo Ahn, Jiwook Han, Youngrae Kim, Joonseok Lee, Jinwoo Choi
Abstract: Fine-tuning MLLMs for Video Temporal Grounding (VTG) often improves in-domain performance but degrades sharply under domain shift. In this work, we find that this failure is primarily driven not just by unseen query concepts, but by visual domain shift, which prevents the model from coupling its learned temporal localization knowledge with its inherent entity-attention capability. To address this, we introduce EVIDENT, a parameter-efficient adaptation framework that anchors temporal grounding in the inherent entity-attention of pre-trained MLLMs by routing VTG adaptation through explicit visual entity evidence. EVIDENT consists of three components: (i) an Entity Bottleneck Adapter that transforms dense visual tokens into compact entity-level slots, (ii) an Entity-Binding Distillation loss that instills objectness priors into the semantically unstructured MLLM visual space, guiding each slot to bind to a coherent entity, and (iii) an Entity-to-eVidence gating mechanism that leverages the captured entities as evidence, steering the model to localize moments containing query-relevant entities. Together, these components enable VTG fine-tuning to rely on entity-grounded evidence rather than brittle dataset shortcuts. Experiments on cross-domain VTG benchmarks show that EVIDENT consistently improves out-of-domain robustness while preserving competitive in-domain performance with modest parameter overhead. These results suggest that entity-level grounding is an effective inductive bias for generalizable temporal localization.
Authors: Yang Luo, Shengju Qian, Xiaohang Tang, Zirui Zhu, Yong Liu, Xin Wang, Yang You
Abstract: Autoregressive video generators are attractive for streaming, long-horizon, and interactive applications, but distilling strong black-box teachers into causal students remains difficult. The student must learn under its own rollout distribution, whereas practical teachers may expose only prompt-conditioned completed videos and may differ in architecture, capacity, temporal design, and sampling schedule. This interface makes supervised fine-tuning off-policy, score-based distillation inapplicable, and direct adversarial imitation too sparse for denoising-time credit assignment. We propose Adversarial Flow Distillation (AFD), an on-policy framework for heterogeneous black-box video distillation. AFD queries the teacher and rolls out the current student on the same prompts, trains a prompt-paired Bradley-Terry discriminator to estimate clean-sample teacher-student discrepancy, and converts the resulting on-policy advantage into forward-process flow-matching updates on the student's own noised states. Thus, AFD provides dense velocity-field supervision while requiring no teacher scores, latents, denoising trajectories, step alignment, or reverse-chain reinforcement learning. Experiments across two causal AR student families show that AFD consistently improves motion- and physics-sensitive generation while preserving general video quality, and ablations validate the importance of adaptive on-policy feedback and forward-process credit assignment. The method requires only clean teacher videos and student rollouts, providing a practical route for distilling proprietary or heterogeneous video generators into efficient autoregressive students.
Authors: Yushi Huang, Xiangxin Zhou, Ruoyu Wang, Chi Zhang, Jun Zhang, Tianyu Pang
Abstract: Recent advances in few-step diffusion distillation have enabled efficient image generation, yet aligning these models with human preferences remains challenging. We propose Reward-Tilted Distribution Matching Distillation (RTDMD), a two-stage framework that unifies distribution matching distillation with reward-guided reinforcement learning for few-step flow generators. We show that minimizing the KL divergence to a reward-tilted teacher distribution naturally decomposes into a distribution matching term and a reward maximization term. In the first stage, we introduce Ambient-Consistent Distribution Matching Distillation (AC-DMD), which performs subinterval-wise distribution matching and augments the fake score objective with a consistency regularizer to help the fake score model track the shifting generator distribution under limited updates. In the second stage, we jointly optimize both terms: for the reward maximization term, we derive a hybrid policy gradient that combines a GRPO-style estimator for the stochastic intermediate transitions with direct reward backpropagation through the deterministic final step, and further introduce step-subset GRPO (SubGRPO) to reduce variance. Experiments on SD3, SD3.5, and FLUX.2 demonstrate that RTDMD establishes new state-of-the-art results across preference, aesthetic, and compositional metrics with only 4 inference steps, outperforming previous few-step text-to-image generation methods. Code and models are available at https://github.com/Harahan/RTDMD.
Authors: Jiraphon Yenphraphai, Jianqi Chen, Jian Wang, Gordon Qian, Sergey Tulyakov, Rameen Abdal, Raymond A. Yeh, Peter Wonka, Chaoyang Wang
Abstract: Current video-to-4D methods struggle with complex topology changes, transparent materials, thin structures, and inner surfaces. We present Helix4D, a dynamic mesh generation framework by inheriting the expressive representation of Trellis2, adapting it from image-to-3D to video-conditioned 4D generation. Our design arises from two key questions: (a) how to enable Trellis2's frame-local attention to share information across frames while preserving its pretrained quality on rare cases such as transparent objects and inner surfaces, and (b) how to inject temporal information into a purely 3D positional encoding without breaking pretrained capabilities. We address (a) with a sliding-window cross-frame attention and anchor on the first frame. The first frame is generated by the base Trellis2 model and injected into our model, letting it inherit Trellis2's quality in rare cases through cross-frame attention. We address (b) with a 4D temporal encoding that repurposes redundant low-frequency spatial RoPE bands for time, extending the encoding from 3D with no additional parameters. Extensive experiments show the effectiveness of Helix4D for high-quality dynamic mesh generation on ActionBench and our own challenging complex dynamics set.
Authors: Shuhong Zheng, Aashish Kumar Misraa, Yu-Teng Li, Yu-Jhe Li, Igor Gilitschenski
Abstract: Subject-driven image generation aims to synthesize new images that preserve the identity of the given subject while following textual instructions. Existing approaches often encode text and reference images separately. This limits cross-modal reasoning abilities and causes copy-paste artifacts. Recent frameworks that connect multimodal models and diffusion models improve instruction following, but largely overlook identity preservation. To address these limitations, we condition diffusion models on Multimodal Large Language Models (MLLMs) that jointly encode text and reference images, and augment it with VAE-based identity conditioning. A novel Dual Layer Aggregation (DLA) module is designed to aggregate multi-level MLLM features for optimal conditioning, and a multi-stage denoising strategy is applied to progressively balance the semantic information from MLLM and fine-detail identity from VAE during inference. Extensive experiments demonstrate that our approach harmonizes multimodal understanding with identity preservation, mitigates copy-paste issues, and achieves superior performance regarding human preference on subject-driven image generation. Our project website is available at https://zsh2000.github.io/squeeze-mllm-subject-gen/.
Authors: Weijie Wang, Zimu Li, Jinchuan Shi, Zeyu Zhang, Botao Ye, Marc Pollefeys, Donny Y. Chen, Bohan Zhuang
Abstract: Sparse-view 3D reconstruction is increasingly addressed with feed-forward splatting networks that predict explicit primitives directly from images. Yet most existing methods remain centered on Gaussian primitives and expose surfaces only indirectly: extracting a usable mesh for downstream simulation, physics reasoning, or embodied interaction still requires expensive post-hoc steps that break the feed-forward promise. This limitation is especially pronounced in pose-free settings, where scene structure and camera parameters must be estimated jointly from sparse observations. We present TriSplat, a feed-forward reconstruction network that represents scenes with oriented triangle primitives and directly exports simulation-ready mesh scenes from a single forward pass. Given input images, the network predicts local 3D point maps, triangle attributes, camera poses, and optional intrinsics. Rather than regressing triangle orientation as an unconstrained latent variable, our approach constructs geometry normals from the predicted point maps, refines them with an image-conditioned normal head, and converts them into stable local frames for triangle parameterization. A mono-normal bootstrap schedule further stabilizes early training, while opacity and blur scheduling progressively sharpens the learned surface representation for direct mesh extraction. Experiments on RealEstate10K and DL3DV show that this representation produces more geometry-faithful reconstructions than Gaussian feed-forward baselines while maintaining competitive novel-view rendering quality. Because the rendering primitives are themselves surface triangles, the output can be directly ingested by physics engines, collision detectors, and standard rendering pipelines without any conversion, making it a practical simulation-ready solution for feed-forward 3D scene reconstruction.
Authors: Sam Earle, Kay Arulkumaran, Andrew Dai, Akarsh Kumar, Julian Togelius, Sebastian Risi
Abstract: We are in the midst of large-scale industrial and academic efforts to automate the processes of scientific, technological and creative production through AI-driven assistants. Historically, a fundamental property of these processes in their human form has been their open-endedness: their capacity for generating a seemingly endless supply of novel and meaningful new forms. Do artificial agents have any capacity for such fruitful unguided discovery? To answer this question, we turn to Picbreeder, the canonical exemplar of human-driven open-ended search, in which users collaboratively generated a diverse library of images through interactive evolution of small neural networks. We replicate Picbreeder, replacing human users with frontier Vision Language Models (VLMs). We observe clear qualitative differences between the output of our system and the historical human baseline, and attempt to characterize them using metrics of phylogenetic complexity and visual and semantic salience and novelty. In an effort to identify some of the causal factors contributing these differences, we study the addition of exploratory noise to the agents' selection process, of behavioral diversity between agents, and of narrative momentum in the form of memory of past actions. We make our code available at https://github.com/smearle/picbreeder-vlm.
Authors: Heqiang Wang, Weihong Yang, Zheyuan Yang, Jia Zhou, Xiaoxiong Zhong, Fangming Liu, Weizhe Zhang
Abstract: Industrial anomaly detection has attracted significant attention as a fundamental challenge in industrial systems. The rapid advancement of heterogeneous industrial sensors has driven industrial anomaly detection from unimodal to multimodal paradigms. However, existing methods are primarily designed for centralized and offline settings, overlooking the distributed and continuously generated data characteristic of real-world industrial environments. With the advancement of edge intelligence, modern edge devices are increasingly capable of not only data acquisition but also distributed model training, enabling collaborative intelligence across the system. Industrial anomaly detection represents a critical application in this context. Motivated by these challenges, we propose a novel framework termed Multimodal Online Distributed Industrial Anomaly Detection (MODIAD). We first present a comprehensive workflow for MODIAD and then formulate a Multi-class Intelligent Scheduling (MIS) problem to coordinate cross class model updates by balancing data sufficiency and class update frequency. To efficiently solve this problem, we design a Sequential Marginal Gain Greedy (SMG) algorithm that enables effective multi-class training under resource constraints. Furthermore, to improve the computational and communication efficiency during training, we propose an Resource Efficient Class-Wise Low Rank Adaptation (REC-LoRA) strategy, which significantly reduces system overhead while preserving detection performance. Extensive experiments on two representative multimodal industrial anomaly detection datasets, MVTec 3D-AD and Eyecandies demonstrate that the proposed approach achieves superior performance and efficiency under the MODIAD scenario.
Authors: Zhengqi Sun, Yiwen Sun, Boxuan Liu, Tailai Chen, Tianxu Guo, Jiabin Liu
Abstract: Large language models (LLMs) are promising for autonomous driving, but semantics-only decision policies can yield physically unsafe behavior in dynamic traffic. Existing methods either perform online language reasoning without explicit dynamics verification or use world models mainly in offline pipelines, leaving a gap between semantic intent and physical feasibility at decision time. We propose Reason--Imagine--Act (RIA), a closed-loop framework that couples an LLM reasoner with an action-conditioned world model for online safety verification. At each step, the LLM proposes an action template and candidate sub-actions, the world model performs short-horizon rollouts, and a safety scorer selects the safest executable action with feedback to the next reasoning step. Under a unified CARLA point-goal protocol (1000 episodes), RIA achieves 80.05% route completion, 51.10% arrival rate, and 0.20% collision rate. Under the same closed-loop interface, RIA consistently outperforms training-free baselines, including CARLA TM and MADA, on core closed-loop metrics. For reproducibility, code is available at https://github.com/pku-smart-city/source_code/tree/main/RIA.
URLs: https://github.com/pku-smart-city/source_code/tree/main/RIA.
Authors: Amin Abbasishahkoo, Mahboubeh Dadkhah, Lionel Briand
Abstract: Fault detection for Deep Neural Networks (DNNs) has received increasing attention in recent years. While more advanced hybrid approaches have been proposed to combine multiple sources of information and outperform earlier techniques, they often incur substantial computational overhead, limiting scalability and practicality in real-world settings. In this paper, we introduce Concept-Aware Fault Detection (CAFD), a learning-based approach that achieves superior fault detection performance by effectively integrating multiple information sources while maintaining practical efficiency. Specifically, CAFD is trained using a carefully selected set of informative features, including model-based signals derived from the DNN's outputs, distance-based features, and a novel concept-based feature, called Concept Failure Ratio (CFR). CFR leverages Vision-Language Models (VLMs) to extract textual concepts from images and quantify the likelihood that their presence is associated with DNN failures. By incorporating this feature, CAFD benefits from complementary semantic information, enabling more effective fault detection. Our results demonstrate that CFR serves as an effective indicator for DNN fault detection. We conduct an extensive empirical evaluation of CAFD, comparing it against five state-of-the-art baselines across three subject DNN models and datasets, including ImageNet. Across a wide range of constrained selection budgets, CAFD consistently outperforms all baselines in Fault Detection Rate (FDR), achieving average FDR improvements of 18.3% across all investigated subjects and budget sizes.
Authors: Matthew Niedoba, Berend Zwartsenberg, Frank Wood
Abstract: The neural-network denoising functions which form the backbone of image diffusion models are remarkably consistent in their generalization behaviour across a wide variety of network architectures and training procedure hyperparameters. A recent line of research has sought to model the outputs of these networks by aggregating posterior weighted averages of training dataset patches. In this work, we consolidate these approaches into a unified model class which we call Filtered Posterior Mean Collections (FPMCs). We define this model class using query precision vectors, response weights, and source distributions, and illustrate that existing methods are recoverable with specific choices of these design axes. Investigating each axis in turn, we find that FPMC performance can be improved with soft relaxations of prior patch-based methods, and through augmentations of source distributions. Applying these findings to an existing FPMC, we demonstrate consistent sample improvement across three natural image datasets.
Authors: Chad Weatherly, Sen Lin
Abstract: Continual anomaly detection (CAD) addresses the need for industrial inspection systems to adapt to evolving production conditions, yet existing methods share three critical gaps: unrealistic evaluation, no systematic comparison, and no consideration of edge deployment constraints. We introduce a unified benchmark combining discrete-task evaluation on structural and logical anomalies, a novel continuous drift protocol, the first head-to-head comparison of all published CAD methods, and computational efficiency profiling on edge hardware. Our results reveal that existing CAD methods do not consistently outperform traditional approaches with simple experience replay. Thus motivated, we propose DINOSaur, a training-free method combining a frozen DINOv3 backbone with spatially-indexed coreset memory and neighborhood-restricted anomaly scoring. DINOSaur achieves zero forgetting by construction, outperforms all evaluated methods across all five protocols, and runs at sub-100\,ms inference on an NVIDIA Jetson Orin Nano, with on-device adaptation to new tasks in under 30 seconds.
Authors: Hao Sun, Yingyan Hou, Jiayan Guo, Bo Wang, Chunyu Yang, Jinsong Ni, Yan Zhang
Abstract: Document retrieval in real-world scenarios faces significant challenges due to diverse document formats and modalities. Traditional text-based approaches rely on tailored parsing techniques that disregard layout information and are prone to errors, while recent parsing-free visual methods often struggle to capture fine-grained textual semantics in text-rich scenarios. To address these limitations, we propose \textbf{Unveil}, a novel visual-textual embedding framework that effectively integrates textual and visual features for robust document representation. Through knowledge distillation, we transfer the semantic understanding capabilities from the visual-textual embedding model to a purely visual model, enabling efficient parsing-free retrieval while preserving semantic fidelity. Experimental results demonstrate that our visual-textual embedding method surpasses existing approaches, while knowledge distillation successfully bridges the performance gap between visual-textual and visual-only methods, improving both retrieval accuracy and efficiency.
Authors: Sattam Altuuaim, Lama Ayash, Muhammad Mubashar, Naeemullah Khan
Abstract: Despite the central role of optimization in deep learning, most optimizers rely on update structures whose functional form is fixed before training begins. This static design can limit their ability to respond to changing gradient behavior across the loss landscape, where training may shift between stable, noisy, and inconsistent regimes. This study proposes PILOT (Policy-Informed Learned OpTimizer), an online optimizer that adapts its update behavior during training. Rather than using a fixed balance between momentum, normalization, and sign-based updates, PILOT uses gradient-direction agreement as a signal of local training stability. Conditioning the update rule on this agreement signal allows the optimizer to adjust its behavior when gradients become stable, noisy, or inconsistent. Experiments on FashionMNIST and CIFAR-10 show that PILOT consistently achieves the highest accuracy among the evaluated optimizers across convolutional settings. On the CNN architecture, PILOT reaches 94.13% on FashionMNIST and 81.94% on CIFAR-10. On ResNet-18, it further improves performance, reaching 95.71% on FashionMNIST and 93.42% on CIFAR-10. These results suggest that learning how to adapt the update structure during training can improve performance across both compact and deeper convolutional models while preserving a simple first-order optimization framework. The implementation of PILOT is publicly available at https://github.com/SattamAltwaim/PILOT.git
Authors: Gustavo (Jesus), Angulo
Abstract: We develop a rigorous algebraic framework for deep convolutional architectures, CNNs, ResNets, and encoder--decoder networks such as UNet, grounded in lattice theory and mathematical morphology. The central tool is the Matheron--Maragos--Banon--Barrera (MMBB) universal representation theory for translation-invariant operators, which we apply systematically to every layer of a standard deep network. The principal finding is that the standard CNN pipeline (linear convolution~$+$ ReLU~$+$ flat max-pooling) is a cross-lattice operator: the convolution is an erosion in the Fourier inf-semilattice while ReLU is a lattice-join closing and max-pooling is a dilation in the pointwise max-plus lattice, and their composition is a morphological opening in neither. A second finding is that the upper adjoint of ReLU in the pointwise lattice is a global (non-local) operator, the identity on globally non-negative functions and $-\infty$ otherwise, so no local morphological erosion can form an adjunction pair with ReLU. These two results together provide the precise algebraic reason why depth in standard CNNs introduces genuine representational power: the composed layer is not idempotent. Three layer designs that are genuine idempotent openings are identified and fully characterised: the pure max-plus morphological layer (pointwise lattice), the spectral Wiener layer (Fourier lattice), and the self-dual morphological layer. We establish a complete fixed-point and convergence theory. The framework also unifies max-pooling, strided convolution, and the Laplacian pyramid under the Goutsias--Heijmans adjoint pyramid theory, and gives the Activation--Pooling Dilation (APD) factorisation with its correct adjoint.
Authors: Mustafa Kadhim, Viktor Rogowski, Emilia Persson, Camila Gonzalez, Andr\'e Haraldsson, Sofie Ceberg, Mikael Nilsson, Malin K\"ugele, Sven B\"ack, Christian Jamtheim Gustafsson
Abstract: Artificial intelligence is increasingly integrated into radiotherapy workflows, yet such pipelines remain vulnerable to out-of-distribution image data that may introduce unexpected behavior in clinical tasks. Deep learning-based anomaly detection for pelvic magnetic resonance imaging (MRI) remains largely unexplored, and transparent evaluation of its feasibility for full automation is limited. We developed and evaluated a fully automated, unsupervised anomaly-detection framework for pelvic and brain MRI. A two-stage framework was trained on reference images from public datasets: LUND-PROBE for pelvic MRI, and IXI, fastMRI, and fastMRI+ for brain MRI. In the first stage, MRI slices were compressed into discrete tokens; in the second, the distribution of normal tokens was modeled. Anomaly evidence was estimated by combining perceptual image differences with token-surprisal scores based on negative log-likelihood. Automated detection was evaluated on pelvic MRI with synthetic global and real clinical anomalies, and on brain MRI with clinically annotated fastMRI+ abnormalities. Sensitivity, specificity, area under the receiver operating characteristic curve (AUC), and false-positive behavior in held-out normal cases were assessed. The framework achieved robust detection across hidden evaluation cohorts, with AUCs of 0.97 (95% CI, 0.95-0.98) and 0.81 (95% CI, 0.74-0.87) for pelvic and brain MRI, respectively. Heatmap analysis showed strong spatial agreement between detected anomalies and ground-truth locations, supporting localization accuracy and interpretability. These results support the potential of unsupervised anomaly detection as an automated MRI quality-control layer for radiotherapy workflows, with transparent visualization of image regions likely to compromise downstream AI-based tasks.
Authors: Anna Deichler
Abstract: A robot resolving ``put the cup on that one'' must fuse gesture, language, and scene geometry, yet 3D grounding benchmarks only partially capture this regime: descriptions are written post-hoc, gestures are templated, or pointing is staged for the camera. MM-Conv captures natural co-speech gesture from dyadic VR interaction alongside full-body motion capture and 3D scene graphs. We use it to evaluate pose-language fusion with a decoupled late-fusion architecture in which pose and text pathways share no learned parameters. The two choices together make category, pose, and text contributions easier to isolate through controlled ablations. Fusion with frozen MiniLM category embeddings exceeds pose alone and the best text-only pathway on every reference type, reaching 31.9% top-1. The learned scalar gate flips between opposing policies depending on whether the text pathway has category access. This is a reliability diagnostic: fusion-accuracy claims for semantic grounding systems are indistinguishable from category-representation artifacts unless pathways are architecturally decoupled.
Authors: Sol Park, Soobin Um
Abstract: Minority sampling aims to generate low-density instances on a data manifold and is of central importance in applications such as medical diagnosis, anomaly detection, and creative AI. Existing approaches, however, define minority samples relative to generative priors learned from training data, confining rarity to model-specific notions that may poorly reflect real-world semantics. In this work, we propose a world-centric perspective on minority sampling, which defines rarity with respect to real-world priors rather than generator-induced densities. To this end, we introduce JEPA guidance, a diffusion sampling framework guided by a Joint-Embedding Predictive Architecture (JEPA) -- a class of world models that encode broad, semantically rich representations. JEPA guidance steers diffusion trajectories toward low-density regions under the implicit density induced by the JEPA, thereby aligning generated minorities with real-world semantic rarity. To make JEPA guidance computationally practical, we develop principled approximation strategies accompanied by theoretical error bounds, significantly reducing the overhead of guidance computation. Extensive experiments across unconditional, class-conditional, and text-to-image generation demonstrate that JEPA guidance consistently improves the fidelity and semantic validity of minority samples, outperforming generator-centric baselines in capturing real-world notions of rarity. Code is available at https://github.com/soobin-um/jepa-guidance.
Authors: Jialiang Yang, Bin Xia, Ruihang Chu, Dingdong Wang, Wanke Xia, Zhun Mou, Tianyang Zhong, Yiting Zhao, Wenming Yang
Abstract: Rapid advances in audio-video (AV) generation have enabled high-fidelity synthesis with synchronized sound, particularly for human-related scenarios involving speech and interactions. Yet evaluation for AV generation remains at an early stage, with only a few coarse-grained benchmarks for human-related scenarios and relying on limited preset evaluations with generic multimodal LLMs, leading to inaccurate assessments of model capabilities. To address these issues, we introduce AVBench, a fully automated benchmark tailored for human-centric AV generation. AVBench is built on two key designs for comprehensive and accurate evaluation: (i) Human-centric and fine-grained metrics. AVBench integrates ten evaluation dimensions designed for human-centered real-world scenarios, covering visual quality, audio quality, and multi-level consistency across modalities. These practical metrics capture human-related details that existing benchmarks often overlook. (ii) Specialized evaluators via preference learning. To address the lack of specialized training data, we construct large-scale supervision by transforming real-world videos into diverse training pairs with controlled perturbations. After fine-tuning on this high-quality dataset, the evaluators learn to reliably detect subtle cross-modal inconsistencies. Crucially, instead of producing discrete textual judgment, AVBench derives continuous evaluation scores from the model's prediction confidence on binary decisions. This probabilistic scoring mechanism enables a more reliable assessment than traditional VQA-style evaluation and aligns closely with human judgment. Taken together, AVBench offers automated evaluation for AV generation, demonstrates strong potential for data filtering, and serves as a differentiable reward signal for Reinforcement Learning from Human Feedback (RLHF).
Authors: Ben S. Southworth, Shuai Jiang, Daniel McBride, Eric C. Cyr, Stephen Thomas
Abstract: Muon is a recently developed matrix-aware optimizer that has shown strong results in transformer training, but its behavior in vision transformers (ViTs) is not yet well understood. We study Muon for ViT training, largely on ImageNet-100 and Pl@ntNet-300K, comparing against AdamW under standard vision recipes involving mixup, cutmix, smoothing, and random augmentation and erasing. Muon consistently outperforms AdamW, with especially large gains on long-tailed Pl@ntNet macro top-1. These gains are also recipe-dependent, where Muon benefits much more than AdamW from advanced and significant data augmentation techniques. To understand this interaction, we analyze the singular-value structure of matrix gradients throughout the ViT. Within Muon training runs, removing heavy data augmentation induces a late-training spectral concentration and mode collapse in gradient matrices, primarily in deep MLP-down blocks. Under a fixed "full" augmentation recipe, the clearest Muon-AdamW contrast appears instead in QKV gradients, where AdamW gradient energy remains concentrated in a much narrower basis while Muon spreads energy across substantially more singular modes. Muon in ViTs is therefore best understood as an optimizer-recipe interaction. Under a fixed recipe, Muon differs from AdamW most clearly in attention projections, where its gradients consist of a broader spectral basis. Within Muon, a full training recipe is important for preventing late spectral concentration and mode collapse in deep feedforward blocks. We further demonstrate efficacy in training ViTs on image segmentation and masked autoencoder models, where Muon outperforms AdamW in all settings considered.
Authors: Seokjun Choi, Yunseong Moon, Kaizhang Kang, Hoon-Gyu Chung, Jin-Nyeong Kim, Giljoo Nam, Seung-Hwan Baek
Abstract: Inverse rendering remains a core challenge in graphics and vision, especially in the snapshot configurations required for lightweight desktop workflows, where the per-frame information budget is highly constrained. Previous inverse rendering work explores various available dimensions for enriching the per-shot information, including temporal modulation, spectral encoding, and polarization. In this work, we introduce polarimetric display inverse rendering, using an LCD to project a linearly polarized RGB binary pattern and an RGB polarization camera augmented with a quarter-wave plate to acquire spectro-polarimetric measurements in a single shot. A feed-forward transformer maps these measurements to per-pixel normal, albedo, roughness, and metallicity. To overcome training data scarcity, we expand a limited set of measured polarimetric bidirectional reflectance distribution functions via a generative manifold. Evaluations on a real desktop setup demonstrate accurate inverse rendering across diverse scenes, outperforming existing approaches.
Authors: Zhi (Leo), Wang, Botao He, Kelin Yu, Seungjae Lee, Ruohan Gao, Furong Huang, Yiannis Aloimonos
Abstract: Human egocentric video captures rich manipulation demonstrations without any robot hardware, yet transferring these skills to robots remains challenging due to the embodiment gap between human and robot in both visual appearance and kinematics. We present HumanEgo, a framework that bridges the embodiment gap by lifting each human demonstration to an entity-level representation of hand-object interaction, and training a flow matching policy with dense auxiliary objectives that amplify supervision from every trajectory. HumanEgo is robot-data-free, hardware-agnostic, data-efficient, and zero-shot human-to-robot transferable. With only 30 minutes of human videos per task, HumanEgo achieves 92.5% average success across four real-world tasks (75% with just 15 minutes), outperforms matched-time robot teleoperation by 41%, and robustly transfers zero-shot across novel robots, cameras, and environments.
Authors: Jianrui Zhang, Hyun Jung Lee, Sukanta Ganguly, Tae-Eui Kam, Donghyun Kim, Yong Jae Lee
Abstract: Multimodal retrieval relies heavily on single-vector retrievers, which compress rich, sequential token sequences into one single global representation. While efficient, they discard fine-grained, local evidence critical for dense retrieval tasks. Multi-vector approaches were introduced as a solution, but they strictly require training and many ignore the necessity of a globally summarizing representation. To address this, we introduce SMART, a framework that unlocks the latent multi-vector capabilities of standard single-vector models. We first demonstrate that standard contrastive training on the pooled embedding implicitly shapes the retrieval geometry of preceding hidden states via gradient flow. By applying direct late-interaction over these frozen hidden states during inference, SMART acts as a plug-and-play upgrade that consistently improves performance across diverse modalities, improving even the state-of-the-art models further on MMEB-V2. We also reveal SMART's superior performance, as simple lightweight post-training not only saves time and compute, but also brings forth further improvement on Visual Document retrieval, allowing a single-vector model to outperform SoTA multi-vector counterparts. Ultimately, SMART offers both a highly efficient inference enhancement and a powerful finetuning technique for multimodal retrieval. We open source our code and weights at https://github.com/HanSolo9682/SMART.
Authors: Yuanzhi Xu, Qian Gao, Jun Fan, Guohui Ding, Zhenyu Yang, Sixue Lin, Yuteng Xiao
Abstract: The generation of factually incorrect objects, commonly known as object hallucination, remains a persistent challenge in Large Vision-Language Models (LVLMs). Current approaches to address this issue - ranging from expensive data-driven fine-tuning and high-latency contrastive decoding to rigid attention head truncation - frequently compromise either computational efficiency or the continuity of the model's feature space. To overcome these limitations, we introduce a novel, training-free inference strategy that operates as a region-aware adaptive weighting mechanism to dynamically correct semantic drift without relying on abrupt heuristic truncations. By computing an outlier-resistant statistical midpoint across various attention heads, we establish a stable anchor for reliable visual representations. We then utilize the inter-head disagreement mapped across regions to dynamically determine intervention budgets, gently suppressing hallucination-inducing attention paths through a continuous penalty modulation. This recalibration process effectively rectifies visual-semantic misalignments while fully preserving generative fluency and language priors. Comprehensive evaluations on standard multimodal benchmarks, including CHAIR, POPE, and MME, reveal that our strategy substantially curtails both instance- and sentence-level hallucinations. The results demonstrate state-of-the-art performance against contemporary baselines, confirming our method's efficiency and algorithmic robustness. Our code will be public.
Authors: Sijin Yu, Zijiao Chen, Zhenyu Yang, Zihao Tan, Jiakun Xu, Zhongliang Liu, Shengxian Chen, Wenxuan Wu, Xiangmin Xu, Xin Zhang
Abstract: Current fMRI decoders face a performance-fidelity trade-off where efficient ID encoders outperform geometrically faithful surface-based models. We argue this is partly driven by inefficient surface tokenization and the failure to use anatomy as a predictive signal. We present NeurIPS, a framework that improves surface-based decoding by reframing anatomical variation from a nuisance to a powerful inductive prior. NeurIPS unites two innovations: a Selective ROI Spherical Tokenizer (SRST) for efficient geometric encoding, and a Structure-Guided Mixture of Experts (SG-MoE) that explicitly models individual anatomy using cortical features. On the Natural Scenes Dataset, NeurIPS establishes a new state-of-the-art for surface decoders and achieves performance comparable to strong 1D baselines. This is achieved with unprecedented efficiency, as the model converges dramatically faster (10 vs. 600 epochs). This efficiency enables rapid adaptation to new subjects using only 20% of data and ensures robust scalability as the training cohort is expanded. Ablations provide causal evidence that these gains are driven by the model's use of cortical features, not by memorizing subject IDs. By leveraging anatomical priors, NeurIPS provides a principled and scalable path toward robust, generalizable brain decoding.
Authors: Weixin Wang, Yu Yang, Wei Deng, Pan Xu
Abstract: We study inference-time alignment for diffusion-based generative models, aiming to steer a base model toward high-reward outputs without updating its weights. Recent Sequential Monte Carlo (SMC)-based steering methods approximate reward-tilted target distributions in a principled way, but their proposals remain largely tied to the base sampler. Since reward information is mainly used after propagation through particle reweighting and resampling, these methods can require large particle budgets and suffer from weight degeneracy and high-variance estimates. One way to reduce variance and improve particle efficiency is to iteratively learn twisting functions that provide look-ahead guidance, as in twisted SMC. However, existing learnable twisting methods are developed mainly for classical sequential inference and can be unstable when applied to diffusion-based alignment with high-dimensional state spaces and terminal, noisy, or black-box rewards. We propose Trust-Region Iterative Twisted Sequential Monte Carlo (TRI-TSMC), a trust-region framework for learning twisting functions in SMC-based inference-time alignment. Each iteration computes an exact KL-constrained update in path space, which admits a closed-form solution by tempered importance reweighting, and projects this target back to the parameterized twisted family by weighted maximum likelihood. Theoretically, we formalize the value-function interpretation of the optimal twisting function and show that it yields a zero-variance sampler. We prove that the trust-region update follows an escort path toward the target distribution, that the weighted maximum-likelihood update is a forward-KL projection, and that the path reduces residual importance-weight variance. Empirically, TRI-TSMC improves primary alignment objectives on discrete diffusion text generation and text-to-image generation under matched inference-time budgets.
Authors: Kozachok Elena Sergeevna
Abstract: This study presents a methodology for constructing a clinically verified dataset of dermatoscopic images for medical informatics research. The relevance of the work is driven by the fact that the performance of automated diagnostic support systems depends not only on the volume of images, but also on the reproducibility of the image acquisition procedure, the completeness of structured metadata, and the reliability of diagnostic labels. International collections were primarily created under conditions that differ substantially from routine Russian outpatient practice and mobile dermatoscopy. The proposed methodology integrates three interconnected components: (1) a standard operating procedure (SOP) for acquiring images via mobile dermatoscopy, (2) an information model comprising 16 structured metadata fields organized into six clinically oriented blocks in ISIC-compatible notation, and (3) a multi-stage expert verification of diagnostic labels (initial clinical annotation, consensus review by three specialists, and histological confirmation of all malignant neoplasms). Using this methodology, a dataset of 1,026 unique dermatoscopic images from 443 patients was collected between June 2025 and May 2026. From 1,044 initial records, 18 duplicates were excluded. The dataset includes nine nosological categories; all 39 malignant lesions (18 melanomas, 15 basal cell carcinomas, and 6 squamous cell carcinomas) were histologically verified. Patient age ranged from 2 to 90 years (median 38), with 279 females (63%) and 164 males (37%). Each image is accompanied by expert-annotated dermatoscopic structures and an explicit verification_stage field indicating the level of diagnostic confirmation. The resulting dataset serves as a pilot clinically verified resource suitable for independent model evaluation, domain shift analysis, interpretability studies, and further expansion.
Authors: Aditya Sridhar
Abstract: Concept Bottleneck Models (CBMs) have emerged as a cornerstone approach for interpretable machine learning, providing human-understandable intermediate representations through explicit concept activations. However, this interpretability fundamentally introduces a critical, previously unexplored attack surface: the concept bottleneck layer itself. We present a comprehensive, systematic study of concept-level adversarial vulnerabilities in CBMs, revealing that targeted, minimal perturbations operating on input pixels can induce catastrophic misclassification by manipulating semantic representations. We develop a rigorous theoretical framework to quantify concept-space robustness, establishing novel metrics that expose the vulnerability landscape of these architectures. Our extensive analysis on the CUB-200-2011 dataset demonstrates that standard CBMs exhibit severe susceptibility to concept-level manipulation. To address this critical weakness, we introduce SPECTRA (Semantic Perturbation-based Concept Training for Robustness against Attacks), a principled stability regularization defense. SPECTRA effectively hardens the semantic representation space, increasing the minimal perturbation norm required for a successful attack from 0.46 to over 4,200, rendering targeted concept manipulation computationally prohibitive. Furthermore, SPECTRA preserves baseline classification accuracy to within 2.2%. By establishing concept-level attacks as a fundamentally distinct threat model, this work opens a new research frontier at the intersection of interpretable machine learning and adversarial robustness.
Authors: Keyang Ye, Hongzhi Wu, Kun Zhou
Abstract: Novel view synthesis has been significantly advanced by NeRFs and 3D Gaussian Splatting (3DGS), which require ordering volumetric samples or primitives for correct color blending. While the recent Gaussian-Enhanced Surfels (GES) enable high-performance, sort-free rendering, they suffer from aliasing artifacts and suboptimal reconstruction. To address these limitations, we propose DP-GES, a novel representation that augments opaque surfels with semi-transparent boundaries and leverages Depth Peeling to establish accurate per-pixel ordering. This design enables sort-free Gaussian splatting with correct transmittance modulation, effectively eliminating aliasing and popping artifacts while facilitating a fully differentiable joint optimization. Extensive experiments demonstrate that our method achieves superior reconstruction quality and compares favorably against state-of-the-art techniques across a wide range of scenes.
Authors: Veera Varuni Radhakrishnan, Chinthaka Dinesh, Qurat-ul-Ain Azim
Abstract: Low-dose computed tomography (LDCT) reconstruction faces a critical tradeoff between reconstruction quality and resource requirements. While recent deep learning methods achieve state-of-the-art performance, they typically rely on over 500,000 parameters trained on large-scale datasets exceeding 35,000 scans. This work investigates whether graph-based regularization can provide meaningful noise reduction under strict resource constraints. We propose Deep Graph Laplacian Regularization (Deep GLR), integrating quadratic graph regularization into a Proximal Forward-Backward Splitting optimization framework with three lightweight CNN modules. Evaluated on the LoDoPaB-CT benchmark, Deep GLR achieves 30.70 dB PSNR, representing a 6.33 dB improvement over filtered backprojection, while using only 91,848 parameters trained on 1000 samples (2.8\% of standard training set). Compared to benchmark methods, this represents 5.8 times better parameter efficiency and 30 times better data efficiency per dB improvement. The learned graph bandwidth parameter ($\epsilon$=1.25) converges to interpretable values, suggesting the method captures meaningful image priors rather than overfitting. While a 13 dB gap remains versus state-of-the-art methods, results demonstrate that graph-based regularization provides a favorable efficiency-quality tradeoff for resource-constrained medical imaging scenarios.
Authors: Divyam Goel, Nithin Chalapathi, Sanjeev Raja, Aditi S. Krishnapriyan
Abstract: Inverse problems in partial differential equations (PDEs) involve estimating the physical parameters of a system from observed spatiotemporal solution fields. Neural networks are well-suited for PDE parameter estimation due to their capability to model function-to-function space transformations. While existing benchmarks of machine learning methods for PDEs primarily focus on the forward problem, there are no similar comprehensive studies and benchmark datasets on PDE inverse problems, i.e., mapping solution fields to underlying physical parameters. We fill this gap by introducing PDEInvBench, a comprehensive benchmark dataset consisting of numerical simulations for both time-dependent and time-independent PDEs across a wide range of physical behaviors and parameters. Our dataset includes evaluation splits that assess performance in both in-distribution and various out-of-distribution settings. Using our benchmark dataset, we comprehensively explore the design space of neural networks for PDE inverse problems along three key dimensions: (1) optimization procedures, analyzing the role of supervised, self-supervised, and test-time training objectives on performance, (2) problem representations, where we study the value of architectural choices with different inductive biases and various conditioning strategies, and (3) scaling, which we perform with respect to both model and data size. Our experiments reveal several practical insights: 1) neural networks perform best with a two-stage training procedure: initial supervision with PDE parameters followed by test-time fine-tuning using the PDE residual, 2) incorporating PDE derivatives as input features consistently improves accuracy, and 3) increasing the diversity of initial conditions in the training data yields greater performance gains than expanding the range of PDE parameters. We make our dataset and codebase publicly available.
Authors: Huakeng Ding, Zhanpeng Liu, Fan Pei, Kun Zhou, Hongzhi Wu
Abstract: We present a differentiable framework to automatically learn view-dependent 2D kernels in a splatting-based pipeline to improve reconstruction quality and representation efficiency for novel 3D view synthesis. Our volumetric primitive is defined as a bounding ellipsoid and a 3D-kernel latent vector. We first learn a projection network to output a 2D-kernel latent, taking the attributes of the ellipsoid and the 3D-kernel latent as input. Next, the result is sent to a decoder to produce a radially symmetric 2D kernel in terms of Mahalanobis distance, bounded by the projected ellipsoid. The neural networks along with per-primitive attributes are jointly optimized. The effectiveness of our approach is demonstrated on standard benchmarks, comparing favorably against state-of-the-art techniques on both analytical and learned kernels. Finally, we extend the idea to learn general 2D kernels for 2D splatting as well as image representation.
Authors: Wenhui Chu
Abstract: Robotic perception in unstructured environments remains challenging despite the zero-shot capabilities of foundation models such as SAM. This work attributes performance degradation to non-uniform representation shifts across transformer layers: shallow layers exhibit substantial domain gaps (CKA < 0.5), whereas deep layers transfer effectively (CKA > 0.7). Based on this observation, we propose RepSAM, a representation-guided parameter-efficient fine-tuning (PEFT) framework for adapting foundation models to robotic vision. RepSAM employs a theoretically grounded CKA-guided rank allocation strategy combined with a multi-modal fusion module for robust handling of challenging robotic scenarios, including transparent objects and cluttered scenes. Experimental evaluation across six benchmarks and robotic manipulation tasks demonstrates that RepSAM achieves 97.9% of full fine-tuning performance (89.0% vs. 90.9% mIoU) while reducing trainable parameters by 158x (from 632M to 4.0M). RepSAM outperforms DoRA by 7.9% mIoU with just 4 hours of training on a single A100 GPU (a 96x reduction from full fine-tuning, which takes 384 GPU-hours). These improvements are statistically significant (p < 0.01) and translate to a 12.0% absolute improvement in robotic manipulation success rates over the LoRA (RGB) baseline.
Authors: Sizhe Zhao, Shengping Zhang, Shuo Yang, Weiyu Zhao, Shuigen Wang, Xiangyang Ji
Abstract: Existing embodied control research demonstrates remarkable performance improvements by scaling training data and model size. We instead explore inference-time strategy as an alternative axis. Non-deterministic generative models, such as diffusion and autoregressive models, have been widely adopted in the field of embodied control. However, the single-shot inference paradigm limits their performance. In this paper, we propose \textbf{TapSampling}, a plug-and-play framework for inference-time sampling. First, we introduce an Action-VAE that represents actions in a low-dimensional latent space by mapping policy-generated initial actions into a compressed posterior distribution, from which any number of latent samples can be drawn and decoded into candidate actions that approximate the true action distribution. Second, we formulate action verification as task-progress outcome prediction, using the intrinsic sequential structure of robotic datasets to train a semantically grounded verifier for interpretable action selection. Furthermore, TapSampling is a policy-agnostic framework. Extensive experiments in both simulated and real-world environments demonstrate that our method substantially improves multiple generalist policies without further policy finetuning. Code and models are available at the project page.
Authors: Yuanye Liu, Yibo Gao, Yuanyang Chen, Xiahai Zhuang
Abstract: Evidential Deep Learning (EDL) has emerged as an efficient, sampling-free strategy for uncertainty estimation. A series of EDL variants have been proposed to address specific limitations of the original framework, achieving notable success. However, the underlying theoretical structure of EDL and the relationships among these variants have received limited systematic investigation. In this work, we establish a principled theoretical foundation for EDL by interpreting it within a generalized Bayesian framework that includes prior specification, posterior update, and training objective. We further characterize evidential uncertainty from a Bayesian distributional uncertainty viewpoint, established via asymptotic analysis. Building on this perspective, we further propose Generalized Evidential Deep Learning (GEDL), a unified and extensible framework that explicitly disentangles the roles of individual components and systematically relates GEDL to existing variants. Extensive experiments demonstrate that GEDL yields comparable results on classification, uncertainty estimation and OOD detections, with theoretical grounding.
Authors: Florent Tariolle, Florian Yger
Abstract: Black-box adversarial attacks that minimize only the ground-truth confidence suffer from class drift: perturbations wander through the feature space without committing to a specific adversarial class, wasting queries on diffuse, undirected progress. We introduce Opportunistic Target Selection (OTS), a lightweight wrapper that switches an untargeted attack to a targeted objective early in its trajectory, locking onto whichever non-true class currently leads. OTS requires no architectural modification to the underlying attack, no gradient access, and no a priori target-class knowledge. We validate OTS on three score-based attacks (SimBA, Square Attack with cross-entropy loss, and Bandits) across five standard ImageNet classifiers (4,500 runs). On random-search attacks, OTS closely tracks oracle performance, with gains up to +27 pp in success rate and 43% relative reduction in censored-mean iterations on ResNet-50. On gradient-estimation attacks (Bandits) and attacks with margin loss, OTS is redundant, a negative result that reinforces our interpretation of OTS as a margin-loss surrogate. On adversarially-trained models, a bimodal difficulty distribution eliminates the regime where targeting helps.
Authors: Yunfei Wang, Xiaohao Xu, Yang Li, Xiaonan Huang
Abstract: Large language models (LLMs) are increasingly used as proposal generators for evolutionary robot design, yet most loops remain memoryless: simulator results shape the next population but are not preserved as reusable design knowledge. We present Auto-Robotist, a self-evolving LLM agent that distills morphology-search traces into an explicit natural-language skill library. Each skill stores a structural archetype, evidence-grounded positive and negative rules, and the evaluated designs that support them, making design memory inspectable rather than implicit in a population. During search, the agent retrieves skills to condition LLM edits of elite bodies while retaining a Genetic Algorithm (GA) mutation path for exploration; after evaluation, it updates the library through Add, Diagnose, and Merge. Across seven EvoGym tasks spanning locomotion, traversal, and object interaction, Auto-Robotist improves cold-start 5x5 search and transfers learned skills to 10x10 design spaces, where reference-conditioned transfer outperforms GA on every task. These results suggest that LLM agents can convert expensive physical evaluations into reusable, auditable design principles. Our code will be released upon acceptance.
Authors: Zhengrui Guo, Zhengyu Zhang, Jiabo Ma, Yihui Wang, Fengtao Zhou, Yingxue Xu, Ling Liang, Chenglong Zhao, Qi Xie, Jinbang Li, Shujing Guo, Fangyi Han, Zhijian Cen, Ziyi Liu, Cheng Jin, Junlin Hou, Zhixuan Chen, Yu Cai, Lijuan Qu, Shifu Chen, Yueping Liu, Zhe Wang, Xiuming Zhang, Muyan Cai, Li Liang, Hao Chen
Abstract: Pathological assessment guides lung cancer diagnosis, treatment selection, and prognostic evaluation, yet current CPath approaches rely on task-specific models for isolated objectives. Although pan-cancer foundation models offer versatility, they lack subspecialty-level depth and have not been evaluated across clinical workflows or prospectively validated in real-world settings. We introduce PulmoFoundation, a multi-center, prospectively validated, randomized controlled trial (RCT)-evaluated foundation model for comprehensive lung pathology assessment across pre-operative, intra-operative, and post-operative care. Built upon Virchow2 via subspecialty-specific pretraining using ~40,000 diagnostic H&E-stained whole-slide images (WSIs), PulmoFoundation was systematically evaluated on ~26,000 WSIs across 32 clinically relevant tasks. In addition to accurately predicting molecular markers and patient survival, our model achieves clinical-grade performance in core diagnostic tasks across biopsy, frozen section, and surgical resection slides. In a registered prospective study of 1,357 patients across 11 diagnostic tasks, our model achieved an average AUC of 92.3%. Using pre-specified triage thresholds, PulmoFoundation could reduce additional second-review burden for 68.8% of biopsies and 83.0% of frozen sections, and defer 44.5% of IHC stain orders, with PPVs of 1.0, 0.991, and 0.966. Beyond prospective validation, we conducted a crossover RCT with eight pathologists, in which AI assistance improved diagnostic accuracy across 4,928 case-reader pairs (91.7% w/ AI vs. 83.8% w/o AI). AI assistance also reduced median diagnostic time by 19.6%, increased diagnostic confidence by 8.7%, and improved inter-rater agreement from moderate (kappa = 0.56) to substantial (kappa = 0.76). Together, these evaluations support PulmoFoundation as a clinically validated decision-support system for lung pathology.
Authors: Jai Bardhan, Ramya Hebbalaguppe, Aravind Udupa
Abstract: Advancements in 3D curve skeletonization are accelerating progress across a wide range of applications. However, developing robust skeletonization algorithms that capture intricate object details remains challenging. Skeletonization via Local Separators (LS) offers an efficient graph-based approach but suffers from representation inaccuracies due to its discrete nature. To address this, we introduce CSCD, a novel framework for Curve Skeletonization in the Continuous Domain, generalizing LS to manifolds. Specifically, we present two realizations: CSCD-M for meshes and CSCD-PC for point clouds. CSCD-M leverages the intrinsic triangulation of a mesh for resilience to noise and improved topological preservation, while CSCD-PC employs tufted Laplacians for enhanced robustness. To our knowledge, CSCD-M is the first intrinsic method for curve skeletonization. Our results show CSCD-M matches LS performance across diverse meshes and outperforms LS (TOG'21) on benchmarks like Thingi10k dataset. CSCD-PC qualitatively outperforms CoverageAxis++ (Eurographics'24) and EPCS (CAG'23). Finally, we demonstrate the efficacy of CSCD in a few downstream tasks: object classification, shape segmentation, identifying handles, tunnels, and constrictions in objects. Project Website: https://cscd-skel.pages.dev
Authors: Benjamin Herb, Steve G\"oring, Alexander Raake, Rakesh Rao Ramachandra Rao
Abstract: Recent video super-resolution (VSR) approaches use deep neural networks to enhance low-quality input videos and recover visual detail, with diffusion-based methods in particular showing promising results. In this paper, we investigate whether existing video quality models can be used to assess the performance of these diffusion-based VSR methods, by comparing model predictions with results from a subjective test. The study compares six upscaling methods (Lanczos, Rhea, SCST, DOVE, SeedVR2, Starlight Mini) applied to both compressed (AV1 and DCVC-RT) and uncompressed low-resolution videos considering the play-out on a UHD-1/4K screen. A range of full- and no-reference quality models are used to assess their applicability to this new type of quality degradation, focusing on within-sequence performance. The results highlight that CNN-based full-reference models, such as LPIPS, DISTS, and CVQA-FR show significantly higher correlation coefficients than both conventional full- as well as the tested no-reference models. Most overestimate the overly sharp results of SCST, with VMAF mainly failing due to spatial inconsistencies introduced by Starlight Mini. None of the tested video quality models reach sufficient accuracy so as to replace complementary subjective testing. The reference, degraded and upscaled videos, as well as the user ratings and model scores are made available with the paper at https://github.com/Telecommunication-Telemedia-Assessment/AVT-VQDB-UHD-1-VSR as open data.
URLs: https://github.com/Telecommunication-Telemedia-Assessment/AVT-VQDB-UHD-1-VSR
Authors: Guangming Fu, Jiahui Fan, Jian Yang, Milo\v{s} Ha\v{s}an, Beibei Wang
Abstract: Capturing relightable 3D assets from real-world objects is a widely researched problem. Several per-scene optimization-based methods, based on 3D Gaussian splatting (3DGS), support relighting; however, they usually require dense input views, and their overfitting nature makes it difficult to generalize across scenes. Unlike per-scene optimization methods, generalized feed-forward models can directly reconstruct Gaussians from sparse input views. However, the resulting assets have baked-in illumination and cannot be easily used for relighting. In this paper, we present F-RNG, a feed-forward framework that directly generates relightable 3DGS assets from sparse-view inputs. Training such a model from scratch can require massive data and computing resources, and it is especially challenging to generate relightable assets in a feed-forward manner with acceptable cost. We develop F-RNG upon an existing large reconstruction model (LRM) to extract relightable representations, while also utilizing priors from an intrinsic decomposition model (IDM). Specifically, we first introduce a latent-interpolated fine-grained geometry synthesis to enhance the LRM's geometry representation. Second, we propose a prior-guided relightable appearance distillation to extract relightable neural representations by incorporating IDM priors. Finally, a universal neural renderer enables flexible and high-fidelity relighting. F-RNG requires neither re-training nor fine-tuning of the underlying LRMs, thus can automatically benefit from better LRMs and IDMs in the future. With only small networks that can be trained with affordable data and computational resources, F-RNG avoids the repetitive inference of large models under different light conditions. By comparison to the state-of-the-art LRM-based relighting method, F-RNG achieves ~25x faster relighting, as well as superior quality (~+2.0 dB).
Authors: Branislav Kveton, Anup Rao, Subhojyoti Mukherjee, Krishna Kumar Singh, Viet Dac Lai
Abstract: We introduce AdvantageFlow, a forward-process reinforcement learning algorithm for rectified flow models. Unlike Flow-GRPO, which optimizes the reverse process, we optimize an advantage-weighted forward-process prediction loss. This optimization problem is unstable when advantages are negative and the loss becomes non-convex. We stabilize it by rollout policy regularization, which reduces variance and arises from fitting a local reward-improving target distribution. We evaluate AdvantageFlow on image generation tasks with Stable Diffusion 3.5 Medium. It outperforms both Flow-GRPO and a state-of-the-art forward-process RL baseline based on negative-aware fine-tuning.
Authors: Dale Decatur, Jacob Serfaty, Oded Stein, Amir Vaxman, Rana Hanocka
Abstract: We present CrossLift, a technique for computing cross fields on meshes guided by visual features in images. We leverage powerful text-to-image priors that are capable of synthesizing images of feature-aligned quad meshes in 2D. We extract this signal as explicit per-pixel directions in the 2D images, which we then back-project to the mesh surface. We aggregate these candidate surface directions by performing two smooth interpolations on the mesh surface (first within each view and second across multiple views). We propose custom confidence-based weights for the candidate directions in each interpolation that allow us to resolve conflicts between candidates on the same face and smoothly interpolate our field to occluded faces. Our method is modular and can be used with many different 2D visual priors. We show additional applications to texture-aligned quad meshing as well as interactive cross-field design using coarse, user-drawn lines as signal. We demonstrate the effectiveness of CrossLift on a diverse set of both organic and mechanical shapes and produce quad meshes that exhibit superior semantic alignment as compared to existing methods. Project page at: https://crosslift.github.io/
Authors: Jun-Tao Tang, Yu-Cheng Shi, Zhen-Hao Xie, Da-Wei Zhou
Abstract: Multimodal Large Language Models (MLLMs) achieve versatility by reformulating diverse tasks into a unified instruction-following framework via instruction tuning. However, real-world deployment requires continuous adaptation to emerging tasks, motivating Multimodal Continual Instruction Tuning (MCIT). Despite its growing importance, current MCIT research is hindered by severe engineering bottlenecks. Existing methods are typically implemented by directly modifying the base MLLM codebase, which imposes substantial implementation overhead and yields method-specific architectures that severely limit code reuse and fair comparison. To address this, we introduce Prism, a plug-in reproducible codebase specifically designed for scalable MCIT research. It separates algorithmic development from the backbone implementation via a lightweight plugin registration mechanism, enabling new strategies to be integrated as independent plugins without modifying the underlying MLLM codebase, thereby eliminating structural fragmentation and accelerating method development. Prism natively supports widely used large-scale training pipeline, thereby enabling reproducible and scalable MCIT experimentation. Code is available at https://github.com/LAMDA-CL/Prism.
Authors: Haiming Zhang, Junfei Zhou, Feng Jiang, Jingzhong Li, Zhenglong Guo, Penglin Dai, Jifeng Dai, Yan Xie, Benjin Zhu
Abstract: Generating high-fidelity and controllable synthetic data is critical for advancing end-to-end autonomous driving, particularly for addressing the long tail of rare safety-critical scenarios. Existing occupancy-guided methods typically rely on shallow conditioning mechanisms and reference-frame-dependent video synthesis, which limits fine-grained controllability from arbitrary BEV layouts and restricts their applicability for scalable simulation. In this paper, we propose AnyScene, a unified occupancy-centric framework for driving scene generation. AnyScene generates semantic occupancy sequences from BEV layouts through a Spatial-Temporal Occupancy Diffusion Transformer that jointly tokenizes BEV and occupancy features in an autoregressive manner. This design enables precise controllability from cross-dataset and user-defined BEV inputs while naturally supporting long-horizon generation. Building upon the generated occupancy, a Geometry-Grounded View Expansion module treats occupancy as the canonical spatial representation and synthesizes temporally consistent multi-view driving videos in a reference-free and autoregressive fashion, supporting flexible camera configurations at inference time. Extensive experiments demonstrate that AnyScene achieves state-of-the-art performance in both occupancy and video generation. It exhibits strong generalization to unseen and customized layouts, and provides measurable benefits for downstream tasks such as sparse-view 3D reconstruction.
Authors: Xiang Fang, Yuchong Hu, Pan Zhou, Dapeng Oliver Wu
Abstract: Multi-view clustering has wide applications in many image processing scenarios. In these scenarios, original image data often contain missing instances and noises, which is ignored by most multi-view clustering methods. However, missing instances may make these methods difficult to use directly and noises will lead to unreliable clustering results. In this paper, we propose a novel Auto-weighted Noisy and Incomplete Multi-view Clustering framework (ANIMC) via a soft auto-weighted strategy and a doubly soft regular regression model. Firstly, by designing adaptive semi-regularized nonnegative matrix factorization (adaptive semi-RNMF), the soft auto-weighted strategy assigns a proper weight to each view and adds a soft boundary to balance the influence of noises and incompleteness. Secondly, by proposing{\theta}-norm, the doubly soft regularized regression model adjusts the sparsity of our model by choosing different{\theta}. Compared with existing methods, ANIMC has three unique advantages: 1) it is a soft algorithm to adjust our framework in different scenarios, thereby improving its generalization ability; 2) it automatically learns a proper weight for each view, thereby reducing the influence of noises; 3) it performs doubly soft regularized regression that aligns the same instances in different views, thereby decreasing the impact of missing instances. Extensive experimental results demonstrate its superior advantages over other state-of-the-art methods.
Authors: Xiang Fang, Daizong Liu, Pan Zhou, Yuchong Hu
Abstract: As an increasingly popular task in multimedia information retrieval, video moment retrieval (VMR) aims to localize the target moment from an untrimmed video according to a given language query. Most previous methods depend heavily on numerous manual annotations (i.e., moment boundaries), which are extremely expensive to acquire in practice. In addition, due to the domain gap between different datasets, directly applying these pre-trained models to an unseen domain leads to a significant performance drop. In this paper, we focus on a novel task: cross-domain VMR, where fully-annotated datasets are available in one domain (``source domain''), but the domain of interest (``target domain'') only contains unannotated datasets. As far as we know, we present the first study on cross-domain VMR. To address this new task, we propose a novel Multi-Modal Cross-Domain Alignment (MMCDA) network to transfer the annotation knowledge from the source domain to the target domain. However, due to the domain discrepancy between the source and target domains and the semantic gap between videos and queries, directly applying trained models to the target domain generally leads to a performance drop. To solve this problem, we develop three novel modules: (i) a domain alignment module is designed to align the feature distributions between different domains of each modality; (ii) a cross-modal alignment module aims to map both video and query features into a joint embedding space and to align the feature distributions between different modalities in the target domain; (iii) a specific alignment module tries to obtain the fine-grained similarity between a specific frame and the given query for optimal localization. By jointly training these three modules, our MMCDA can learn domain-invariant and semantic-aligned cross-modal representations.
Authors: Xiang Fang, Daizong Liu, Pan Zhou, Guoshun Nan
Abstract: Given an untrimmed video, temporal sentence grounding (TSG) aims to locate a target moment semantically according to a sentence query. Although previous respectable works have made decent success, they only focus on high-level visual features extracted from the consecutive decoded frames and fail to handle the compressed videos for query modelling, suffering from insufficient representation capability and significant computational complexity during training and testing. In this paper, we pose a new setting, compressed-domain TSG, which directly utilizes compressed videos rather than fully-decompressed frames as the visual input. To handle the raw video bit-stream input, we propose a novel Three-branch Compressed-domain Spatial-temporal Fusion (TCSF) framework, which extracts and aggregates three kinds of low-level visual features (I-frame, motion vector and residual features) for effective and efficient grounding. Particularly, instead of encoding the whole decoded frames like previous works, we capture the appearance representation by only learning the I-frame feature to reduce delay or latency. Besides, we explore the motion information not only by learning the motion vector feature, but also by exploring the relations of neighboring frames via the residual feature. In this way, a three-branch spatial-temporal attention layer with an adaptive motion-appearance fusion module is further designed to extract and aggregate both appearance and motion information for the final grounding. Experiments on three challenging datasets shows that our TCSF achieves better performance than other state-of-the-art methods with lower complexity.
Authors: Robin Karlsson, Francisco Lepe-Salazar, Kazuya Takeda
Abstract: Vision-language models (VLMs) transform environment percepts into vision-language semantics interpretable by LLMs. However, completing complex tasks often requires reasoning about information beyond what is currently perceived. We propose latent compositional semantic embeddings z* as a principled learning-based knowledge representation for queryable spatio-semantic memories. We mathematically prove that z* can always be found, and that the optimal z* is the centroid for any set Z. We derive a probabilistic bound for estimating separability of related and unrelated semantics. We prove that z* is discoverable from visual appearance and singular descriptions by iterative gradient descent. We experimentally verify our findings on four embedding spaces including CLIP and SBERT. Our results show that z* can represent up to 10 semantics encoded by SBERT, and up to 100 semantics for ideal uniformly distributed high-dimensional embeddings. We introduce three new datasets with overlapping semantics to show that common VLMs trained on conventional nonoverlapping annotations discover z*. Our novel sufficient similarity inference method overcomes fundamental limitations of conventional inference, and improves higher-level overlapping semantic inference performance by 19.63 mIoU on average.
Authors: Xiao Zhang, Ruoxi Jiang, William Gao, Rebecca Willett, Michael Maire
Abstract: We show that introducing a weighting factor to reduce the influence of identity shortcuts in residual networks significantly enhances semantic feature learning in generative representation learning frameworks, such as masked autoencoders (MAEs) and diffusion models. Our modification notably improves feature quality, raising ImageNet-1K K-Nearest Neighbor accuracy from 27.4% to 63.9% and linear probing accuracy from 67.8% to 72.7% for MAEs with a ViT-B/16 backbone, while also enhancing generation quality in diffusion models. This significant gap suggests that, while residual connection structure serves an essential role in facilitating gradient propagation, it may have a harmful side effect of reducing capacity for abstract learning by virtue of injecting an echo of shallower representations into deeper layers. We ameliorate this downside via a fixed formula for monotonically decreasing the contribution of identity connections as layer depth increases. Our design promotes the gradual development of feature abstractions, without impacting network trainability. Analyzing the representations learned by our modified residual networks, we find correlation between low effective feature rank and downstream task performance.
Authors: Samar Fares, Klea Ziu, Toluwani Aremu, Nikita Durasov, Martin Tak\'a\v{c}, Pascal Fua, Ivan Laptev, Karthik Nandakumar
Abstract: Vision-Language Models (VLMs) are increasingly susceptible to sophisticated adversarial attacks, including adaptive strategies specifically designed to bypass existing defenses. To address this vulnerability, we propose MirrorCheck, a robust and model-agnostic detection framework that operates effectively in both unimodal and multimodal settings. MirrorCheck leverages Text-to-Image (T2I) models to regenerate visual content from captions produced by the target model and assesses semantic consistency by comparing feature-space embeddings between the original and synthesized images. To enhance robustness against adaptive attacks, MirrorCheck introduces a stochastic defense strategy that randomly selects T2I generators and image encoders from a diverse model zoo. Additionally, we incorporate a novel One-Time-Use (OTU) perturbation applied to the selected encoder embeddings, regulated by a scaling factor, which decreases the effectiveness of adaptive attacks. Extensive experiments across multiple threat scenarios demonstrate that MirrorCheck consistently outperforms baseline methods, and maintains its utility even under strong adaptive adversarial conditions.
Authors: Roman Beliy, Navve Wasserman, Amit Zalcher, Michal Irani
Abstract: Image-to-fMRI encoding is important for both neuroscience research and practical applications. However, such "Brain-Encoders" have been typically trained per-subject and per fMRI-dataset, thus restricted to very limited training data. In this paper we propose a Universal Brain-Encoder, which can be trained jointly on data from many different subjects/datasets/machines. What makes this possible is our new voxel-centric Encoder architecture, which learns a unique "voxel-embedding" per brain-voxel. Our Encoder trains to predict the response of each brain-voxel on every image, by directly computing the cross-attention between the brain-voxel embedding and multi-level deep image features. This voxel-centric architecture allows the functional role of each brain-voxel to naturally emerge from the voxel-image cross-attention. We show the power of this approach to (i) combine data from multiple different subjects (a "Crowd of Brains") to improve each individual brain-encoding, (ii) quick & effective Transfer-Learning across subjects, datasets, and machines (e.g., 3-Tesla, 7-Tesla), with few training examples, and (iii) use the learned voxel-embeddings as a powerful tool to explore brain functionality (e.g., what is encoded where in the brain).
Authors: Fuchen Zheng, Xuhang Chen, Weihuang Liu, Haolun Li, Yingtie Lei, Jiahui He, Chi-Man Pun, Shounjun Zhou
Abstract: In medical image segmentation, specialized computer vision techniques, notably transformers grounded in attention mechanisms and residual networks employing skip connections, have been instrumental in advancing performance. Nonetheless, previous models often falter when segmenting small, irregularly shaped tumors. To this end, we introduce SMAFormer, an efficient, Transformer-based architecture that fuses multiple attention mechanisms for enhanced segmentation of small tumors and organs. SMAFormer can capture both local and global features for medical image segmentation. The architecture comprises two pivotal components. First, a Synergistic Multi-Attention (SMA) Transformer block is proposed, which has the benefits of Pixel Attention, Channel Attention, and Spatial Attention for feature enrichment. Second, addressing the challenge of information loss incurred during attention mechanism transitions and feature fusion, we design a Feature Fusion Modulator. This module bolsters the integration between the channel and spatial attention by mitigating reshaping-induced information attrition. To evaluate our method, we conduct extensive experiments on various medical image segmentation tasks, including multi-organ, liver tumor, and bladder tumor segmentation, achieving state-of-the-art results. Code and models are available at: https://github.com/lzeeorno/SMAFormer.
Authors: Kiran Purohit, Anurag Reddy Parvathgari, Sourangshu Bhattacharya
Abstract: Deep convolutional neural networks (CNNs) have achieved impressive performance in many computer vision tasks. However, their large model sizes require heavy computational resources, making pruning redundant filters from existing pre-trained CNNs an essential task in developing efficient models for resource-constrained devices. Whole-network filter pruning algorithms prune varying fractions of filters from each layer, hence providing greater flexibility. Current whole-network pruning methods are either computationally expensive due to the need to calculate the loss for each pruned filter using a training dataset, or use various heuristic / learned criteria for determining the pruning fractions for each layer. This paper proposes a two-level hierarchical approach for whole-network filter pruning which is efficient and uses the classification loss as the final criterion. The lower-level algorithm (called filter-pruning) uses a sparse-approximation formulation based on linear approximation of filter weights. We explore two algorithms: orthogonal matching pursuit-based greedy selection and a greedy backward pruning approach. The backward pruning algorithm uses a novel closed-form error criterion for efficiently selecting the optimal filter at each stage, thus making the whole algorithm much faster. The higher-level algorithm (called layer-selection) greedily selects the best-pruned layer (pruning using the filter-selection algorithm) using a global pruning criterion. We propose algorithms for two different global-pruning criteria: (1) layer-wise relative error (HBGS), and (2) final classification error (HBGTS). Our suite of algorithms outperforms state-of-the-art pruning methods on ResNet18, ResNet32, ResNet56, VGG16, and ResNext101. Our method reduces the RAM requirement for ResNext101 from 7.6 GB to 1.5 GB and achieves a 94% reduction in FLOPS without losing accuracy on CIFAR-10.
Authors: Xiang Fang, Arvind Easwaran, Blaise Genest
Abstract: Out-of-distribution (OOD) detection targets to detect and reject test samples with semantic shifts, to prevent models trained on in-distribution (ID) dataset from producing unreliable predictions. Existing works only extract the appearance features on image datasets, and cannot handle dynamic multimedia scenarios with much motion information. Therefore, we target a more realistic and challenging OOD detection task: OOD action detection (ODAD). Given an untrimmed video, ODAD first classifies the ID actions and recognizes the OOD actions, and then localizes ID and OOD actions. To this end, in this paper, we propose a novel Uncertainty-Guided Appearance-Motion Association Network (UAAN), which explores both appearance features and motion contexts to reason spatial-temporal inter-object interaction for ODAD.Firstly, we design separate appearance and motion branches to extract corresponding appearance-oriented and motion-aspect object representations. In each branch, we construct a spatial-temporal graph to reason appearance-guided and motion-driven inter-object interaction. Then, we design an appearance-motion attention module to fuse the appearance and motion features for final action detection. Experimental results on two challenging datasets show that UAAN beats state-of-the-art methods by a significant margin, illustrating its effectiveness.
Authors: Zihan You, Ni Wang, Hao Wang, Qichao Zhao, Jinxiang Wang
Abstract: Accurate 3D object detection in autonomous driving relies on Bird's Eye View (BEV) perception and effective temporal fusion. However, existing fusion strategies based on convolutional layers or deformable self-attention struggle to model global context in BEV space, leading to reduced accuracy for large objects.To address this limitation, we propose MambaBEV, a novel BEV-based 3D object detection model that leverages Mamba2, an advanced state-space model (SSM) optimized for long-sequence processing. Our key contribution is TemporalMamba, a temporal fusion module that enhances global context modeling through a BEV feature discrete rearrangement mechanism tailored for sequential processing. In addition, we introduce a Mamba-based DETR head to improve multi-object representation. Evaluations on the nuScenes dataset demonstrate that MambaBEV-base achieves 51.7% NDS and an 42.7% mAP. Furthermore, evaluation within an end-to-end autonomous driving paradigm validates its effectiveness in motion forecasting and planning.These results highlight the potential of state-space models for improving global context understanding and large-object detection in autonomous driving perception systems.
Authors: Xiang Fang, Arvind Easwaran, Blaise Genest, Ponnuthurai Nagaratnam Suganthan
Abstract: Previous OOD detection systems only focus on the semantic gap between ID and OOD samples. Besides the semantic gap, we are faced with two additional gaps: the domain gap between source and target domains, and the class-imbalance gap between different classes. In fact, similar objects from different domains should belong to the same class. In this paper, we introduce a realistic yet challenging setting: class-imbalanced cross-domain OOD detection (CCOD), which contains a well-labeled (but usually small) source set for training and conducts OOD detection on an unlabeled (but usually larger) target set for testing. We do not assume that the target domain contains only OOD classes or that it is class-balanced: the distribution among classes of the target dataset need not be the same as the source dataset. To tackle this challenging setting with an OOD detection system, we propose a novel uncertainty-aware adaptive semantic alignment (UASA) network based on a prototype-based alignment strategy. Specifically, we first build label-driven prototypes in the source domain and utilize these prototypes for target classification to close the domain gap. Rather than utilizing fixed thresholds for OOD detection, we generate adaptive sample-wise thresholds to handle the semantic gap. Finally, we conduct uncertainty-aware clustering to group semantically similar target samples to relieve the class-imbalance gap. Extensive experiments on three challenging benchmarks demonstrate that our proposed UASA outperforms state-of-the-art methods by a large margin.
Authors: Donghwna Lee, Kirok Kim, Jisu Lee, Kyungha Min, Wooju Kim
Abstract: Pose-Guided Person Image Synthesis (PGPIS) aims to generate human images in specified poses while preserving the identity and appearance of a source image. This technology facilitates diverse applications, including virtual try-on, digital avatars, animation, and sign language generation. Despite the high-quality results of recent diffusion-based PGPIS, these models typically depend on implicit feature aggregation within the denoising process. As a result, fine-grained texture preservation is limited, and even for the same identity, it is difficult to ensure consistent generation under variations in pose and source appearance. To address these limitations, we propose Fusion Embedding for PGPIS using a Diffusion Model (FPDM), the first framework that explicitly aligns fused source-pose embeddings with target image embeddings via contrastive learning, and subsequently employs the learned fusion embedding as a conditioning signal for generation. FPDM integrates an Image-Pose Fusion (IPF) module into our proposed Source-Enhanced Pose Fusion approach to learn a fusion embedding aligned with the target image. We then employ a conditional diffusion model guided by source appearance, target pose, and the learned fusion embedding. Experiments on the DeepFashion benchmark and the RWTH-PHOENIX-Weather 2014T dataset demonstrate competitive performance compared to existing methods in both quantitative and qualitative evaluations, with ablation studies confirming that explicit fusion embedding alignment substantially improves texture fidelity and consistency across pose and source appearance variations.
Authors: Rishabh Sabharwal, Ram Samarth B B, Parikshit Singh Rathore, Punit Rathore
Abstract: Channel and spatial attention mechanisms introduced by earlier works enhance the representation abilities of deep convolutional neural networks (CNNs) but often lead to increased parameter and computation costs. While recent approaches focus solely on efficient feature context modeling for channel attention, we aim to model both channel and spatial attention comprehensively with minimal parameters and reduced computation. Leveraging the principles of relational modeling in graphs, we introduce a constant-parameter module, STEAM: Squeeze and Transform Enhanced Attention Module, which integrates channel and spatial attention to enhance the representation power of CNNs. To our knowledge, we are the first to propose a graph-based approach for modeling both channel and spatial attention, utilizing concepts from multi-head graph transformers. Additionally, we introduce Output Guided Pooling (OGP), which efficiently captures spatial context to further enhance spatial attention. We extensively evaluate STEAM for large-scale image classification, object detection and instance segmentation on standard benchmark datasets. STEAM achieves a 2% increase in accuracy over the standard ResNet-50 model with only a meager increase in GFLOPs. Furthermore, STEAM outperforms leading modules ECA and GCT in terms of accuracy while achieving a three-fold reduction in GFLOPs.
Authors: Xiang Fang, Arvind Easwaran, Blaise Genest, Ponnuthurai Nagaratnam Suganthan
Abstract: This paper focuses on a significant yet challenging task: out-of-distribution detection (OOD detection), which aims to distinguish and reject test samples with semantic shifts, so as to prevent models trained on in-distribution (ID) data from producing unreliable predictions. Although previous works have made decent success, they are ineffective for real-world challenging applications since these methods simply regard all unlabeled data as OOD data and ignore the case that different datasets have different label granularity. For example, "cat" on CIFAR-10 and "tabby cat" on Tiny-ImageNet share the same semantics but have different labels due to various label granularity. To this end, in this paper, we propose a novel Adaptive Hierarchical Graph Cut network (AHGC) to deeply explore the semantic relationship between different images. Specifically, we construct a hierarchical KNN graph to evaluate the similarities between different images based on the cosine similarity. Based on the linkage and density information of the graph, we cut the graph into multiple subgraphs to integrate these semantics-similar samples. If the labeled percentage in a subgraph is larger than a threshold, we will assign the label with the highest percentage to unlabeled images. To further improve the model generalization, we augment each image into two augmentation versions, and maximize the similarity between the two versions. Finally, we leverage the similarity score for OOD detection. Extensive experiments on two challenging benchmarks (CIFAR- 10 and CIFAR-100) illustrate that in representative cases, AHGC outperforms state-of-the-art OOD detection methods by 81.24% on CIFAR-100 and by 40.47% on CIFAR-10 in terms of "FPR95", which shows the effectiveness of our AHGC.
Authors: Xiang Fang, Wanlong Fang, Changshuo Wang, Daizong Liu, Keke Tang, Jianfeng Dong, Pan Zhou, Beibei Li
Abstract: Given some video-query pairs with untrimmed videos and sentence queries, temporal sentence grounding (TSG) aims to locate query-relevant segments in these videos. Although previous respectable TSG methods have achieved remarkable success, they train each video-query pair separately and ignore the relationship between different pairs. We observe that the similar video/query content not only helps the TSG model better understand and generalize the cross-modal representation but also assists the model in locating some complex video-query pairs. Previous methods follow a single-thread framework that cannot co-train different pairs and usually spends much time re-obtaining redundant knowledge, limiting their real-world applications. To this end, in this paper, we pose a brand-new setting: Multi-Pair TSG, which aims to co-train these pairs. In particular, we propose a novel video-query co-training approach, Multi-Thread Knowledge Transfer Network, to locate a variety of video-query pairs effectively and efficiently. Firstly, we mine the spatial and temporal semantics across different queries to cooperate with each other. To learn intra- and inter-modal representations simultaneously, we design a cross-modal contrast module to explore the semantic consistency by a self-supervised strategy. To fully align visual and textual representations between different pairs, we design a prototype alignment strategy to 1) match object prototypes and phrase prototypes for spatial alignment, and 2) align activity prototypes and sentence prototypes for temporal alignment. Finally, we develop an adaptive negative selection module to adaptively generate a threshold for cross-modal matching. Extensive experiments show the effectiveness and efficiency of our proposed method.
Authors: Aditya Vora, Sauradip Nag, Kai Wang, Hao Zhang
Abstract: We present ATOP (Articulate That Object Part), a novel few-shot method based on motion personalization to articulate a static 3D object with respect to a part and its motion as prescribed in a text prompt. Given the scarcity of available datasets with motion attribute annotations, existing methods struggle to generalize well in this task. In our work, the text input allows us to tap into the power of modern-day diffusion models to generate plausible motion samples for the right object category and part. In turn, the input 3D object provides ``image prompting'' to personalize the generated motion to the very input object. Our method starts with a few-shot finetuning to inject articulation awareness to current diffusion models to learn a unique motion identifier associated with the target object part. Our finetuning is applied to a pre-trained diffusion model for controllable multi-view motion generation, trained with a small collection of reference motion frames demonstrating appropriate part motion. The resulting motion model can then be employed to realize plausible motion of the input 3D object from multiple views. At last, we transfer the personalized motion to the 3D space of the object via differentiable rendering to optimize part articulation parameters by a score distillation sampling loss. Experiments on PartNet-Mobility and ACD datasets demonstrate that our method can generate realistic motion samples with higher accuracy, leading to more generalizable 3D motion predictions compared to prior approaches in the few-shot setting.
Authors: Shizhan Liu, Hao Zheng, Hang Yu, Jianguo Li
Abstract: Image personalization has garnered attention for its ability to customize Text-to-Image generation using only a few reference images. However, a key challenge in image personalization is the issue of conceptual coupling, where the limited number of reference images leads the model to form unwanted associations between the personalization target and other concepts. Current methods attempt to tackle this issue indirectly, leading to a suboptimal balance between text control and personalization fidelity. In this paper, we take a direct approach to the concept coupling problem through statistical analysis, revealing that it stems from two distinct sources of dependence discrepancies. We therefore propose two complementary plug-and-play loss functions: Denoising Decouple Loss and Prior Decouple loss, each designed to minimize one type of dependence discrepancy. Extensive experiments demonstrate that our approach achieves a superior trade-off between text control and personalization fidelity.
Authors: Takeshi Noda, Chao Chen, Junsheng Zhou, Weiqi Zhang, Yu-Shen Liu, Zhizhong Han
Abstract: Inferring signed distance functions (SDFs) from sparse point clouds remains a challenge in surface reconstruction. The key lies in the lack of detailed geometric information in sparse point clouds, which is essential for learning a continuous field. To resolve this issue, we present a novel approach that learns a dynamic deformation network to predict SDFs in an end-to-end manner. To parameterize a continuous surface from sparse points, we propose a bijective surface parameterization (BSP) that learns the global shape from local patches. Specifically, we construct a bijective mapping for sparse points from the parametric domain to 3D local patches, integrating patches into the global surface. Meanwhile, we introduce grid deformation optimization (GDO) into the surface approximation to optimize the deformation of grid points and further refine the parametric surfaces. Experimental results on synthetic and real scanned datasets demonstrate that our method significantly outperforms the current state-of-the-art methods. Project page: https://takeshie.github.io/Bijective-SDF
Authors: Yeqi Fang, Rong Zhou
Abstract: Positron Emission Tomography (PET) is an important molecular imaging tool widely used in medicine. Traditional PET systems rely on complete detector rings for full angular coverage and reliable data collection. However, incomplete-ring PET scanners have emerged due to hardware failures, cost constraints, or specific clinical needs. Standard reconstruction algorithms often suffer from performance degradation with these systems because of reduced data completeness and geometric inconsistencies. We present a two-stage deep-learning framework that, without incorporating any time-of-flight (TOF) information, restores high-quality images from data with about 50% missing coincidences - double the loss levels previously addressed by CNN-based methods. The pipeline operates in two stages: a projection-domain Attention U-Net first predicts the missing sections of the sinogram by leveraging spatial context from neighbouring slices, after which the completed data are reconstructed with OSEM algorithm and passed to a cascaded U-Net & warm-start diffusion model for image refinement. This module starts the reverse diffusion process from the U-Net coarse prediction rather than pure Gaussian noise. Using 613 simulated brain volumes from real scans (196 healthy brain samples, 217 Alzheimer's disease samples, and 200 Mild Cognitive Impairment samples), the result shows that our model successfully preserves most anatomical structures and tracer distribution features with PSNR of 38.18 to 38.59 dB and SSIM of 0.9904 to 0.9925. Our two-stage deep-learning framework effectively restores high-quality PET images from over 50% incomplete-ring data, achieving near-complete anatomical fidelity and robust performance without requiring TOF information.
Authors: Tajamul Ashraf, Rajes Manna, Partha Sarathi Purkayastha, Tavaheed Tariq, Janibul Bashir
Abstract: Source-free object detection (SFOD) faces persistent challenges due to class imbalance-driven context bias and instability in teacher-student training under noisy pseudo-labels. Existing techniques tend to ignore context bias and class-imbalance shifts, especially in medical data. To tackle this, we propose Grounded Teacher (GT), a bias-aware source-free framework that grounds the teacher model through relational and semantic regularization. To explicitly model directional confusion between classes, GT introduces a Relational Context Module (RCM) that maintains an exponential moving average (EMA) estimate of cross-domain contextual bias. Building upon this, a Semantic Augmentation (SA) strategy selectively augments minority and confusable classes through adaptive MixUp in both source-similar and source-dissimilar target regions, improving minority recall without overfitting dominant categories. To stabilize learning under biased pseudo-labels, we design a Semantic-Aware Loss (SAL) that applies diagonally normalized weights, preventing gradient explosion while emphasizing minority-majority corrections. Additionally, a frozen Expert branch derived from large vision foundation models (LVFMs) serves as a supervisory reference during training, refining pseudo-label quality without adding inference overhead. GT's behavior-driven bias quantification makes it broadly applicable across domains without relying on dataset priors. Evaluations on Cityscapes-to-Foggy (50.8 mAP) and medical transfers (+5.9 AP50 on DDSM-to-INBreast) show consistent gains and improved minority-class detection, with less than 12\% additional training cost. Code and model are available at https://github.com/Tajamul21/Grounded-Teacher.
Authors: Linhan Cao, Wei Sun, Xiangyang Zhu, Kaiwei Zhang, Jun Jia, Yicong Peng, Dandan Zhu, Guangtao Zhai, Xiongkuo Min
Abstract: Video quality assessment (VQA) seeks to predict the perceptual quality of a video in alignment with human visual perception, serving as a fundamental tool for quantifying quality degradation across video processing workflows. The dominant VQA paradigm relies on supervised training with human-labeled datasets, which, despite substantial progress, still suffers from poor generalization to unseen video content. In this work, we explore weak-to-strong (W2S) learning as a new paradigm for advancing VQA without reliance on human-labeled datasets. We first provide empirical evidence that a straightforward W2S strategy allows a strong student model to not only match its weak teacher on in-domain benchmarks but also surpass it on out-of-distribution (OOD) benchmarks, revealing a distinct weak-to-strong effect in VQA. Building on this insight, we propose a novel framework that enhances W2S learning from two aspects: (1) integrating homogeneous and heterogeneous supervision signals from diverse VQA teachers -- including off-the-shelf VQA models and synthetic distortion simulators -- via a learn-to-rank formulation, and (2) iterative W2S training, where each strong student is recycled as the teacher in subsequent cycles, progressively focusing on challenging cases. Extensive experiments show that our method achieves state-of-the-art results across both in-domain and OOD benchmarks, with especially strong gains in OOD scenarios. Our findings highlight W2S learning as a principled route to break annotation barriers and achieve scalable generalization in video quality assessment. Our data and code will be available at https://github.com/clh124/W2S-VQA.
Authors: Sriram Mandalika
Abstract: Few-shot adaptation of vision-language models remains fundamentally limited by how negative class signals are handled at inference. Existing methods apply uniform negative suppression across all queries, ignoring that the most damaging confusions are query-specific and shift with support-set geometry. We introduce SCAN (Selective Confusion-Aware Negatives), a framework that addresses this gap through three targeted contributions. In inference, query-adaptive negative routing restricts suppression to the top-K most confusable classes per query, requiring zero additional parameters. Generic negative text templates are replaced with LLM-bootstrapped contrastive prompts that describe discriminative attributes between confusable class pairs, sharpening the textual decision boundary where it matters most. A parameter-free adaptive fusion weight estimated from support-set Fisher discriminability removes the need for manual tuning of the vision-language trade-off. Evaluated across 11 standard benchmarks, SCAN consistently outperforms prior prompt-based and adapter-based methods by an average of 4.61% at 16-shot, with gains of up to 7.70% on fine-grained datasets where inter-class confusion is most severe. SCAN also generalizes strongly under distribution shift, improving by 2.95% on average across four ImageNet OOD variants, and maintains robust performance under significant label noise, with accuracy under 50% label corruption still exceeding the clean baseline of the strongest competing method.
Authors: Sihan Yang, Runsen Xu, Yiman Xie, Sizhe Yang, Mo Li, Jingli Lin, Chenming Zhu, Xiaochen Chen, Haodong Duan, Xiangyu Yue, Dahua Lin, Tai Wang, Jiangmiao Pang
Abstract: Spatial intelligence is essential for multimodal large language models (MLLMs) operating in the complex physical world. Existing benchmarks, however, probe only single-image relations and thus fail to assess the multi-image spatial reasoning that real-world deployments demand. We introduce MMSI-Bench, a VQA benchmark dedicated to multi-image spatial intelligence. Six 3D-vision researchers spent more than 300 hours meticulously crafting 1,000 challenging, unambiguous multiple-choice questions from over 120,000 images, each paired with carefully designed distractors and a stepwise reasoning process. We conduct extensive experiments and evaluate 37 open-source and proprietary MLLMs, observing a wide gap: the strongest open-source model attains roughly 30% accuracy and OpenAI's GPT-5 reasoning model reaches 40%, while humans score 97%. These results underscore the challenging nature of MMSI-Bench and the substantial headroom for future research. Leveraging the annotated reasoning processes, we also provide an automated error analysis pipeline that diagnoses four dominant failure modes, including (1) grounding errors, (2) overlap-matching and scene-reconstruction errors, (3) situation-transformation reasoning errors, and (4) spatial-logic errors, offering insights for advancing spatial intelligence. Project page: https://runsenxu.com/projects/MMSI_Bench .
Authors: Tajamul Ashraf, Amal Saqib, Hanan Ghani, Muhra AlMahri, Yuhao Li, Noor Ahsan, Umair Nawaz, Jean Lahoud, Hisham Cholakkal, Mubarak Shah, Philip Torr, Fahad Shahbaz Khan, Rao Muhammad Anwer, Salman Khan
Abstract: Deep reasoning is fundamental for solving complex tasks, especially in vision-centric scenarios that demand sequential, multimodal understanding. However, existing benchmarks typically evaluate agents with fully synthetic, single-turn queries, limited visual modalities, and lack a framework to assess reasoning quality over multiple steps as required in real-world settings. To address this, we introduce Agent-X, a large-scale benchmark for evaluating vision-centric agents multi-step and deep reasoning capabilities in real-world, multimodal settings. Agent- X features 828 agentic tasks with authentic visual contexts, including images, multi-image comparisons, videos, and instructional text. These tasks span six major agentic environments: general visual reasoning, web browsing, security and surveillance, autonomous driving, sports, and math reasoning. Our benchmark requires agents to integrate tool use with explicit, stepwise decision-making in these diverse settings. In addition, we propose a fine-grained, step-level evaluation framework that assesses the correctness and logical coherence of each reasoning step and the effectiveness of tool usage throughout the task. Our results reveal that even the best-performing models, including GPT, Gemini, and Qwen families, struggle to solve multi-step vision tasks, achieving less than 50% full-chain success. These findings highlight key bottlenecks in current LMM reasoning and tool-use capabilities and identify future research directions in vision-centric agentic reasoning models. Our data and code are publicly available at https://github.com/mbzuai-oryx/Agent-X
Authors: Kailing Li, Qi'ao Xu, Tianwen Qian, Yuqian Fu, Yang Jiao, Xiaoling Wang
Abstract: Embodied Visual Reasoning (EVR) seeks to follow complex, free-form instructions based on egocentric video, enabling semantic understanding and spatiotemporal reasoning in dynamic environments. Despite its promising potential, EVR encounters significant challenges stemming from the diversity of complex instructions and the intricate spatiotemporal dynamics in long-term egocentric videos. Prior solutions either employ Large Language Models (LLMs) over static video captions, which often omit critical visual details, or rely on end-to-end Vision-Language Models (VLMs) that struggle with stepwise compositional reasoning. Consider the complementary strengths of LLMs in reasoning and VLMs in perception, we propose CLiViS. It is a novel training-free framework that leverages LLMs for high-level task planning and orchestrates VLM-driven open-world visual perception to iteratively update the scene context. Building on this synergy, the core of CLiViS is a dynamic Cognitive Map that evolves throughout the reasoning process. This map constructs a structured representation of the embodied scene, bridging low-level perception and high-level reasoning. Extensive experiments across multiple benchmarks demonstrate the effectiveness and generality of CLiViS, especially in handling long-term visual dependencies. Code is available at https://github.com/Teacher-Tom/CLiViS.
Authors: Christina Ourania Tze, Daniel Dauner, Yiyi Liao, Dzmitry Tsishkou, Andreas Geiger
Abstract: Existing approaches to 3D semantic urban scene generation predominantly rely on voxel-based representations, which are bound by fixed resolution, challenging to edit, and memory-intensive in their dense form. In contrast, we advocate for a primitive-based paradigm where urban scenes are represented using compact, semantically meaningful 3D elements that are easy to manipulate and compose. To this end, we introduce PrITTI, a latent diffusion model that leverages vectorized object primitives and rasterized ground surfaces for generating diverse, controllable, and editable 3D semantic urban scenes. This hybrid representation yields a structured latent space that facilitates object- and ground-level manipulation. Experiments on KITTI-360 show that primitive-based representations unlock the full capabilities of diffusion transformers, achieving state-of-the-art 3D scene generation quality with lower memory requirements, faster inference, and greater editability than voxel-based methods. Beyond generation, PrITTI supports a range of downstream applications, including scene editing, inpainting, outpainting, and photo-realistic street-view synthesis. The source code and more results can be found at https://raniatze.github.io/pritti/.
Authors: Beomjun Kim, Suhan Woo, Sejong Heo, Euntai Kim
Abstract: Bird's-Eye-View (BEV) map segmentation is one of the most important and challenging tasks in autonomous driving. Camera-only approaches have drawn attention as cost-effective alternatives to LiDAR, but they still fall behind LiDAR-Camera (LC) fusion-based methods. Knowledge Distillation (KD) has been explored to narrow this gap, but existing methods mainly enlarge the student model by mimicking the teacher's architecture, leading to higher inference cost. To address this issue, we introduce BridgeTA, a cost-effective distillation framework to bridge the representation gap between LC fusion and Camera-only models through a Teacher Assistant (TA) network while keeping the student's architecture and inference cost unchanged. A lightweight TA network combines the BEV representations of the teacher and student, creating a shared latent space that serves as an intermediate representation. To ground the framework theoretically, we derive a distillation loss using Young's Inequality, which decomposes the direct teacher-student distillation path into teacher-TA and TA-student dual paths, stabilizing optimization and strengthening knowledge transfer. Extensive experiments on the challenging nuScenes dataset demonstrate the effectiveness of our method, achieving an improvement of 4.2% mIoU over the Camera-only baseline, up to 45% higher than the improvement of other state-of-the-art KD methods.
Authors: Yukang Lin, Xiang Zhang, Shichang Jia, Bowen Wan, Chenghan Fu, Xudong Ren, Yueran Liu, Wanxian Guan, Pengji Wang, Jian Xu, Bo Zheng, Baolin Liu
Abstract: Creative image in advertising is the heart and soul of e-commerce platform. An eye-catching creative image can enhance the shopping experience for users, boosting income for advertisers and advertising revenue for platforms. With the advent of AIGC technology, advertisers can produce large quantities of creative images at minimal cost. However, they struggle to assess the creative quality to select. Existing methods primarily focus on creative ranking, which fails to address the need for explainable creative selection. In this work, we propose the first paradigm for explainable creative assessment and selection. Powered by multimodal large language models (MLLMs), our approach integrates the assessment and selection of creative images into a natural language generation task. To facilitate this research, we construct CreativePair, the first comparative reasoning-induced creative dataset featuring 8k annotated image pairs, with each sample including a label indicating which image is superior. Additionally, we introduce Creative4U (pronounced Creative for You), a MLLMs-based creative selector that takes into account users' interests. Through Reason-to-Select RFT, which includes supervised fine-tuning with Chain-of-Thought (CoT-SFT) and Group Relative Policy Optimization (GRPO) based reinforcement learning, Creative4U is able to evaluate and select creative images accurately. Both offline and online experiments demonstrate the effectiveness of our approach. Our code and dataset will be made public to advance research and industrial applications.
Authors: Abdullah Al Nomaan Nafi, Habibur Rahaman, Zafaryab Haider, Tanzim Mahfuz, Fnu Suya, Swarup Bhunia, Prabuddha Chakraborty
Abstract: Numerous techniques have been proposed for generating adversarial examples in white-box settings under strict Lp-norm constraints. However, such norm-bounded examples often fail to align well with human perception, and only a few methods specifically explore perceptually aligned adversarial examples. Moreover, it remains unclear whether insights from Lp-constrained attacks can be effectively leveraged to improve perceptual efficacy. In this paper, we introduce DASH, a fully differentiable meta-attack framework that generates effective and perceptually aligned adversarial examples by strategically composing existing Lp-based attack methods. DASH operates in a multi-stage fashion: at each stage, it aggregates candidate adversarial examples from multiple base attacks using learned, adaptive weights and propagates the result to the next stage. A novel meta-loss function guides this process by jointly minimizing misclassification loss and perceptual distortion, enabling the framework to dynamically modulate the contribution of each base attack throughout the stages. We evaluate DASH on adversarially trained models across CIFAR-10, CIFAR-100, and ImageNet. Despite relying solely on Lp-constrained based methods, DASH significantly outperforms state-of-the-art perceptual attacks such as AdvAD, achieving higher attack success rates (e.g., 20.63% improvement) and superior visual quality, as measured by SSIM, LPIPS, and FID (improvements $\approx$ of 11, 0.015, and 5.7, respectively). Furthermore, DASH generalizes well to unseen defenses, making it a practical and strong baseline for evaluating robustness without requiring handcrafted adaptive attacks for each new defense.
Authors: Luu Tu Nguyen, Vu Tram Anh Khuong, Thanh Ha Le, Thi Duyen Ngo
Abstract: Micro-expression recognition (MER) is a challenging task due to the subtle and fleeting nature of micro-expressions. Traditional input modalities, such as Apex Frame, Optical Flow, and Dynamic Image, often fail to adequately capture these brief facial movements, resulting in suboptimal performance. In this study, we introduce the Micro-expression Spatio-Temporal Image (MESTI), a micro-expression-specific reformulation of dynamic rank pooling that transforms a video sequence into a single image while emphasizing the onset-apex-offset temporal pattern of micro-expressions. Additionally, we present the Micro-expression Gradient Attention Network (MEGANet), which incorporates a proposed Gradient Attention block to enhance the extraction of fine-grained motion features from micro-expressions. By combining MESTI and MEGANet, we aim to establish a more effective approach to MER. Extensive experiments were conducted to evaluate the effectiveness of MESTI, comparing it with existing input modalities across regular architectures. Moreover, we demonstrate that replacing the input of previously published MER networks with MESTI leads to consistent performance improvements. The performance of MEGANet is also evaluated, showing that our proposed network achieves state-of-the-art results on the SMIC-HS, SAMM and competitive performance on CASMEII datasets, it also achieves leading performance in the reported cross-dataset evaluation settings. The combination of MESTI and MEGANet consistently outperforms the compared methods. These findings underscore the potential of MESTI as a superior input modality and MEGANet as an advanced recognition network, aiming to more effective MER systems in a variety of applications.
Authors: Dejia Cai, Ali Abdollahi, Xi Wang, Kun Yang, Zhaohui Guo, Xiaowei Zhou, Hao Chen
Abstract: High-Intensity Focused Ultrasound (HIFU) is a non-invasive therapy, yet its safety is often degraded by severe acoustic interference during continuous ultrasound guidance. Conventional HIFU interference suppression methods heavily rely on proprietary raw Radio-Frequency (RF) data or complex hardware synchronization, limiting their clinical utility and preventing real-time implementation. To address this limitation, we propose Manifold-Constrained Hyper-Connections Diffusion (mHC-Diff), an image-domain diffusion framework for real-time interference suppression without specialized hardware synchronization, disentangling complex interference from anatomical structures while ensuring high reconstruction fidelity. To achieve clinical real-time application, our approach employs a two-stage strategy: (i) anatomy-aware prior acquisition, where a diffusion model is trained with multi-step UNet as a highfidelity Teacher; and (ii) efficiency distillation, where this prior is distilled into a one-step Student via knowledge distillation to achieve real-time throughput. Extensive validation on a clinically representative dataset across diverse therapeutic scenarios shows that mHC-Diff achieves superior restoration (26.65 dB PSNR), while enabling real-time inference (~20 FPS) on a single NVIDIA RTX 4090, providing a ~6.8x speedup over iterative diffusion baselines (e.g., HIFU-Diff). By eliminating the requirement for specialized hardware synchronization and proprietary RF access, this image-domain framework ensures compatibility and facilitates real-time interference suppression during ultrasound-guided HIFU interventions.
Authors: Hanzhen Wang, Jiaming Xu, Yushun Xiang, Jiayi Pan, Yongkang Zhou, Yong-Lu Li, Guohao Dai
Abstract: Pruning is a typical acceleration technique for compute-bound models by removing computation on unimportant values. Recently, it has been applied to accelerate Vision-Language-Action (VLA) model inference. However, existing acceleration methods focus on local information from the current action step and ignore the global context, leading to >20% success rate drop and limited speedup in some scenarios. In this paper, we point out spatial-temporal consistency in VLA tasks: input images in consecutive steps exhibit high similarity, and propose the key insight that token selection should combine local information with global context of the model. Based on this, we propose SpecPrune-VLA, a training-free, two-level pruning method with heuristic control. (1) Action-level static pruning. We leverage global history and local attention to statically reduce visual tokens per action. (2) Layer-level dynamic pruning. We prune tokens adaptively per layer based on layer-wise importance. (3) Lightweight action-aware controller: We classify actions as coarse- or fine-grained by the speed of the end effector and adjust pruning aggressiveness accordingly. Extensive experiments show that SpecPrune-VLA achieves up to 1.57$\times$ speedup in LIBERO simulation and 1.70$\times$ on real-world tasks, with negligible success rate degradation.
Authors: Bingkui Tong, Jiaer Xia, Sifeng Shang, Kaiyang Zhou
Abstract: Hallucinations in multimodal large language models (MLLMs) -- where the model generates content inconsistent with the input image -- pose significant risks in real-world applications, from misinformation in visual question answering to unsafe errors in decision-making. Existing benchmarks primarily test recognition accuracy, i.e., evaluating whether models can select the correct answer among distractors. This overlooks another important capability for trustworthy AI: recognizing when none of the provided options is supported by the image and abstaining from committing to a false choice, a humility-related behavior. We present HumbleBench, a new hallucination benchmark designed to evaluate false-option rejection in MLLMs under a forced-choice multiple-choice setting with a ``None of the above'' option. Built from a panoptic scene graph dataset, we leverage fine-grained scene graph annotations for objects and relations, use candidate attribute cues, and prompt GPT-4-Turbo to generate multiple-choice questions, followed by a rigorous manual filtering process. Each question includes a ``None of the above'' option, requiring models not only to recognize correct visual information but also to identify when no provided answer is valid. We evaluate a variety of state-of-the-art MLLMs -- including general-purpose, specialized reasoning, and proprietary models -- on HumbleBench and report empirical findings for the community. By incorporating explicit false-option rejection, HumbleBench fills a key gap in current evaluation suites by assessing a narrower but important abstention-oriented behavior that is relevant to trustworthy multimodal reasoning. Our code and dataset are released publicly and can be accessed at \href{https://github.com/maifoundations/HumbleBench}{https://github.com/maifoundations/HumbleBench}.
URLs: https://github.com/maifoundations/HumbleBench, https://github.com/maifoundations/HumbleBench
Authors: Gabrijel Boduljak, Laurynas Karazija, Iro Laina, Christian Rupprecht, Andrea Vedaldi
Abstract: We consider the problem of forecasting motion from a single image, i.e., predicting how objects in the world are likely to move, without the ability to observe other parameters such as the object velocities or the forces applied to them. We formulate this task as conditional generation of dense trajectory grids with a model that closely follows the architecture of modern video generators but outputs motion trajectories instead of pixels. This approach captures scene-wide dynamics and uncertainty, yielding more accurate and diverse predictions than prior regressors and generators. We extensively evaluate our method on simulated data, demonstrate its effectiveness on downstream applications such as robotics, and show promising accuracy on real-world intuitive physics datasets. Although recent state-of-the-art video generators are often regarded as world models, we show that they struggle with forecasting motion from a single image, even in simple physical scenarios such as falling blocks or mechanical object interactions, despite fine-tuning on such data. We show that this limitation arises from the overhead of generating pixels rather than directly modeling motion.
Authors: Yuhan Zhu, Xiangyu Zeng, Chenting Wang, Xinhao Li, Chunxu Liu, Yicheng Xu, Ziang Yan, Yi Wang, Limin Wang
Abstract: Multimodal large language models (MLLMs) are emerging as versatile foundations for mixed-modality retrieval. Yet, they often require heavy post-hoc training to convert them into contrastive encoders for retrieval. This work asks: Can off-the-shelf MLLMs serve as powerful retrievers without additional training? We present FreeRet, a plug-and-play framework that turns any MLLM into a two-stage retriever. FreeRet first derives semantically grounded embeddings directly from the model for fast candidate search, and then exploits its reasoning ability for precise reranking. The framework contributes three advances: bypassing lexical alignment layers to obtain semantically faithful embeddings, conditioning representation generation with explicit priors, and mitigating framing effect in reranking via neutral choice framing. On the MMEB and MMEB-V2 benchmarks spanning 46 datasets, FreeRet substantially outperforms models trained on millions of pairs. Beyond benchmarks, FreeRet is model-agnostic and scales seamlessly across MLLM families and sizes, preserves their generative abilities, supports arbitrary modality combinations, and unifies retrieval, reranking, and generation into end-to-end RAG within a single model. Our findings demonstrate that pretrained MLLMs, when carefully harnessed, can serve as strong retrieval engines without training, closing a critical gap in their role as generalists.
Authors: Paul Gavrikov, Wei Lin, M. Jehanzeb Mirza, Soumya Jahagirdar, Muhammad Huzaifa, Sivan Doveh, Serena Yeung-Levy, James Glass, Hilde Kuehne
Abstract: Is basic visual understanding really solved in state-of-the-art VLMs? We present VisualOverload, a slightly different visual question answering (VQA) benchmark comprising 2,720 question-answer pairs, with privately held ground-truth responses. Unlike prior VQA datasets that typically focus on near global image understanding, VisualOverload challenges models to perform simple, knowledge-free vision tasks in densely populated (or, overloaded) scenes. Our dataset consists of high-resolution scans of public-domain paintings that are populated with multiple figures, actions, and unfolding subplots set against elaborately detailed backdrops. We manually annotated these images with questions across six task categories to probe for a thorough understanding of the scene. We hypothesize that current benchmarks overestimate the performance of VLMs, and encoding and reasoning over details is still a challenging task for them, especially if they are confronted with densely populated scenes. Indeed, we observe that even the best model (o3) out of 37 tested models only achieves 19.6% accuracy on our hardest test split and overall 69.5% accuracy on all questions. Beyond a thorough evaluation, we complement our benchmark with an error analysis that reveals multiple failure modes, including a lack of counting skills, failure in OCR, and striking logical inconsistencies under complex tasks. Altogether, VisualOverload exposes a critical gap in current vision models and offers a crucial resource for the community to develop better models. Benchmark: http://paulgavrikov.github.io/visualoverload
Authors: Xueyang Zhou, Yangming Xu, Guiyao Tie, Yongchao Chen, Guowen Zhang, Duanfeng Chu, Pan Zhou, Lichao Sun
Abstract: LIBERO has emerged as a widely adopted benchmark for evaluating Vision-Language-Action (VLA) models; however, its current training and evaluation settings are problematic, often leading to inflated performance estimates and preventing fair model comparison. To address these issues, we introduce LIBERO-PRO, an extended LIBERO benchmark that systematically evaluates model performance under reasonable perturbations across four dimensions: manipulated objects, initial states, task instructions, and environments. Experimental results reveal that, although existing models achieve over 90% accuracy under the standard LIBERO evaluation, their performance collapses to 0.0% under our generalized setting. Crucially, this discrepancy exposes the models' reliance on rote memorization of action sequences and environment layouts from the training set, rather than genuine task understanding or environmental perception. For instance, models persist in executing grasping actions when the target object is replaced with irrelevant items, and their outputs remain unchanged even when given corrupted instructions or even messy tokens. These findings expose the severe flaws in current evaluation practices, and we call on the community to abandon misleading methodologies in favor of robust assessments of model generalization and comprehension. Our code is available at: https://github.com/Zxy-MLlab/LIBERO-PRO.
Authors: Chunyu Xie, Bin Wang, Fanjing Kong, Jincheng Li, Dawei Liang, Ji Ao, Dawei Leng, Yuhui Yin
Abstract: Fine-grained vision-language understanding requires precise alignment between visual content and linguistic descriptions, a capability that remains limited in current models, particularly in non-English settings. While models like CLIP perform well on global alignment, they often struggle to capture fine-grained details in object attributes, spatial relations, and linguistic expressions, with limited support for bilingual comprehension. To address these challenges, we introduce FG-CLIP 2, a bilingual vision-language model designed to advance fine-grained alignment for both English and Chinese. Our approach leverages rich fine-grained supervision, including region-text matching and long-caption modeling, alongside multiple discriminative objectives. We further introduce the Textual Intra-modal Contrastive (TIC) loss to better distinguish semantically similar captions. Trained on a carefully curated mixture of large-scale English and Chinese data, including a newly released 12M Chinese region-text dataset, FG-CLIP 2 achieves powerful bilingual performance. To enable rigorous evaluation, we present a new benchmark for Chinese multimodal understanding, featuring long-caption retrieval and bounding box classification. Extensive experiments on 29 datasets across 8 tasks show that FG-CLIP 2 outperforms existing methods, achieving state-of-the-art results in both languages. We release the model, code, and benchmark to facilitate future research on bilingual fine-grained vision-language alignment.
Authors: Lin Zhu, Yifeng Yang, Xinbing Wang, Qinying Gu, Nanyang Ye
Abstract: Recent approaches for vision-language models (VLMs) have shown remarkable success in achieving fast downstream adaptation. When applied to real-world downstream tasks, VLMs inevitably encounter both the in-distribution (ID) data and out-of-distribution (OOD) data. The OOD datasets often include both covariate shifts (e.g., known classes with changes in image styles) and semantic shifts (e.g., test-time unseen classes). This highlights the importance of improving VLMs' generalization ability to covariate-shifted OOD data, while effectively detecting open-set semantic-shifted OOD classes. In this paper, inspired by the substantial energy change observed in closed-set data when re-aligning vision-language modalities (specifically by directly reducing the maximum cosine similarity to a low value), we introduce a novel OOD score, named {\Delta}Energy. {\Delta}Energy significantly outperforms the vanilla energy-based OOD score and provides a more reliable approach for OOD detection. Furthermore, {\Delta}Energy can simultaneously improve OOD generalization under covariate shifts, which is achieved by lower-bound maximization for {\Delta}Energy (termed EBM). EBM is theoretically proven to not only enhance OOD detection but also yields a domain-consistent Hessian, which serves as a strong indicator for OOD generalization. Based on this finding, we developed a unified fine-tuning framework that allows for improving VLMs' robustness in both OOD generalization and OOD detection. Extensive experiments on challenging OOD detection and generalization benchmarks demonstrate the superiority of our method, outperforming recent approaches by 10% to 25% in AUROC.
Authors: Mihai-Cristian P\^irvu, Marius Leordeanu
Abstract: The real-world is inherently multi-modal at its core. Our tools observe and take snapshots of it, in digital form, such as videos or sounds, however much of it is lost. Similarly for actions and information passing between humans, languages are used as a written form of communication. Traditionally, Machine Learning models have been unimodal (i.e. rgb -> semantic or text -> sentiment_class). Recent trends go towards bi-modality, where images and text are learned together, however, in order to truly understand the world, we need to integrate all these independent modalities. In this work we try to combine as many visual modalities as we can using little to no human supervision. In order to do this, we use pre-trained experts and procedural combinations between them on top of raw videos using a fully autonomous data-pipeline, which we also open-source. We then make use of PHG-MAE, a model specifically designed to leverage multi-modal data. We show that this model which was efficiently distilled into a low-parameter (<1M) can have competitive results compared to models of ~300M parameters. We deploy this model and analyze the use-case of real-time semantic segmentation from handheld devices or webcams on commodity hardware. Finally, we deploy other off-the-shelf models using the same framework, such as DPT for near real-time depth estimation.
Authors: Weijie Wang, Jiagang Zhu, Zeyu Zhang, Xiaofeng Wang, Zheng Zhu, Guosheng Zhao, Chaojun Ni, Haoxiao Wang, Guan Huang, Xinze Chen, Yukun Zhou, Wenkang Qin, Duochao Shi, Haoyun Li, Yicheng Xiao, Donny Y. Chen, Jiwen Lu
Abstract: We present DriveGen3D, a novel framework for generating high-quality and highly controllable dynamic 3D driving scenes that addresses critical limitations in existing methodologies. Current approaches to driving scene synthesis either suffer from prohibitive computational demands for extended temporal generation, focus exclusively on prolonged video synthesis without 3D representation, or restrict themselves to static single-scene reconstruction. Our work bridges this methodological gap by integrating accelerated long-term video generation with large-scale dynamic scene reconstruction through multimodal conditional control. DriveGen3D introduces a unified pipeline consisting of two specialized components: FastDrive-DiT, an efficient video diffusion transformer for high-resolution, temporally coherent video synthesis under text and Bird's-Eye-View (BEV) layout guidance; and FastRecon3D, a feed-forward module that rapidly builds 3D Gaussian representations across time, ensuring spatial-temporal consistency. DriveGen3D enable the generation of long driving videos (up to $800\times424$ at $12$ FPS) and corresponding 3D scenes, achieving state-of-the-art results while maintaining efficiency.
Authors: Zahraa Al Sahili, Maimuna Nowaz, Maryam Fetanat, Ioannis Patras, Matthew Purver
Abstract: Evaluating text-to-image (T2I) systems requires judging not only whether an image matches a prompt, but also whether socially salient attributes are represented faithfully and without unsupported inference. Existing automated evaluators typically rely on face-centric recognizers or contrastive image--text similarity, which provide limited diagnostic feedback and often force predictions even when visual evidence is ambiguous or absent. For fairness-sensitive attributes such as religion and disability, where cues may be contextual, indirect, or intentionally unspecified, these evaluators can therefore miss failure modes that careful human reviewers would notice. We introduce \textsc{FairJudge}, an abstention-aware evaluation protocol that uses instruction-following multimodal LLMs as structured judges for social-attribute prediction, profession grounding, and prompt--image alignment. The protocol constrains outputs to closed label sets, requires visible-evidence rationales, supports an explicit \textsc{unspecified} decision when cues are insufficient, and maps rubric-based alignment judgments to $[-1,1]$. These constraints turn MLLM judging from open-ended assessment into a parseable, auditable evaluation procedure. Across four attribute-prediction benchmarks and three profession/alignment benchmarks, \textsc{FairJudge} outperforms or complements CLIP, DeepFace, VIEScore, and VQAScore. Ablations show that closed labels, abstention, and evidence reporting are central to reliability. We further introduce \textsc{DIVERSIFY} and \textsc{DIVERSIFY-Professions}, two context-rich resources for evaluating social representation and profession grounding beyond face-visible or iconic cues. We release code, prompts, datasets, parser logs, and per-image judge outputs to support reproducible auditing.
Authors: Bohan Li, Xin Jin, Hu Zhu, Hongsi Liu, Ruikai Li, Jiazhe Guo, Kaiwen Cai, Chao Ma, Yueming Jin, Hao Zhao, Xiaokang Yang, Wenjun Zeng
Abstract: Driving scene generation is a critical domain for autonomous driving, enabling downstream applications, including perception and planning evaluation. Occupancy-centric methods have recently achieved state-of-the-art results by offering consistent conditioning across frames and modalities; however, their performance heavily depends on annotated occupancy data, which still remains scarce. To overcome this limitation, we curate Nuplan-Occ, the largest semantic occupancy dataset to date, constructed from the widely used Nuplan benchmark. Its scale and diversity facilitate not only large-scale generative modeling but also autonomous driving downstream applications. Based on this dataset, we develop a unified framework that jointly synthesizes high-quality semantic occupancy, multi-view videos, and LiDAR point clouds. Our approach incorporates a spatio-temporal disentangled architecture to support high-fidelity spatial expansion and temporal forecasting of 4D dynamic occupancy. To bridge modal gaps, we further propose two novel techniques: a Gaussian splatting-based sparse point map rendering strategy that enhances multi-view video generation, and a sensor-aware embedding strategy that explicitly models LiDAR sensor properties for realistic multi-LiDAR simulation. Extensive experiments demonstrate that our method achieves superior generation fidelity and scalability compared to existing approaches, and validates its practical value in downstream tasks. Repo: https://github.com/Arlo0o/UniScene-Unified-Occupancy-centric-Driving-Scene-Generation/tree/v2
URLs: https://github.com/Arlo0o/UniScene-Unified-Occupancy-centric-Driving-Scene-Generation/tree/v2
Authors: Ziyan Liu, Yeqiu Chen, Hongyi Cai, Tao Lin, Shuo Yang, Zheng Liu, Bo Zhao
Abstract: Vision-Language-Action (VLA) models have shown great potential for embodied AI by integrating visual perception, language understanding, and action execution. In real-time deployment, these models must process continuous visual streams, incurring substantial computational overhead. Visual token pruning -- a mainstream technique for accelerating Vision-Language Models (VLMs) by retaining salient tokens while discarding redundant ones -- offers a natural candidate solution to this challenge. However, directly applying VLM-oriented pruning methods to VLA inference can cause severe degradation in manipulation performance. Our analysis attributes this degradation to a key mismatch: VLA inference exhibits distinct attention patterns between the vision-language prefill stage and the action-decode stage, so pruning based only on context-prefill semantic salience is biased toward semantic cues and may remove action-critical visual tokens. Motivated by this observation, we propose VLA-Pruner, an effective plug-and-play token pruning method grounded in the visual requirements of VLA inference, further exploiting the temporal continuity of robot manipulation. Specifically, VLA-Pruner estimates visual-token importance from both semantic prefilling and temporally smoothed action relevance, and then applies a Combine-then-Filter strategy to retain compact, non-redundant tokens under the compute budget. Experiments show that VLA-Pruner outperforms state-of-the-art approaches across multiple VLA architectures, achieving up to 1.99x speedup with comparable manipulation quality.
Authors: Jin-Young Kim, Hyojun Go, Lea Bogensperger, Julius Erbach, Nikolai Kalischek, Federico Tombari, Konrad Schindler, Dominik Narnhofer
Abstract: MeanFlow promises high-quality generative modeling in few steps, by jointly learning instantaneous and average velocity fields. Yet, the underlying training dynamics remain unclear. We analyze the interaction between the two velocities and find: (i) well-established instantaneous velocity is a prerequisite for learning average velocity; (ii) learning of instantaneous velocity benefits from average velocity when the temporal gap is small, but degrades as the gap increases; and (iii) task-affinity analysis indicates that smooth learning of large-gap average velocities, essential for one-step generation, depends on the prior formation of accurate instantaneous and small-gap average velocities. Guided by these observations, we design an effective training scheme that accelerates the formation of instantaneous velocity, then shifts emphasis from short- to long-interval average velocity. Our enhanced MeanFlow training yields faster convergence and significantly better few-step generation: With the same DiT-XL backbone, our method reaches an impressive FID of 2.87 on 1-NFE ImageNet 256x256, compared to 3.43 for the conventional MeanFlow baseline. Alternatively, our method matches the performance of the MeanFlow baseline with 2.5x shorter training time, or with a smaller DiT-L backbone.
Authors: Yuke Li, Lianli Gao, Ji Zhang, Pengpeng Zeng, Lichuan Xiang, Hongkai Wen, Heng Tao Shen, Jingkuan Song
Abstract: Exemplar-guided Image Editing (EIE) aims to modify a source image according to a visual reference. Existing approaches often require large-scale pre-training to learn relationships between the source and reference images, incurring high computational costs. As a training-free alternative, inversion techniques can be used to map the source image into a latent space for manipulation. However, our empirical study reveals that standard inversion is sub-optimal for EIE, leading to poor quality and inefficiency. To tackle this challenge, we introduce \textbf{Reversible Inversion ({ReInversion})} for effective and efficient EIE. Specifically, ReInversion operates as a two-stage denoising process, which is first conditioned on the source image and subsequently on the reference. Besides, we introduce a Mask-Guided Selective Denoising (MSD) strategy to constrain edits to target regions, preserving the structural consistency of the background. Both qualitative and quantitative comparisons demonstrate that our ReInversion method achieves state-of-the-art EIE performance with the lowest computational overhead.
Authors: Yihong Tang, Haicheng Liao, Tong Nie, Junlin He, Ao Qu, Kehua Chen, Wei Ma, Zhenning Li, Lijun Sun, Chengzhong Xu
Abstract: End-to-end autonomous driving (AD) systems increasingly adopt vision-language-action (VLA) models, yet they typically ignore the passenger's emotional state, which is central to comfort and AD acceptance. We introduce Open-Domain End-to-End (OD-E2E) autonomous driving, where an autonomous vehicle (AV) must interpret free-form natural-language commands, infer the emotion, and plan a physically feasible trajectory. We propose E3AD, an emotion-aware VLA framework that augments semantic understanding with two cognitively inspired components: a continuous Valenc-Arousal-Dominance (VAD) emotion model that captures tone and urgency from language, and a dual-pathway spatial reasoning module that fuses egocentric and allocentric views for human-like spatial cognition. A consistency-oriented training scheme, combining modality pretraining with preference-based alignment, further enforces coherence between emotional intent and driving actions. Across real-world datasets, E3AD improves visual grounding and waypoint planning and achieves state-of-the-art (SOTA) VAD correlation for emotion estimation. These evaluation results show that injecting emotion into VLA-style driving yields more human-aligned grounding, planning, and feedback.
Authors: Jiawen Wen, Yu Hu, Suixuan Qiu, Jinshan Huang, Xiaowen Chu
Abstract: Real-time tracking of small unmanned aerial vehicles (UAVs) on edge devices faces a fundamental resolution-speed conflict. Downsampling high-resolution imagery to standard detector input sizes causes small target features to collapse below detectable thresholds. Yet processing native 1080p frames on resource-constrained platforms yields insufficient throughput for smooth gimbal control. We propose SDG-Track, a Sparse Detection-Guided Tracker that adopts an Observer-Follower architecture to reconcile this conflict. The Observer stream runs a high-capacity detector at low frequency on the GPU to provide accurate position anchors from 1920x1080 frames. The Follower stream performs high-frequency trajectory interpolation via ROI-constrained sparse optical flow on the CPU. To handle tracking failures from occlusion or model drift caused by spectrally similar distractors, we introduce Dual-Space Recovery, a training-free re-acquisition mechanism combining color histogram matching with geometric consistency constraints. Experiments on a ground-to-air tracking station demonstrate that SDG-Track achieves 35.1 FPS system throughput while retaining 97.2\% of the frame-by-frame detection precision. The system successfully tracks agile FPV drones under real-world operational conditions on an NVIDIA Jetson Orin Nano. Our paper code is publicly available at https://github.com/Jeffry-wen/SDG-Track
Authors: Yun Liu, Tao Li, Guanghui Yue, Wenqi Ren, Cosmin Ancuti, Weisi Lin
Abstract: Scene recovery from real-world images degraded by scattering effects, such as haze, sandstorm, underwater, and remote sensing conditions, remains a fundamental yet challenging problem in computer vision. Existing methods either rely on a single prior, which is inherently insufficient to characterize diverse scattering degradations, or employ deep networks trained on synthetic data, which often suffer from limited generalization to real-world scenarios. In this paper, we propose Spatial and Frequency Priors (SFP) for real-world scene recovery under scattering-induced degradations. In the spatial domain, we observe that the inverse of a scattering-degraded image reveals a projection along its spectral direction that correlates with the underlying scene transmission. Based on this observation, a spatial prior is formulated to estimate the transmission map, enabling effective recovery of scene radiance under scattering effects. In the frequency domain, we design an adaptive frequency enhancement strategy guided by two novel priors. The first prior assumes that the mean intensity of the direct current (DC) components across channels in degraded images approximates that of the corresponding clear images. The second prior is based on the observation that, in clear images, low radial frequencies within a narrow band contribute only a small proportion of the overall spectrum. These priors enable targeted compensation for scattering-induced attenuation across different frequency bands. Finally, a weighted fusion of the spatial and frequency domain results is performed to obtain the final recovered image. Extensive experiments on diverse real-world scattering-degraded scenarios verify that our SFP achieves superior performance and strong generalization capability compared to state-of-the-art methods.
Authors: Yuchen Feng, Zhenyu Zhang, Naibin Gu, Yilong Chen, Peng Fu, Zheng Lin, Shuohuan Wang, Yu Sun, Hua Wu, Weiping Wang, Haifeng Wang
Abstract: Multimodal large language models (MLLMs) have achieved remarkable progress on various vision-language tasks, yet their visual perception remains limited. Humans, in comparison, perceive complex scenes efficiently by dynamically scanning and focusing on salient regions in a sequential "blink-like" process. Motivated by this strategy, we first investigate whether MLLMs exhibit similar behavior. Our pilot analysis reveals that MLLMs naturally attend to different visual regions across layers and that selectively allocating more computation to salient tokens can enhance visual perception. Building on this insight, we propose Blink, a dynamic visual token resolution framework that emulates the human-inspired process within a single forward pass. Specifically, Blink includes two modules: saliency-guided scanning and dynamic token resolution. It first estimates the saliency of visual tokens in each layer based on the attention map, and extends important tokens through a plug-and-play token super-resolution (TokenSR) module. In the next layer, it drops the extended tokens when they lose focus. This dynamic mechanism balances broad exploration and fine-grained focus, thereby enhancing visual perception adaptively and efficiently. Extensive experiments validate Blink, demonstrating its effectiveness in enhancing visual perception and multimodal understanding.
Authors: Jingmin Zhu, Anqi Zhu, James Bailey, Jun Liu, Hossein Rahmani, Mohammed Bennamoun, Farid Boussaid, Qiuhong Ke
Abstract: Zero-shot skeleton-based action recognition (ZS-SAR) is fundamentally constrained by prevailing approaches that rely on aligning skeleton features with static, class-level semantics. This coarse-grained alignment fails to bridge the domain shift between seen and unseen classes, thereby impeding the effective transfer of fine-grained visual knowledge. To address these limitations, we introduce \textbf{DynaPURLS}, a unified framework that establishes robust, multi-scale visual-semantic correspondences and dynamically refines them at inference time to enhance generalization. Our framework leverages a large language model to generate hierarchical textual descriptions that encompass both global movements and local body-part dynamics. Concurrently, an adaptive partitioning module produces fine-grained visual representations by semantically grouping skeleton joints. To fortify this fine-grained alignment against the train-test domain shift, DynaPURLS incorporates a dynamic refinement module. During inference, this module adapts textual features to the incoming visual stream via a lightweight learnable projection. This refinement process is stabilized by a confidence-aware, class-balanced memory bank, which mitigates error propagation from noisy pseudo-labels. Extensive experiments on three large-scale benchmark datasets, including NTU RGB+D 60/120 and PKU-MMD, demonstrate that DynaPURLS significantly outperforms prior art, setting new state-of-the-art records. The source code is made publicly available at https://github.com/Alchemist0754/DynaPURLS
Authors: Hangwei Zhang, Armando Fortes, Tianyi Wei, Xingang Pan
Abstract: Bokeh rendering and depth estimation share a fundamental optical connection, yet existing methods fail to fully exploit this reciprocity. Conventional bokeh pipelines rely heavily on noisy depth maps that inevitably introduce visual artifacts. Conversely, existing monocular depth models typically follow two flawed paradigms. Generative diffusion-based frameworks often lack consistent metric scale. Meanwhile, feed-forward metric depth models frequently fail in textureless or distant regions where defocus blur can provide geometric information. We propose BokehDepth, a two-stage framework that treats synthetic defocus as a supervision-free geometric signal. In the first stage, a physically grounded generative model produces calibrated bokeh stacks from a single sharp input without requiring prior depth input. Subsequently, a lightweight defocus-aware aggregation module integrates these stacks into the encoder of a depth estimation framework. This mechanism allows the model to extract consistent geometric features from the defocus dimension while keeping the decoder architecture unchanged. Experiments demonstrate that BokehDepth achieves superior visual bokeh fidelity compared to depth-dependent rendering baselines and consistently enhances the metric accuracy of state-of-the-art monocular depth models.
Authors: Christophe Bolduc, Julien Philip, Li Ma, Mingming He, Paul Debevec, Jean-Fran\c{c}ois Lalonde
Abstract: We present Lighting in Motion (LiMo), a diffusion-based approach to spatiotemporal lighting estimation. LiMo targets both realistic high-frequency detail prediction and accurate illuminance estimation. To account for both, we propose generating a set of mirrored and diffuse spheres at different exposures, based on their 3D positions in the input. Making use of diffusion priors, we fine-tune powerful existing diffusion models on a large-scale customized dataset of indoor and outdoor scenes, paired with spatiotemporal light probes. For accurate spatial conditioning, we demonstrate that depth alone is insufficient and we introduce a new geometric condition to provide the relative position of the scene to the target 3D position. Finally, we combine diffuse and mirror predictions at different exposures into a single HDRI map leveraging differentiable rendering. We thoroughly evaluate our method and design choices to establish LiMo as state-of-the-art for both spatial control and prediction accuracy.
Authors: Francesco Di Sario, Daniel Rebain, Dor Verbin, Marco Grangetto, Andrea Tagliasacchi
Abstract: Radiance field methods (e.g. 3D Gaussian Splatting) have emerged as a powerful paradigm for novel view synthesis, yet their appearance modeling often relies on Spherical Harmonics (SH), which impose fundamental limitations. SH struggle with high-frequency signals, exhibit Gibbs ringing artifacts, and fail to capture specular reflections - a key component of realistic rendering. Although alternatives like spherical Gaussians offer improvements, they add significant optimization complexity. We propose Spherical Voronoi (SV) as a unified framework for appearance representation in 3D Gaussian Splatting. SV partitions the directional domain into learnable regions with smooth boundaries, providing an intuitive and stable parameterization for view-dependent effects. For diffuse appearance, SV achieves competitive results while keeping optimization simpler than existing alternatives. For reflections - where SH fail - we leverage SV as learnable reflection probes, taking reflected directions as input following principles from classical graphics. This formulation attains state-of-the-art results on synthetic and real-world datasets, demonstrating that SV offers a principled, efficient, and general solution for appearance modeling in explicit 3D representations. Project page: https://sphericalvoronoi.github.io/
Authors: Kewei Wei, Bocheng Hu, Jie Cao, Xiaohan Chen, Zhengxi Lu, Wubing Xia, Weili Xu, Jiaao Wu, Junchen He, Mingyu Jia, Ciyun Zhao, Ye Sun, Yizhi Li, Zhonghan Zhao, Jian Zhang, Gaoang Wang
Abstract: Modern Large Multimodal Models (LMMs) have demonstrated extraordinary ability in static image and single-state spatial-temporal understanding. However, their capacity to comprehend the dynamic changes of objects within a shared spatial context between two distinct video observations, remains largely unexplored. This ability to reason about transformations within a consistent environment is particularly crucial for advancements in the field of spatial intelligence. In this paper, we introduce $M^3-Verse$, a Multi-Modal, Multi-State, Multi-Dimensional benchmark, to formally evaluate this capability. It is built upon paired videos that provide multi-perspective observations of an indoor scene before and after a state change. The benchmark contains a total of 270 scenes and 2,932 questions, which are categorized into over 50 subtasks that probe 4 core capabilities. We evaluate 16 state-of-the-art LMMs and observe their limitations in tracking state transitions. To address these challenges, we further propose a simple yet effective baseline that achieves significant performance improvements in multi-state perception. $M^3-Verse$ thus provides a challenging new testbed to catalyze the development of next-generation models with a more holistic understanding of our dynamic visual world. You can get the construction pipeline from https://github.com/Wal-K-aWay/M3-Verse_pipeline and full benchmark data from https://www.modelscope.cn/datasets/WalKaWay/M3-Verse.
URLs: https://github.com/Wal-K-aWay/M3-Verse_pipeline, https://www.modelscope.cn/datasets/WalKaWay/M3-Verse.
Authors: Mengqi He, Xinyu Tian, Xin Shen, Jinhong Ni, Shu Zou, Zhaoyuan Yang, Jing Zhang
Abstract: Vision-language models (VLMs) achieve remarkable performance but remain vulnerable to adversarial attacks. Entropy, as a measure of model uncertainty, is highly correlated with VLM reliability. While prior entropy-based attacks maximize uncertainty at all decoding steps, implicitly assuming that every token equally contributes to model instability, we reveal that a small fraction (around 20%) of high-entropy tokens, in the evaluated representative open-source VLMs with diverse architectures, concentrates a disproportionate share of adversarial influence during autoregressive generation. We demonstrate that concentrating adversarial perturbations on these high-entropy positions achieves comparable semantic degradation to global methods while optimizing fewer decoding positions. Additionally, across multiple representative VLMs, such attacks induce not only semantic drift but also a substantial unsafe subset (20-31%) under the current pipeline. Remarkably, since such vulnerable high-entropy tokens recur across architecturally diverse VLMs, attacks focused on them exhibit non-trivial transferability. Motivated by these findings, we design a simple Entropy-Guided Attack (EGA) that operationalizes sparse high-entropy targeting and extends it with a reusable token bank, yielding competitive attack success rates (93-95%) with a considerable harmful rate (30.2-38.6%) on the three representative open-source VLMs.
Authors: Weijie Wei, Zhipeng Luo, Ling Feng, Venice Erin Liong
Abstract: While Vision-Language Models (VLMs) show significant promise for end-to-end autonomous driving by leveraging the common sense embedded in language models, their reliance on 2D image cues for complex scene understanding and decision-making presents a critical bottleneck for safety and reliability. Current image-based methods struggle with accurate metric spatial reasoning and geometric inference, leading to unreliable driving policies. To bridge this gap, we propose LVLDrive (LiDAR-Vision-Language), a novel framework specifically designed to upgrade existing VLMs with robust 3D metric spatial understanding for autonomous driving by incoperating LiDAR point cloud as an extra input modality. A key challenge lies in mitigating the catastrophic disturbance introduced by disparate 3D data to the pre-trained VLMs. To this end, we introduce a Gradual Fusion Q-Former that incrementally injects LiDAR features, ensuring the stability and preservation of the VLM's existing knowledge base. Furthermore, we develop a spatial-aware question-answering (SA-QA) dataset to explicitly teach the model advanced 3D perception and reasoning capabilities. Extensive experiments on driving benchmarks demonstrate that LVLDrive achieves superior performance compared to vision-only counterparts across scene understanding, metric spatial perception, and reliable driving decision-making. Our work highlights the necessity of explicit 3D metric data for building trustworthy VLM-based autonomous systems.
Authors: Rajarshi Roy, Ashhar Aziz, Shashwat Bajpai, Nasrin Imanpour, Gurpreet Singh, Shwetangshu Biswas, Kapil Wanaskar, Parth Patwa, Subhankar Ghosh, Shreyas Dixit, Nilesh Ranjan Pal, Vipula Rawte, Ritvik Garimella, Amitava Das, Amit Sheth, Gaytri Jena, Vasu Sharma, Aishwarya Naresh Reganti, Vinija Jain, Aman Chadha
Abstract: Multimodal generative AI systems like Stable Diffusion, DALL-E, and MidJourney have fundamentally changed how synthetic images are created. These tools drive innovation but also enable the spread of misleading content, false information, and manipulated media. As generated images become harder to distinguish from photographs, detecting them has become an urgent priority. To combat this challenge, we release MS COCOAI, a novel dataset for AI generated image detection consisting of 96000 real and synthetic datapoints, built using the MS COCO dataset. To generate synthetic images, we use five generators: Stable Diffusion 3, Stable Diffusion 2.1, SDXL, DALL-E 3, and MidJourney v6. Based on the dataset, we propose two tasks: (1) classifying images as real or generated, and (2) identifying which model produced a given synthetic image. The dataset is available at https://huggingface.co/datasets/Rajarshi-Roy-research/Defactify_Image_Dataset.
URLs: https://huggingface.co/datasets/Rajarshi-Roy-research/Defactify_Image_Dataset.
Authors: Anees Ur Rehman Hashmi, Numan Saeed, Christoph Lippert
Abstract: Multimodal medical large language models have shown substantial progress in chest X-ray interpretation but continue to face challenges in spatial reasoning and anatomical understanding. Although existing grounding techniques improve overall performance, they often fail to establish a true anatomical correspondence, resulting in incorrect anatomical understanding in the medical domain. To address this gap, we introduce AnatomiX, a multitask multimodal large language model for anatomically grounded chest X-ray interpretation. Inspired by the radiological workflow, AnatomiX adopts a two stage approach: first, it identifies anatomical structures and extracts their features, and then leverages a large language model to perform diverse downstream tasks such as phrase grounding, report generation, visual question answering, and image understanding. Extensive experiments across multiple benchmarks demonstrate that AnatomiX achieves superior anatomical reasoning and delivers over 25% improvement in performance on anatomy grounding, phrase grounding, grounded diagnosis and grounded captioning tasks compared to existing approaches. Code and pretrained model are available at https://aneesurhashmi.github.io/anatomix
Authors: Cuong Le, Pavlo Melnyk, Bastian Wandt, M{\aa}rten Wadenb\"ack
Abstract: Recovering 3D human poses from a monocular camera view is a highly ill-posed problem due to the depth ambiguity. Earlier studies on 3D human pose lifting from 2D often contain incorrect-yet-overconfident 3D estimations. To mitigate the problem, emerging probabilistic approaches treat the 3D estimations as a distribution, taking into account the uncertainty measurement of the poses. Falling in a similar category, we proposed FMPose, a probabilistic 3D human pose estimation method based on the flow matching generative approach. Conditioned on the 2D cues, the flow matching scheme learns the optimal transport from a simple source distribution to the plausible 3D human pose distribution via continuous normalizing flows. The 2D lifting condition is modeled via graph convolutional networks, leveraging the learnable connections between human body joints as the graph structure for feature aggregation. While trade-offs between processing time and precision exist, already in the equal-accuracy comparison, FMPose exhibits significantly faster processing time than the diffusion model, and also offers another faster and more accurate configuration. Experimental results show major improvements of our FMPose over current state-of-the-art methods on two common benchmarks for 3D human pose estimation, namely Human3.6M, MPI-INF-3DHP. Additionally, FMPose shows competitive performance on the more challenging 3DPW dataset. The code implementation is available at https://github.com/cuongle1206/FMPose
Authors: Yu Xia, Chang Liu, Tianqi Xiang, Zhigang Tu
Abstract: Real-time small object detection in Unmanned Aerial Vehicle (UAV) imagery remains challenging due to limited feature representation and ineffective multi-scale fusion. Existing methods underutilize frequency information and rely on static convolutional operations, which constrain the capacity to obtain rich feature representations and hinder the effective exploitation of deep semantic features. To address these issues, we propose EFSI-DETR, a novel detection framework that integrates efficient semantic feature enhancement with dynamic frequency-spatial guidance. EFSI-DETR comprises two main components: (1) a Dynamic Frequency-Spatial Unified Synergy Network (DyFusNet) that jointly exploits frequency and spatial cues for robust multi-scale feature fusion, (2) an Efficient Semantic Feature Concentrator (ESFC) that enables deep semantic extraction with minimal computational cost. Furthermore, a Fine-grained Feature Retention (FFR) strategy is adopted to incorporate spatially rich shallow features during fusion to preserve fine-grained details, crucial for small object detection in UAV imagery. Extensive experiments on VisDrone and CODrone benchmarks demonstrate that our EFSI-DETR achieves the state-of-the-art performance with real-time efficiency, yielding improvement of \textbf{1.6}\% and \textbf{5.8}\% in AP and AP$_{s}$ on VisDrone, while obtaining \textbf{188} FPS inference speed on a single RTX 4090 GPU.
Authors: Zihan Su, Hongyang Wei, Kangrui Cen, Yong Wang, Guanhua Chen, Chun Yuan, Xiangxiang Chu
Abstract: Unified Multimodal Models (UMMs) integrate both visual understanding and generation within a single framework. Their ultimate aspiration is to create a cycle where understanding and generation mutually reinforce each other. While recent post-training methods have successfully leveraged understanding to enhance generation, the reverse direction of utilizing generation to improve understanding remains largely unexplored. In this work, we propose UniMRG (Unified Multi-Representation Generation), a simple yet effective architecture-agnostic post-training method. UniMRG enhances the understanding capabilities of UMMs by incorporating auxiliary generation tasks. Specifically, we train UMMs to generate multiple intrinsic representations of input images, namely pixel (reconstruction), depth (geometry), and segmentation (structure), alongside standard visual understanding objectives. By synthesizing these diverse representations, UMMs capture complementary information regarding appearance, spatial relations, and structural layout. Consequently, UMMs develop a deeper and more comprehensive understanding of visual inputs. Extensive experiments across diverse UMM architectures demonstrate that our method notably enhances fine-grained perception, reduces hallucinations, and improves spatial understanding, while simultaneously boosting generation capabilities.
Authors: Zixuan Xia, Hao Wang, Pengcheng Weng, Yanyu Qian, Yangxin Xu, William Dan, Fei Wang
Abstract: Multimodal fusion is often treated as an optimization-balancing problem, where training signals are adjusted to prevent one modality from dominating the others. However, balanced optimization does not fully determine the geometry of intermediate representations. Supervised multimodal models may still learn low-diversity modality-specific embeddings or allow paired cross-modal observations to drift excessively apart, weakening both unimodal robustness and multimodal fusion. We introduce \regName, a lightweight plug-and-play geometric regularization framework for multimodal representation learning. Rather than enforcing rigid cross-modal alignment, \regName follows a bounded-agreement principle: preserve modality-specific diversity while softly constraining only the portion of paired cross-modal drift that exceeds an admissible agreement band. Operationally, \regName combines a dispersion term that mitigates spectral concentration with an agreement-band anchoring term that controls excessive paired drift, requiring no architectural modification or inference-time overhead. Experiments across audio-visual, image-text, and RF-based benchmarks show that \regName consistently improves multimodal performance and often strengthens unimodal representations. These results suggest that explicitly regulating representation geometry is an effective complement to optimization balancing, and provide evidence that geometry-aware regularization can improve multimodal learning across diverse architectures and domains.
Authors: Yanlong Chen, Amirhossein Habibian, Luca Benini, Yawei Li
Abstract: Vision-Language Models (VLMs) achieve strong multimodal performance but are costly to deploy, and post-training quantization often causes significant accuracy loss. Despite its potential, quantization-aware training for VLMs remains underexplored. We propose GRACE, a framework unifying knowledge distillation and QAT under the Information Bottleneck principle: quantization constrains information capacity while distillation guides what to preserve within this budget. Treating the teacher as a proxy for task-relevant information, we introduce confidence-gated decoupled distillation to filter unreliable supervision, relational centered kernel alignment to transfer visual token structures, and an adaptive controller via Lagrangian relaxation to balance fidelity against capacity constraints. Across extensive benchmarks on LLaVA and Qwen families, our INT4 models consistently outperform FP16 baselines (e.g., LLaVA-1.5-7B: 70.1 vs. 66.8 on SQA; Qwen2-VL-2B: 76.9 vs. 72.6 on MMBench), nearly matching teacher performance. Using real INT4 kernel, we achieve 3$\times$ throughput with 54% memory reduction. This principled framework significantly outperforms existing quantization methods, making GRACE a compelling solution for resource-constrained deployment. Code and data are available at: https://github.com/ForeverBlue816/GRACE.
Authors: Lancheng Gao, Ziheng Jia, Zixuan Xing, Wei Sun, Huiyu Duan, Guangtao Zhai, Xiongkuo Min
Abstract: Understanding the multi-dimensional attributes and intensity nuances of image-evoked emotions is pivotal for advancing machine empathy and empowering diverse human-computer interaction applications. However, existing models are still limited to coarse-grained emotion perception or deficient reasoning capabilities. To bridge this gap, we introduce \textbf{EEmoDB}, the largest image-{\ul e}voked {\ul emo}tion understanding {\ul d}ataset to date. It features $5$ analysis dimensions spanning $5$ distinct task categories, facilitating comprehensive interpretation. Specifically, we compile $1.2M$ question-answering (QA) pairs (EEmoDB-QA) from $125K$ images via automated generation, alongside a $36K$ dataset (EEmoDB-Assess) curated from $25K$ images for fine-grained assessment. Furthermore, we propose \textbf{EEmo-Logic}, an \textbf{all-in-one} multimodal large language model (MLLM) developed via instruction fine-tuning and task-customized group relative preference optimization (GRPO) with novel reward design. Extensive experiments demonstrate that EEmo-Logic achieves robust performance in in-domain and cross-domain datasets, excelling in emotion QA and fine-grained assessment. The dataset and code are available at https://github.com/workerred/EEmo-Logic.
Authors: Chunming He, Rihan Zhang, Fengyang Xiao, Dingming Zhang, Zhiwen Cao, Sina Farsiu
Abstract: Biological learning proceeds from easy to difficult tasks, gradually reinforcing perception and robustness. Inspired by this principle, we address Context-Entangled Content Segmentation (CECS), a challenging setting where objects share intrinsic visual patterns with their surroundings, as in camouflaged object detection. Conventional segmentation networks predominantly rely on architectural enhancements but often ignore the learning dynamics that govern robustness under entangled data distributions. We introduce CurriSeg, a dual-phase learning framework that unifies curriculum and anti-curriculum principles to improve representation reliability. In the Curriculum Selection phase, CurriSeg dynamically selects training data based on the temporal statistics of sample losses, distinguishing hard-but-informative samples from noisy or ambiguous ones, thus enabling stable capability enhancement. In the Anti-Curriculum Promotion phase, we design Spectral-Blindness Fine-Tuning, which suppresses high-frequency components to enforce dependence on low-frequency structural and contextual cues and thus strengthens generalization. Extensive experiments demonstrate that CurriSeg achieves consistent improvements across diverse CECS benchmarks without adding parameters or increasing total training time, offering a principled view of how progression and challenge interplay to foster robust and context-aware segmentation. Code will be released.
Authors: Chengtao Lv, Yumeng Shi, Yushi Huang, Ruihao Gong, Shen Ren, Wenya Wang
Abstract: Advanced autoregressive (AR) video generation models have improved visual fidelity and interactivity, but the quadratic complexity of attention remains a primary bottleneck for efficient deployment. While existing sparse attention solutions have shown promise on bidirectional models, we identify that applying these solutions to AR models leads to considerable performance degradation for two reasons: isolated consideration of chunk generation and insufficient utilization of past informative context. Motivated by these observations, we propose \textsc{Light Forcing}, the \textit{first} sparse attention solution tailored for AR video generation models. It incorporates a \textit{Chunk-Aware Growth} mechanism to quantitatively estimate the contribution of each chunk, which determines their sparsity allocation. This progressive sparsity increase strategy enables the current chunk to inherit prior knowledge in earlier chunks during generation. Additionally, we introduce a \textit{Hierarchical Sparse Attention} to capture informative historical and local context in a coarse-to-fine manner. Such two-level mask selection strategy (\ie, frame and block level) can adaptively handle diverse attention patterns. Extensive experiments demonstrate that our method outperforms existing sparse attention in quality (\eg, 84.5 on VBench) and efficiency (\eg, $1.2{\sim}1.3\times$ end-to-end speedup). Combined with FP8 quantization and LightVAE, \textsc{Light Forcing} further achieves a $2.3\times$ speedup and 19.7\,FPS on an RTX~5090 GPU. Code will be released at \href{https://github.com/chengtao-lv/LightForcing}{https://github.com/chengtao-lv/LightForcing}.
URLs: https://github.com/chengtao-lv/LightForcing, https://github.com/chengtao-lv/LightForcing
Authors: Xianjie Liu, Yiman Hu, Liang Wu, Ping Hu, Yixiong Zou, Jian Xu, Bo Zheng
Abstract: E-commerce short videos represent a high-revenue segment of the online video industry characterized by a goal-driven format and dense multi-modal signals. Current models often struggle with these videos because existing benchmarks focus primarily on general-purpose tasks and neglect the reasoning of commercial intent. In this work, we first propose a multi-modal information density assessment framework to quantify the complexity of this domain. Our evaluation reveals that e-commerce content exhibits substantially higher density across visual, audio, and textual modalities compared to mainstream datasets, establishing a more challenging frontier for video understanding. To address this gap, we introduce E-commerce Video Ads Benchmark (E-VAds), which is the first benchmark specifically designed for e-commerce short video understanding. We curated 3,961 high-quality videos from Taobao covering a wide range of product categories and used a multi-agent system to generate 19,785 open-ended Q&A pairs. These questions are organized into two primary dimensions, namely Perception and Cognition and Reasoning, which consist of five distinct tasks. Finally, we develop E-VAds-R1, an RL-based reasoning model featuring a multi-grained reward design called MG-GRPO. This strategy provides smooth guidance for early exploration while creating a non-linear incentive for expert-level precision. Experimental results demonstrate that E-VAds-R1 achieves a 109.2% performance gain in commercial intent reasoning with only a few hundred training samples.
Authors: Kfir Goldberg, Elad Richardson, Yael Vinker
Abstract: While generative models have become powerful tools for image synthesis, they are typically optimized for executing carefully crafted textual prompts, offering limited support for the open-ended visual exploration that often precedes idea formation. In contrast, designers frequently draw inspiration from loosely connected visual references, seeking emergent connections that spark new ideas. We propose Inspiration Seeds, a generative framework that shifts image generation from final execution to exploratory ideation. Given two input images, our model produces diverse, visually coherent compositions that reveal latent relationships between inputs, without relying on user-specified text prompts. Our approach is feed-forward, trained on synthetic triplets of decomposed visual aspects derived entirely through visual means: we use CLIP Sparse Autoencoders to extract editing directions in CLIP latent space and isolate concept pairs. By removing the reliance on language and enabling fast, intuitive recombination, our method supports visual ideation at the early and ambiguous stages of creative work.
Authors: Muthu Subash Kavitha, Anas Zafar, Amgad Muneer, Jia Wu
Abstract: Clinical deployment of chest radiograph classifiers requires models that can be updated as new datasets become available without retraining on previously observed data or degrading validated performance. We study a task-incremental continual learning setting for chest radiograph classification under task-unknown inference, where heterogeneous chest X-ray datasets arrive sequentially and task identity is unavailable at deployment time. We propose CARL-CXR, a continual adapter-based routing framework that maintains a fixed high-capacity backbone while incrementally introducing lightweight task-specific adapters and classifier heads. A latent task selector operates on adapter-conditioned features to dynamically route each input to the most relevant task pathway, leveraging compact task prototypes and feature-level experience replay to preserve task identity across sequential updates without storing raw images. Experiments on MIMIC-CXR and CheXpert two large-scale datasets with distinct patient populations, imaging devices, and annotation pipelines demonstrate that CARL-CXR achieves minimal catastrophic forgetting (0.012 AUROC drop), representing a 6X and 11X reduction over established continual learning baselines LwF and EWC respectively, while maintaining competitive diagnostic performance (AUROC 0.74). Under task unknown deployment, CARL-CXR outperforms joint training by 12.5 points in routing accuracy (75.0% vs. 62.5%): unlike LwF and EWC, which require explicit task identifiers at inference and provide no routing mechanism.
Authors: Zhan Liu, Changli Tang, Yuxin Wang, Zhiyuan Zhu, Youjun Chen, Yiwen Shao, Tianzi Wang, Lei Ke, Zengrui Jin, Chao Zhang
Abstract: Current audio-visual large language models (AV-LLMs) are predominantly restricted to 2D perception, relying on RGB video and monaural audio. This design choice introduces a fundamental dimensionality mismatch that precludes reliable source localization and spatial reasoning in complex 3D environments. We address this limitation by presenting JAEGER, a framework that extends AV-LLMs to 3D space, to enable joint spatial grounding and reasoning through the integration of RGB-D observations and multi-channel first-order ambisonics. A core contribution of our work is the neural intensity vector (Neural IV), a learned spatial audio representation that encodes robust directional cues to enhance direction-of-arrival estimation, even in adverse acoustic scenarios with overlapping sources. To facilitate large-scale training and systematic evaluation, we propose SpatialSceneQA, a benchmark of 61k instruction-tuning samples curated from simulated physical environments. Extensive experiments demonstrate that our approach consistently surpasses 2D-centric baselines across diverse spatial perception and reasoning tasks, underscoring the necessity of explicit 3D modelling for advancing AI in physical environments. Our source code, pre-trained model checkpoints, and datasets are available at https://github.com/liuzhan22/JAEGER.
Authors: Junwei Shu, Wenjie Liu, Hantang Liu, Changbo Wang, Yang Li
Abstract: Monte Carlo rendering and modern generative models both transform uncertain states into structured images, yet they are usually studied as separate processes. We introduce Monte Carlo Transport Scheduling, a framework that treats progressive path tracing as a continuous sampling-driven transport process. Our key observation is that the renderer already produces physically valid states along this process: nested Monte Carlo estimates trace a refinement trajectory whose natural time coordinate follows from sampling variance. This view leads to a continuous training framework that learns from real render endpoints rather than synthetic interpolants, preserving the statistical structure of Monte Carlo estimation while enabling arbitrary-step neural refinement. We evaluate the framework on a controlled rendering benchmark designed to separate transport difficulty from scene context, and show that it yields stable render refinement, supports continuous stopping between rendering states, and transfers as a physical prior for frozen generative samplers. These results suggest a common continuous-time substrate for rendering and generation, where Monte Carlo sampling provides both the physical states and the supervision for learning image transport.
Authors: Alaa El Ichi, Khalide Jbilou
Abstract: This paper introduces Multidimensional Task Learning (MTL), a unified mathematical framework based on Generalized Einstein MLPs (GE-MLPs) that operate directly on tensors via the Einstein product. We argue that current computer vision task formulations are inherently constrained by matrix-based thinking: standard architectures rely on matrix-valued weights and vectorvalued biases, requiring structural flattening that restricts the space of naturally expressible tasks. GE-MLPs lift this constraint by operating with tensor-valued parameters, enabling explicit control over which dimensions are preserved or contracted without information loss. Through rigorous mathematical derivations, we demonstrate that classification, segmentation, and detection are special cases of MTL, differing only in their dimensional configuration within a formally defined task space. We further prove that this task space is strictly larger than what matrix-based formulations can natively express, enabling principled task configurations such as spatiotemporal or cross modal predictions that require destructive flattening under conventional approaches. This work provides a mathematical foundation for understanding, comparing, and designing computer vision tasks through the lens of tensor algebra.
Authors: Xingyu Shao, Mengfan He, Chunyu Li, Liangzheng Sun, Ziyang Meng
Abstract: To address the scale mismatch caused by large altitude variations in UAV visual place recognition, we propose a monocular vision-only altitude-adaptive geo-localization framework. The method first estimates relative altitude from a single downward-looking image by transforming the input into the frequency domain and formulating altitude estimation as a regression-as-classification (RAC) problem. The estimated altitude is then used to crop the query image to a canonical scale, after which a classification-then-retrieval visual place recognition module performs coarse localization. To improve retrieval robustness under varying image quality, we further introduce a quality-adaptive margin classifier (QAMC) and refine the final location by weighted coordinate estimation over the top retrieved candidates. Experiments on two synthetic datasets and two real-flight datasets show that the relative altitude estimation (RAE) module yields clear overall improvements in downstream retrieval performance under significant altitude changes. With our visual place recognition module, altitude adaptation improves average R@1 and R@5 by 41.50 and 56.83 percentage points, respectively, compared with using the same retrieval pipeline without altitude normalization, and the full system runs at 13.3 frames/s on the reported workstation hardware. These results indicate that relative altitude estimation provides an effective scale prior for cross-altitude UAV geo-localization and supports GPS-denied coarse initialization without auxiliary range sensors or temporal inputs.
Authors: Jiaqi Tang, Shaoyang Zhang, Xiaoqi Wang, Jiaying Zhou, Yang Liu, Qingchao Chen
Abstract: The advent of large-scale self-supervised learning (SSL) has produced a vast zoo of medical foundation models. However, selecting optimal medical foundation models for specific segmentation tasks remains a computational bottleneck. Existing Transferability Estimation (TE) metrics, primarily designed for classification, rely on global statistical assumptions and fail to capture the topological complexity essential for dense prediction. We propose a novel Topology-Driven Transferability Estimation framework that evaluates manifold tractability rather than statistical overlap. Our approach introduces three components: (1) Global Representation Topology Divergence (GRTD), utilizing Minimum Spanning Trees to quantify feature-label structural isomorphism; (2) Local Boundary-Aware Topological Consistency (LBTC), which assesses manifold separability specifically at critical anatomical boundaries; and (3) Task-Adaptive Fusion, which dynamically integrates global and local metrics based on the semantic cardinality of the target task. Validated on the large-scale OpenMind benchmark across diverse anatomical targets and SSL foundation models, our approach significantly outperforms state-of-the-art baselines by around 31% relative improvement in the weighted Kendall metric, providing a robust, training-free proxy for efficient model selection without the cost of fine-tuning. The code will be made publicly available upon acceptance.
Authors: Zikang Xu, Ruinan Jin, Xiaoxiao Li
Abstract: Fairness in medical agents is becoming critical as tool-using clinical AI systems orchestrate specialized vision and language modules for tasks such as chest X-ray question answering. While these medical AI agents can improve flexibility, their added pipeline complexity also creates new pathways for demographic bias beyond standalone models. We present DUCK, Decomposing Unfairness in Chest X-ray agents, a systematic audit of fairness in tool-using chest X-ray agents instantiated with MedRAX. To localize where disparities arise, we introduce a stage-wise fairness decomposition that separates end-to-end bias from three agent-specific sources: tool exposure bias, or utility gaps conditioned on tool presence; tool transition bias, or subgroup differences in tool-routing patterns; and model reasoning bias, or subgroup differences in synthesis behaviors. Extensive experiments on tool-using agentic frameworks across five driver backbones reveal that demographic gaps persist in end-to-end performance, with equalized odds up to 20.79% and the lowest fairness-utility tradeoff down to 28.65%. Intermediate behaviors, including tool usage, transition patterns, and reasoning traces, exhibit distinct subgroup disparities that are not predictable from end-to-end evaluation alone. For example, conditioned on segmentation-tool availability, the subgroup utility gap reaches as high as 50%. Our findings underscore the need for process-level fairness auditing and debiasing to ensure the equitable deployment of clinical agentic systems. Code: https://github.com/Nanboy-Ronan/DUCK.
Authors: Weicai Yan, Yuhong Dai, Qi Ran, Haodong Li, Wang Lin, Tao Jin, Xing Xie, Hao Liao, Jianxun Lian
Abstract: Proactive and real-time interactive experiences are essential for human-like AI companions, yet face three key challenges: (1) achieving low-latency inference under continuous streaming inputs, (2) autonomously deciding when to respond, and (3) controlling both quality and quantity of generated content to meet real-time constraints. In this work, we instantiate AI companions through two gaming scenarios, commentator and guide, selected for their suitability for automatic evaluation. We introduce the Live Gaming Benchmark, a large-scale dataset with three representative scenarios: solo commentary, co-commentary, and user guidance, and present Proact-VL, a general framework that shapes multimodal language models into proactive, real-time interactive agents capable of human-like environment perception and interaction. Extensive experiments show Proact-VL achieves superior response latency and quality while maintaining strong video understanding capabilities, demonstrating its practicality for real-time interactive applications.
Authors: Haoyang Chen, Jing Zhang, Hebaixu Wang, Shiqin Wang, Pohsun Huang, Jiayuan Li, Haonan Guo, Di Wang, Zheng Wang, Bo Du
Abstract: Multi-modal remote sensing imagery provides complementary observations of the same geographic scene, yet such observations are frequently incomplete in practice. Existing cross-modal translation methods treat each modality pair as an independent task, resulting in quadratic complexity and limited generalization to unseen modality combinations. We formulate Any-to-Any translation as inference over a shared latent representation of the scene, where different modalities correspond to partial observations of the same underlying semantics. Based on this formulation, we propose Any2Any, a unified latent diffusion framework that projects heterogeneous inputs into a geometrically aligned latent space. Such structure performs anchored latent regression with a shared backbone, decoupling modality-specific representation learning from semantic mapping. Moreover, lightweight target-specific residual adapters are used to correct systematic latent mismatches without increasing inference complexity. To support learning under sparse but connected supervision, we introduce RST-1M, the first million-scale remote sensing dataset with paired observations across five sensing modalities, providing supervision anchors for any-to-any translation. Experiments across 14 translation tasks show that Any2Any consistently outperforms pairwise translation methods and exhibits strong zero-shot generalization to unseen modality pairs. Code and models are available at https://github.com/MiliLab/Any2Any.
Authors: Azmine Toushik Wasi, Shahriyar Zaman Ridoy, Koushik Ahamed Tonmoy, Kinga Tshering, S. M. Muhtasimul Hasan, Wahid Faisal, Tasnim Mohiuddin, Md Rizwan Parvez
Abstract: Geo-temporal understanding, the ability to infer location, time, and contextual properties from visual input alone, underpins applications such as disaster management, traffic planning, embodied navigation, world modeling, and geography education. Although recent vision-language models (VLMs) have advanced image geo-localization using cues like landmarks and road signs, their ability to reason about temporal signals and physically grounded spatial cues remains limited. To address this gap, we introduce TimeSpot, a benchmark for evaluating real-world geo-temporal reasoning in VLMs. TimeSpot comprises 1,455 ground-level images from 80 countries and requires structured prediction of temporal attributes (season, month, time of day, daylight phase) and geographic attributes (continent, country, climate zone, environment type, latitude-longitude) directly from visual evidence. It also includes spatial-temporal reasoning tasks that test physical plausibility under real-world uncertainty. Evaluations of state-of-the-art open- and closed-source VLMs show low performance, particularly for temporal inference. While supervised fine-tuning yields improvements, results remain insufficient, highlighting the need for new methods to achieve robust, physically grounded geo-temporal understanding TimeSpot is available at: https://TimeSpot-GT.github.io.
Authors: Jaeha Choi, Jin Won Lee, Siwoo You, Jangho Lee
Abstract: Advances in vision-language models (VLMs) have achieved remarkable success on complex multimodal reasoning tasks, leading to the assumption that they should also excel at reading analog clocks. However, contrary to this expectation, our study reveals that reading analog clocks in real-world environments remains a significant challenge for state-of-the-art VLMs. Existing analog clock datasets are largely synthetic or planar with limited stylistic diversity and minimal background context, failing to capture the visual variability of real-world scenes. As a result, VLMs trained on such data exhibit weak spatiotemporal reasoning, frequently confusing the hour and minute hands and struggling under common visual conditions such as occlusion, lighting variation, and cluttered backgrounds. To address this issue, we introduce TickTockVQA, a human-annotated dataset containing analog clocks in diverse real-world scenarios. TickTockVQA provides explicit hour and minute annotations, and includes an AM/PM tag when it is inferable from the visual context. Furthermore, we propose Swap-DPO, a direct preference optimization-based fine-tuning framework to align model reasoning toward accurate time interpretation. Experimental results demonstrate that our approach substantially enhances clock reading accuracy and robustness under real-world conditions, establishing a foundation for future research on spatiotemporal reasoning and visual understanding in VLMs.
Authors: Nayeb Hasin, Md. Arafath Rahman Nishat, Mainul Islam, Khandakar Shakib Al Hasan, Asif Newaz
Abstract: An Automatic License Plate Recognition (ALPR) system constitutes a crucial element in an intelligent traffic management system. However, the detection of Bangla license plates remains challenging because of the complicated character scheme and uneven layouts. This paper presents a robust Bangla License Plate Recognition system that integrates a deep learning-based object detection model for license plate localization with Optical Character Recognition for text extraction. Multiple object detection architectures, including U-Net and several YOLO (You Only Look Once) variants, are compared for license plate localization. This study proposes a novel two-stage adaptive training strategy built upon the YOLOv8 architecture to improve localization performance. The proposed approach outperforms the established models, achieving an accuracy of 97.83% and an Intersection over Union (IoU) of 91.3%. The text recognition problem is phrased as a sequence generation problem with a VisionEncoderDecoder architecture, with a combination of encoder-decoders evaluated. It was demonstrated that the ViT + BanglaBERT model gives better results at the character level, with a Character Error Rate of 0.1323 and Word Error Rate of 0.1068. The proposed system also shows a consistent performance when tested on an external dataset that has been curated for this study purpose. The dataset offers completely different environment and lighting conditions compared to the training sample, indicating the robustness of the proposed framework. Overall, our proposed system provides a robust and reliable solution for Bangla license plate recognition and performs effectively across diverse real-world scenarios, including variations in lighting, noise, and plate styles. These strengths make it well suited for deployment in intelligent transportation applications such as automated law enforcement and access control.
Authors: Jonas Herzog, Yue Wang
Abstract: Recent research suggested that the embeddings produced by CLIP-like contrastive language-image training are suboptimal for image-only tasks. The main theory is that the inter-modal (language-image) alignment loss ignores intra-modal (image-image) alignment, leading to poorly calibrated distances between images. In this study, we question this intra-modal misalignment hypothesis. We reexamine its foundational theoretical argument, the indicators used to support it, and the performance metrics affected. For the theoretical argument, we demonstrate that there are no such supposed degrees of freedom for image embedding distances. For the empirical measures, our findings reveal they yield similar results for language-image trained models (CLIP, SigLIP) and image-image trained models (DINO, SigLIP2). This indicates the observed phenomena do not stem from a misalignment specific to the former. Experiments on the commonly studied intra-modal tasks retrieval and few-shot classification confirm that addressing task ambiguity, not supposed misalignment, is key for best results.
Authors: Cong Wang, Hanxin Zhu, Xiao Tang, Jiayi Luo, Xin Jin, Long Chen, Zhibo Chen
Abstract: Recent progress in video generation has led to substantial improvements in visual fidelity, yet ensuring physically consistent motion remains a fundamental challenge. Intuitively, this limitation can be attributed to the fact that real-world object motion unfolds in three-dimensional space, while video observations provide only partial, view-dependent projections of such dynamics. To address these issues, we propose OrthoPhys, a two-stage framework that leverages orthogonal-view geometry guidance to enforce physical plausibility. Instead of directly generating unstructured 2D videos, our first stage generates synchronized, four-view orthogonal videos of the foreground dynamics. By incorporating a geometry-enhanced attention mechanism across these orthogonal views, this stage effectively enforces 3D spatial coherence and implicitly grounds the motion in physical attributes. In the second stage, these physically consistent orthogonal foregrounds serve as rigid guidance to synthesize the final complete video, seamlessly learning the interaction between foreground dynamics and the background context. To support this orthogonal-view training paradigm, we construct PhysMV, a dataset containing 40K scenes, each consisting of four orthogonal viewpoints, resulting in a total of 160K video sequences. Extensive experiments demonstrate that OrthoPhys significantly improves physical realism and spatial-temporal coherence over existing video generation methods. Project page: https://anonymous.4open.science/w/Phys4D/.
Authors: U. V. B. L. Udugama, George Vosselman, Francesco Nex
Abstract: Monocular cameras are attractive for robotic perception due to their low cost and ease of deployment, yet achieving reliable real-time spatial understanding from a single image stream remains challenging. While recent multi-task dense prediction models have improved per-pixel depth and semantic estimation, translating these advances into stable monocular mapping systems is still non-trivial. This paper presents M2H-MX, a real-time multi-task perception model for monocular spatial understanding. The model preserves multi-scale feature representations while introducing register-gated global context and controlled cross-task interaction in a lightweight decoder, enabling depth and semantic predictions to reinforce each other under strict latency constraints. Its outputs integrate directly into an unmodified monocular SLAM pipeline through a compact perception-to-mapping interface. We evaluate both dense prediction accuracy and in-the-loop system performance. On NYUDv2, M2H-MX-L achieves state-of-the-art results, improving semantic mIoU by 6.6% and reducing depth RMSE by 9.4% over representative multi-task baselines. When deployed in a real-time monocular mapping system on ScanNet, M2H-MX reduces average trajectory error by 60.7% compared to a strong monocular SLAM baseline while producing cleaner metric-semantic maps. These results demonstrate that modern multi-task dense prediction can be reliably deployed for real-time monocular spatial perception in robotic systems.
Authors: Zhenghao Chen, Huiqun Wang, Di Huang
Abstract: Multimodal large language models (MLLMs) are increasingly being applied to spatial cognition tasks, where they are expected to understand and interact with complex environments. Most existing works improve spatial reasoning by introducing 3D priors or geometric supervision, which enhances performance but incurs substantial data preparation and alignment costs. In contrast, purely 2D approaches often struggle with multi-frame spatial reasoning due to their limited ability to capture cross-frame spatial relationships. To address these limitations, we propose EgoMind, a Chain-of-Thought framework that enables geometry-free spatial reasoning through Role-Play Caption, which jointly constructs a coherent linguistic scene graph across frames, and Progressive Spatial Analysis, which progressively reasons toward task-specific questions. With only 5K auto-generated SFT samples and 20K RL samples, EgoMind achieves competitive results on VSI-Bench, SPAR-Bench, SITE-Bench, and SPBench, demonstrating its effectiveness in strengthening the spatial reasoning capabilities of MLLMs and highlighting the potential of linguistic reasoning for spatial cognition. Code and data are released at https://github.com/Hyggge/EgoMind.
Authors: DataFlow Team, Bohan Zeng, Daili Hua, Kaixin Zhu, Yifan Dai, Bozhou Li, Yuran Wang, Chengzhuo Tong, Yifan Yang, Mingkun Chang, Jianbin Zhao, Zhou Liu, Hao Liang, Xiaochen Ma, Ruichuan An, Junbo Niu, Zimo Meng, Tianyi Bai, Meiyi Qiang, Huanyao Zhang, Zhiyou Xiao, Tianyu Guo, Qinhan Yu, Runhao Zhao, Zhengpin Li, Xinyi Huang, Yisheng Pan, Yiwen Tang, Juanxi Tian, Yang Shi, Yue Ding, Xinlong Chen, Hongcheng Gao, Minglei Shi, Jialong Wu, Zekun Wang, Yuanxing Zhang, Xintao Wang, Pengfei Wan, Yiren Song, Mike Zheng Shou, Wentao Zhang
Abstract: World models have garnered significant attention as a promising research direction in artificial intelligence, yet a clear and unified definition remains lacking. In this paper, we introduce OpenWorldLib, a comprehensive and standardized inference framework for Advanced World Models. Drawing on the evolution of world models, we propose a clear definition: a world model is a model or framework centered on perception, equipped with interaction and long-term memory capabilities, for understanding and predicting the complex world. We further systematically categorize the essential capabilities of world models. Based on this definition, OpenWorldLib integrates models across different tasks within a unified framework, enabling efficient reuse and collaborative inference. Finally, we present additional reflections and analyses on potential future directions for world model research. Code link: https://github.com/OpenDCAI/OpenWorldLib
Authors: Xiangyuan Wang, Honghao Cai, Yunhao Bai, Chao Hui, Tianze Zhou, Haohua Chen, Hao Shi, Yuling Wu, Yao Hu, Xu Tang, Yibo Chen, Wei Zhu
Abstract: High-quality source-target image pairs with precise editing instructions are essential for instruction-guided image editing, yet constructing such training triplets at scale remains costly. Recent pipelines often rely on vision-language models to synthesize editing instructions automatically, but we find that strong VLMs still struggle to describe visual transformations between image pairs. In particular, they exhibit three recurring failure modes: orientation inconsistency, viewpoint ambiguity, and missing fine-grained attributes. In a human evaluation on 400 image pairs, several open-source VLM baselines produce critical-error rates above 47\%, making many synthesized instructions unsuitable for downstream training. To address this, we propose EditCaption, a two-stage post-training pipeline for image editing instruction synthesis. First, we construct a 100K supervised fine-tuning dataset through GLM-based auto-captioning, EditScore filtering, and human refinement. Second, we collect 10K human-annotated preference pairs, where each rejected instruction is labeled with its primary error type and severity. Based on this dataset, we propose Hardness-Adaptive Error-Aware DPO (HAE-DPO), a task-adapted DPO objective that introduces an adaptive margin based on human-labeled severity, failure-mode type, and reference-model hardness. Experiments across three benchmarks demonstrate that our 235B model with SFT+HAE-DPO achieves state-of-the-art performance among open-source and closed models, scoring 4.720 on Eval-400, 4.672 on HQ-Edit, and 4.651 on ByteMorph-Bench -- surpassing Gemini-3-Pro on all three. Human evaluation confirms critical error rates drop from 47.75\% to 17.50\%, with correct rates improving from 41.75\% to 70.25\%, surpassing Gemini-3-Pro (66.00\%).
Authors: Hao Chen, Junnan Xu
Abstract: Existing lip-sync deepfake detectors rely on pixel artifacts or audio-visual correspondence, and both fail under generator or language shift because the features they learn are tied to the training distribution. We take a different approach. Authentic lip motion is constrained by tissue mechanics and neuromuscular bandwidth; current generators typically do not impose these constraints, producing trajectories with elevated variance in velocity, acceleration, and jerk that real speech does not exhibit. We exploit this signal, which we term temporal lip jitter, by computing kinematic statistics from 64 perioral landmarks over short sliding windows and feeding them into a lightweight three-branch network. The model uses only landmark coordinates: no pixels, no audio, and no voiceprint data. We train only on English data and test in a zero-shot setting on five unseen generators and seven languages.
Authors: Yanping Wu, Meiting Dang, Lin Wu, Edmond S. L. Ho, Zhenghua Chen, Chongfeng Wei
Abstract: Recent advances in autonomous driving have motivated research on pedestrian intention prediction, which aims to infer future crossing decisions and actions by modeling temporal dynamics, social interactions, and environmental context. However, existing studies remain constrained by oversimplified multi-agent interaction patterns, opaque reasoning logic, and a lack of global consistency in behavioral predictions, which compromise both robustness and interpretability. In this work, we propose ESIA (Energy-based Spatiotemporal Interaction-Aware framework), a novel Conditional Random Field (CRF)-based paradigm. We cast the intention prediction task as a structured prediction problem over a unified graph-based representation, treating pedestrians and the environment as spatiotemporal nodes. To characterize their distinct roles, we assign unary potentials to nodes to capture individual intentions, and pairwise potentials to edges to encode social and environmental interactions. These potentials are integrated into a unified global energy function to ensure scene-level consistency across behavioral predictions. To further constrain inference without ground-truth supervision, we introduce structural consistency terms to penalize logical contradictions. This optimization is efficiently solved via a novel Unary-Seeded Simulated Annealing (U-SSA) algorithm, which leverages high-confidence unary priors to rapidly converge to a high-quality solution. Extensive experiments on standard benchmarks demonstrate that ESIA achieves state-of-the-art performance with improved interpretability over existing methods.
Authors: W. Cao, D. J\"onsson, Z. Huang, J. Unger
Abstract: Accurate BRDF acquisition is essential for realistic rendering, but dense gonioreflectometer measurements are slow and expensive. We study how to select a small set of BRDF measurements that is most informative for reconstructing material appearance under a learned BRDF prior. Existing sparse-acquisition methods often optimize samples for BRDF-space reconstruction for all materials, while the perceptual importance of a adaptive measurement ultimately depends on its effect on each rendered appearance. We therefore formulate sparse adaptive acquisition as a rendering-aware optimization problem. Our method combines a set encoder for sparse coordinate--value observations, a pretrained hypernetwork-based/PCA-based BRDF reconstructor, and a differentiable renderer. During sampler training, the reconstructor remains fixed, and gradients from a rendered-image loss optimize the measurement locations. This separates acquisition design from prior fitting and encourages the sampler to choose directions that are informative under the learned material distribution. To make the comparison controlled, we evaluate the uniform baseline, meta-learning method, HyperBRDF method, and our learned sampler under matched sample numbers, train/test split, rendering scene, object mask, image mapping, and metrics. Our central claim: rendering-aware sampling improves extremely sparse BRDF acquisition when final rendered appearance is the target. BRDF-space and combined losses are reported only as ablations, together with joint refinement and image-only latent fitting for unseen materials.
Authors: Alcides Toledo Espinosa, Gerardo Antonio \'Alvarez Hern\'andez, \'Angel Eduardo Zamora-Su\'arez, Miguel Bola\~nos, Juan Irving V\'asquez
Abstract: This paper presents a comparative evaluation of convolutional and transformer-based object detection architectures for early weed detection in tomato plantations. Representative models from each paradigm are considered, including YOLOv26-nano, a recent variant of the YOLO family, and RT-DETR Large and RF-DETR Medium as transformer-based architectures. The evaluation was conducted on the GROUNDBASED_WEED dataset, considering six weed classes and an additional category corresponding to unidentified plants, which allowed for the assessment of performance in terms of detection accuracy and computational efficiency using metrics such as precision, recall, average precision, and inference speed, as well as non-parametric statistical tests. The results highlight a clear trade-off between efficiency and contextual modeling: CNN-based detectors achieve high performance at a lower computational cost, while transformer-based approaches offer better global context capture at the expense of higher resource demands. These results provide practical criteria for model selection in precision agriculture applications.
Authors: Peiyang Liu, Ziqiang Cui, Xi Wang, Di Liang, Wei Ye
Abstract: Iterative Retrieval-Augmented Generation (iRAG) has emerged as a powerful paradigm for answering complex multi-hop questions by progressively retrieving and reasoning over external documents. However, current systems predominantly operate on parsed text, which creates two critical bottlenecks: (1) \textit{Coarse-grained attribution}, where users are burdened with manually locating evidence within lengthy documents based on vague text-level citations; and (2) \textit{Visual semantic loss}, where the conversion of visually rich documents (e.g., slides, PDFs with charts) into text discards spatial logic and layout cues essential for reasoning. To bridge this gap, we present \textbf{Chain of Evidence (CoE)}, a retriever-agnostic visual attribution framework that leverages Vision-Language Models to reason directly over screenshots of retrieved document candidates. CoE eliminates format-specific parsing and outputs precise bounding boxes, visualizing the complete reasoning chain within the retrieved candidate set. We evaluate CoE on two distinct benchmarks: \textbf{Wiki-CoE}, a large-scale dataset of structured web pages derived from 2WikiMultiHopQA, and \textbf{SlideVQA}, a challenging dataset of presentation slides featuring complex diagrams and free-form layouts. Experiments demonstrate that fine-tuned Qwen3-VL-8B-Instruct achieves robust performance, significantly outperforming text-based baselines in scenarios requiring visual layout understanding, while establishing a retriever-agnostic solution for pixel-level interpretable iRAG. Our code is available at https://github.com/PeiYangLiu/CoE.git.
Authors: Jiantang Huang
Abstract: Grounding traffic accidents in real CCTV footage is a rare-event problem where training on labeled accident video is often prohibited, yet accurate joint localization in time, space, and collision type is required. We present a no-fine-tuning pipeline that elicits this joint output from frozen vision-language models through two ideas. First, a coarse-to-fine two-pass decomposition: a full-video pass at 1 fps produces a coarse (t, x, y, c) tuple, then a second pass at 5 fps within a +/- 3 s window refines time and location, with two deterministic confidence gates that revert to the coarse estimate on boundary hedges or edge-clamped coordinates. Second, a specialist role assignment: Qwen3-VL-Plus handles grounding, Gemini 3.1 Flash-Lite handles typing on a centered video clip. On the ACCIDENT@CVPR 2026 benchmark (2,027 real CCTV videos) we reach ACC^S = 0.539 (95% CI [0.525, 0.553]): +0.127 over the benchmark paper's best-of-baselines oracle (0.412), +0.143 over the strongest single-VLM baseline (Molmo-7B, 0.396), and +0.250 over the naive baseline (0.289). The VLM path uses up to three API calls per video (17% fall back to physics on API failures); the full run costs ~$20.
Authors: Sheng-Wei Chan, Hsin-Jui Pan, Chun-Po Shen, Yung-Che Wang, Meng-Qian Li, Chia-Min Lin, Jen-Shiun Chiang
Abstract: We present FoR-Net, an efficient semantic segmentation framework that focuses on identifying and enhancing hard regions. Instead of relying on heavy global modeling, FoR-Net adopts an efficient strategy that selectively emphasizes informative regions through a learned importance map and a Top-K activation mechanism. Specifically, a selector module predicts region-wise importance, enabling the model to focus on challenging areas such as thin structures and object boundaries. Multi-scale reasoning is achieved using convolutional branches with different receptive fields, allowing diverse spatial context aggregation. We evaluate FoR-Net on the Cityscapes benchmark under limited computational resources. Despite its efficient design and standard training configuration, FoR-Net achieves competitive performance and exhibits improved attention to difficult regions. These results suggest that selective region-focused reasoning can serve as a practical and efficient alternative for semantic segmentation. This work explores region-focused reasoning under resource-constrained settings and provides insights for developing efficient and region-aware segmentation models.
Authors: Sidhartha Mohapatra, Pallavi Mohanty
Abstract: Clinicians trace cephalometric radiographs by following a structured anatomical workflow -- yet no prior system explicitly encodes this into computation. We present a five-phase anatomy-guided pipeline producing confidence-weighted spatial priors that shape HRNet-W32 training. The system achieves 1.04 mm mean radial error on 25 landmarks across 1,502 radiographs from 7+ imaging devices -- comparable to HYATT-Net (1.05 mm on CEPHA29) via explicit anatomical priors rather than learned attention. A three-way ablation isolates the mechanism: anatomical priors maintain a 1% validation-to-test gap, while removing priors yields an 88% gap (1.94 mm) -- despite identical validation convergence. A training x inference prior matrix confirms that (1) all models are inference-independent, (2) the 28-channel architecture alone provides no benefit, (3) random priors are partial and unstable (1.72 mm), and (4) only anatomically correct, image-specific priors yield 1.04 mm -- functioning as a training-time regularizer. No prior generation is needed at deployment. Five-fold cross-validation (p=0.0015), patient-level permutation testing (p<0.0001, n=151), reproduced baselines, Grad-CAM analysis, and clinical validation (100% skeletal classification across 151 patients including 72 boundary cases, kappa=1.00) provide converging evidence. Cross-domain experiments support the hypothesis that prior effectiveness depends on landmark spatial entropy -- confirmed prospectively across four domains. Supplementary materials included.
Authors: Ahmed Cherif
Abstract: Low-light images suffer from poor visibility, noise, and color distortion. Existing Retinex-based enhancement methods rely on manually tuned parameters that do not generalize across different lighting conditions. This paper proposes BFORE (Butterfly-Firefly Optimized Retinex Enhancement), a framework that automatically finds the best enhancement parameters for each image. BFORE works in two phases: (1) a Butterfly Optimization Algorithm (BOA) searches for optimal Multi-Scale Retinex with Color Restoration (MSRCR) parameters, then (2) a Firefly Algorithm (FA) fine-tunes gamma correction, denoising, and color parameters. Both phases maximize a Gaussian Naturalness Score (GNS), a no-reference metric that measures how natural the enhanced image looks. Standard quality metrics (PSNR, SSIM, NIQE) are computed only after optimization, ensuring zero data leakage. On 30 synthetic image pairs, BFORE achieves GNS = 0.971, outperforming the next-best method MSRCR (0.894) by 8.6%. On 115 real images from the LOL dataset, BFORE achieves GNS = 0.887, outperforming MSRCR (0.808) by 9.8%. A controlled comparison with three deep learning baselines (Zero-DCE, SCI, IAT) trained under identical conditions shows BFORE surpasses the best DL method by 14.7% in GNS. An ablation study confirms that the hybrid BOA+FA strategy significantly outperforms each optimizer in isolation, and a scalability analysis at three evaluation budgets shows that the structured optimizer significantly outperforms uniform random sampling once compute is available (p = 0.009 at 128 evaluations, p = 0.021 at 300 evaluations). All improvements are statistically significant (p < 0.0001, Wilcoxon signed-rank test). Processing time is 3-6 minutes per image on CPU, suitable for offline applications.
Authors: Chuanzhi Xu, Boyu Wei, Haoxian Zhou, Xuanhua Yin, Zihan Deng, Haodong Chen, Qiang Qu, Weidong Cai
Abstract: As 3D Gaussian Splatting (3DGS) gains attention in immersive media and digital content creation, assessing the aesthetics of 3D scenes becomes important in helping creators build more visually compelling 3D content. However, existing evaluation methods for 3D scenes primarily emphasize reconstruction fidelity and perceptual realism, largely overlooking higher-level aesthetic attributes such as composition, harmony, and visual appeal. This limitation comes from two key challenges: (1) the absence of general 3DGS datasets with aesthetic annotations, and (2) the intrinsic nature of 3DGS as a low-level primitive representation, which makes it difficult to capture high-level aesthetic features. To address these challenges, we propose Aes3D, the first systematic framework for assessing the aesthetics of 3D neural rendering scenes. Aes3D includes Aesthetic3D, the first dataset dedicated to 3D scene aesthetic assessment, built on our proposed annotation strategy for 3D scene aesthetics. In addition, we present Aes3DGSNet, a lightweight model that directly predicts scene-level aesthetic scores from 3DGS representations. Notably, our model operates solely on 3D Gaussian primitives, eliminating the need for rendering multi-view images and thus reducing computational cost and hardware requirements. Through aesthetics-supervised learning on multi-view 3DGS scene representations, Aes3DGSNet effectively captures high-level aesthetic cues and accurately regresses aesthetic scores. Experimental results demonstrate that our approach achieves strong performance while maintaining a lightweight design, establishing a new benchmark for 3D scene aesthetic assessment. Code and datasets will be made available in a future version.
Authors: Zhixin Cheng, Yujia Chen, Xujing Tao, Bohao Liao, Xiaotian Yin, Baoqun Yin, Tianzhu Zhang
Abstract: Image-to-point cloud registration is often challenged by viewpoint changes, cross-modal discrepancies, and repetitive textures, which induce scale ambiguity and consequently lead to erroneous correspondences. Recent detection-free methods alleviate this issue by leveraging multi-scale features and transformer-based interactions. However, they still suffer from attention drift across layers and intra-scale inconsistencies, hindering precise registration. Inspired by human behavior, we propose a ``Focus--Sweep'' paradigm and develop a Hierarchical Focus--Sweep Interaction Module within an SSM-based framework to enhance multi-level cross-modal feature association. In addition, we introduce a Dynamic Layer Allocation Strategy that adaptively determines the iteration depth to better exploit geometric constraints and improve matching robustness. Extensive experiments and ablations on two benchmarks, RGB-D Scenes V2 and 7-Scenes, demonstrate that our approach achieves state-of-the-art performance.
Authors: Henry Marichal, Diego Passarella, Gregory Randall
Abstract: Tree ring marking remains a key step in dendrometry and dendrochronology, but it is often performed manually, making the process time-consuming, subjective, and difficult to scale to large image datasets. We present the Tree Ring Analyzer Suite (TRAS), an open-source graphical software for automatic delineation, manual correction, and measurement of tree rings in wood cross-sectional images. TRAS integrates three complementary detection algorithms: the classical image-processing method CS-TRD and two deep-learning approaches, DeepCS-TRD and INBD. The interface allows users to refine automatic detections, remove false positives, and manually add missing rings. It also computes dendrochronological metrics such as earlywood and latewood areas, ring perimeter, equivalent ring width, and custom path-based ring-width measurements. TRAS was evaluated on 18 expertly annotated Pinus taeda L. cross-section images. DeepCS-TRD achieved the best automatic detection performance, with an F-score of 81.0% and precision of 86.4%. Automatic detection reduced the required manual correction effort to approximately 20% of ring boundaries. For one-dimensional ring-width measurements, TRAS showed excellent agreement with CooRecorder ($r > 0.99$). Common detection errors, such as jump propagation or false positives near knots, were easily corrected through the postprocessing interface. TRAS provides a flexible and reproducible solution for tree-ring analysis on Windows, macOS, and Linux. Code is available at the https://hmarichal93.github.io/tras.
Authors: Zhen Fang, Wenxuan Huang, Yu Zeng, Yiming Zhao, Shuang Chen, Kaituo Feng, Yunlong Lin, Lin Chen, Zehui Chen, Shaosheng Cao, Feng Zhao
Abstract: Existing Flow Matching (FM) text-to-image models suffer from two critical bottlenecks under multi-task alignment: the reward sparsity induced by scalar-valued rewards, and the gradient interference arising from jointly optimizing heterogeneous objectives, which together give rise to a 'seesaw effect' of competing metrics and pervasive reward hacking. Inspired by the success of On-Policy Distillation (OPD) in the large language model community, we propose Flow-OPD, the first unified post-training framework that integrates on-policy distillation into Flow Matching models. Flow-OPD adopts a two-stage alignment strategy: it first cultivates domain-specialized teacher models via single-reward GRPO fine-tuning, allowing each expert to reach its performance ceiling in isolation; it then establishes a robust initial policy through a Flow-based Cold-Start scheme and seamlessly consolidates heterogeneous expertise into a single student via a three-step orchestration of on-policy sampling, task-routing labeling, and dense trajectory-level supervision. We further introduce Manifold Anchor Regularization (MAR), which leverages a task-agnostic teacher to provide full-data supervision that anchors generation to a high-quality manifold, effectively mitigating the aesthetic degradation commonly observed in purely RL-driven alignment. Built upon Stable Diffusion 3.5 Medium, Flow-OPD raises the GenEval score from 63 to 92 and the OCR accuracy from 59 to 94, yielding an overall improvement of roughly 10 points over vanilla GRPO, while preserving image fidelity and human-preference alignment and exhibiting an emergent 'teacher-surpassing' effect. These results establish Flow-OPD as a scalable alignment paradigm for building generalist text-to-image models. The codes and weights will be released in: https://github.com/CostaliyA/Flow-OPD .
Authors: Mehrajul Abadin Miraj, Abdul Mohaimen Al Radi, Shariful Islam Rayhan, Md. Tanvir Alam, Ismat Rahman, Yu Tian, Md Mosaddek Khan
Abstract: Selecting informative frames from long videos is a combinatorial problem that existing methods address either through efficient heuristics without explicit modeling of query-conditioned temporal structure, or through multi stage retrieval pipelines with substantial preprocessing cost. We propose \textbf{CREST}, a training-free frame selection method grounded in the temporal geometry of query--frame relevance. CREST is based on the observation that relevance over time exhibits structured local variation: sharp curvature around salient events and flatter regions in redundant segments. By using local curvature to guide selection, CREST allocates a fixed frame budget more effectively across brief decisive events and slowly evolving evidence. Under a fixed backbone and frame budget, CREST achieves higher accuracy than AKS, a lightweight relevance--coverage baseline, on LongVideoBench and VideoMME, while retaining 93--95\% of the accuracy of MIRA, a stronger multi-stage retrieval pipeline, at only 3--4\% of its preprocessing cost.\footnote{Code and implementation details are included in the supplementary material and will be released publicly upon acceptance.} On TempRel, our diagnostic benchmark for temporal frame selection, CREST achieves a 6.88\% relative improvement over AKS. Pairwise LLM-as-a-judge evaluation further shows that CREST-selected frames yield more coherent frame-conditioned descriptions, with win rates of 60.58\% and 54.50\% on the two benchmarks. These results show that local temporal geometry provides a simple and efficient basis for long-video frame selection.
Authors: Zhilei Shu, Shangwen Zhu, Zihang Liang, Xiaofan Li, Qianyu Peng, Xinyu Cui, Bo Ye, Yiming Li, Fan Cheng, Jian Zhao, Yang Cao, Zheng-Jun Zha, Ruili Feng
Abstract: Director-style prompting, robotic action prediction, and interactive video agents demand temporal grounding over concurrent events -- a regime in which 68% of general clips and over 99% of robotics/gameplay clips contain overlapping events, yet existing multi-event generators rest on a single-active-prompt assumption. However, modern video generators, such as Diffusion Transformers (DiT), represent time as discrete points through point-wise positional encodings. This formulation creates a fundamental dimension mismatch: temporally extended intervals and overlapping events are mathematically unrepresentable to the attention mechanism. In this paper, we propose Time Interval Encoding (TIE), a principled, plug-and-play interval-aware generalization of rotary embeddings that elevates time intervals to first-class primitives inside DiT cross-attention. Rather than introducing another heuristic interval embedding, we show that, within RoPE-compatible bilinear attention, TIE is characterized by two basic principles: Temporal Integrability, which requires an event to aggregate positional evidence over its full duration, and Duration Invariance, which removes the trivial bias toward longer intervals. Under a uniform kernel, this characterization yields an efficient closed-form sinc-based solution that preserves the standard attention interface and naturally attenuates boundary noise through interval integration. Empirically, TIE preserves the visual quality of the base DiT model while substantially improving temporal controllability. In our experiments on the OmniEvents dataset, it improves human-verified Temporal Constraint Satisfaction Rate from 77.34% to 96.03% and reduces temporal boundary error from 0.261s to 0.073s, while also improving trajectory-level temporal alignment metrics. The code and dataset are available at https://github.com/MatrixTeam-AI/TIE.
Authors: Mengqi He, Xinyu Tian, Xin Shen, Shu Zou, Jinhong Ni, Zhaoyuan Yang, Weikang Li, Xuesong Li, Jing Zhang
Abstract: Recent studies show that gradient-based universal image jailbreaks on vision-language models (VLMs) exhibit little or no cross-model transferability, casting doubt on the feasibility of transferable multimodal jailbreaks. We revisit this conclusion under a strictly untargeted threat model without enforcing a fixed prefix or response pattern. Our preliminary experiment reveals that refusal behavior concentrates at high-entropy tokens during autoregressive decoding, and non-refusal tokens already carry substantial probability mass among the top-ranked candidates before attack. Motivated by this finding, we propose Untargeted Jailbreak via Entropy Maximization(UJEM)-KL, a lightweight attack that maximizes entropy at these decision tokens to flip refusal outcomes, while stabilizing the remaining low-entropy positions to preserve output quality. Across three VLMs and two safety benchmarks, UJEM-KL achieves competitive white-box attack success rates and consistently improves transferability, while remaining effective under representative defenses. Our experimental results indicate that the limited transferability primarily stems from overly constrained optimization objectives.
Authors: Yanting Miao, Yutao Sun, Dexin Wang, Mengyu Zhou, Pascal Poupart, Lei Lv, Qi Zhao, Li Wang, Hao Li, Xiaoxi Jiang, Guanjun Jiang
Abstract: Visual latent reasoning lets a multimodal large language model (MLLM) create intermediate visual evidence as continuous tokens, avoiding external tools or image generators. However, existing methods usually follow an output-as-input latent paradigm and yield unstable gains. We identify evidence for a feature-space mismatch that can contribute to this instability: dominant visual-latent models build on pre-norm MLLMs and reuse decoder hidden states as predicted latent inputs, even though these states occupy a substantially different norm regime from the input embeddings the model was trained to consume (Xie et al., 2025; Li et al., 2026; Team et al., 2026). This mismatch can make direct latent feedback unreliable. Motivated by this diagnosis, we propose GAP, a Granular Alignment Paradigm for visual latent modeling. GAP aligns visual latent reasoning at three levels: feature-level alignment maps decoder outputs into input-compatible visual latents through a lightweight PCA-aligned latent head; context-level alignment grounds latent targets with inspectable auxiliary visual supervision; and capacity-guided alignment assigns latent supervision selectively to examples where the base MLLM struggles. On Qwen2.5-VL 7B, the resulting model achieves the best mean aggregate perception and reasoning performance among our supervised variants. Inference-time intervention probing further suggests that generated latents provide task-relevant visual signal beyond merely adding token slots.
Authors: Qianxin Xia, Zhiyong Shu, Wenbo Jiang, Jiawei Du, Jielei Wang, Guoming Lu
Abstract: Dataset distillation aims to synthesize a compact proxy dataset that is unreadable or non-raw from the original dataset for privacy protection and highly efficient learning. However, previous approaches typically adopt a single-stage distillation paradigm, which suffers from learning specific patterns that overfit on a prior architecture, consequently suppressing the expression of semantics and leading to performance degradation across heterogeneous architectures. To address this issue, we propose a novel dual-stage distillation framework called ${\textbf{DIVER}}$, which leverages the pre-trained diffusion model to dive deeper into $\textbf{DI}$stilled data $\textbf{V}$ia $\textbf{E}$xpressive semantic $\textbf{R}$ecovery, an entire process of semantic inheritance, guidance, and fusion. Semantic inheritance distills high-level semantics of abstract distilled images into the latent space to filter out architecture-specific ``noise" and retain the intrinsic semantics. Furthermore, semantic guidance improves the preservation of the original semantics by directing the reverse procedure. Finally, semantic fusion is designed to provide semantic guidance only during the concrete phase of the reverse process, preventing semantic ambiguity and artifacts while maintaining the guidance information. Extensive experiments validate the effectiveness and efficiency of DIVER in improving classical distillation techniques and significantly improving cross-architecture generalization, requiring processing time comparable to raw DiT on ImageNet (256$\times$256) with only 4 GB of GPU memory usage.
Authors: Feijiang Li, Zhenxiong Li, Jieting Wang, Zizheng Jiu, Saixiong Liu, Liang Du
Abstract: Image clustering aims to partition unlabeled image datasets into distinct groups. A core aspect of this task is constructing and leveraging prior knowledge to guide the clustering process. Recent approaches introduce semantic descriptions as prior information, most of which typically relying on matching-based techniques with predefined vocabularies. However, the limited matching space restricts their adaptability to downstream clustering tasks. Moreover, these methods primarily focus on reducing bias to improve performance, frequently overlooking the importance of variance reduction. To address these limitations, we propose GSEC (Image Clustering based on Generative Semantic Guidance and Bi-Layer Ensemble), a framework designed to reduce bias through generative semantic guidance and mitigate variance via ensemble learning. Our method employs Multimodal Large Language Models to generate semantic descriptions and derive image embeddings via weighted averaging. Additionally, a bi-layer ensemble strategy integrates cross-modal information through BatchEnsemble in the inner layer and aligns outputs via an alignment mechanism in the outer layer. Comparative experiments demonstrate that GSEC outperforms 18 state-of-the-art methods across six benchmark datasets, while further analysis confirms its effectiveness in simultaneously reducing both bias and variance. The code is available at https://github.com/2017LI/GSEC.git.
Authors: Hansheng Chen, Jan Ackermann, Minseo Kim, Gordon Wetzstein, Leonidas Guibas
Abstract: Flow-based generation in high-dimensional spaces is difficult because velocity prediction requires modeling high-dimensional noise, even when data has strong low-rank structure. We present Asymmetric Flow Modeling (AsymFlow), a rank-asymmetric velocity parameterization that restricts noise prediction to a low-rank subspace while keeping data prediction full-dimensional. From this asymmetric prediction, AsymFlow analytically recovers the full-dimensional velocity without changing the network architecture or training/sampling procedures. On ImageNet 256$\times$256, AsymFlow achieves a leading 1.57 FID, outperforming prior DiT/JiT-like pixel diffusion models by a large margin. AsymFlow also provides the first-ever route for finetuning pretrained latent flow models into pixel-space models: aligning the low-rank pixel subspace to the latent space gives a seamless initialization that preserves the latent model's high-level semantics and structure, so finetuning mainly improves low-level mismatches rather than relearning pixel generation. We show that the pixel AsymFlow model finetuned from FLUX.2 klein 9B establishes a new state of the art for pixel-space text-to-image generation, beating its latent base on HPSv3, DPG-Bench, and GenEval while qualitatively showing substantially improved visual realism.
Authors: Yu He, Fang Li, Haoyang Tong, Lichen Ma, Xinyuan Shan, Jingling Fu, Dong Chen, Luohang Liu, Junshi Huang, Yan Li
Abstract: Recent advances in generative models have empowered impressive layered image generation, yet their success is largely confined to graphic design domains. The layering of in-the-wild images remains an underexplored problem, limiting fine-grained editing and applications of images in real-world scenarios. Specifically, challenges remain in scalable layered data and the modeling of object interaction in natural images, such as illumination effects and structural boundary. To address these bottlenecks, we propose a novel framework for high-fidelity natural image decomposition. First, we introduce an Agent-driven Data Decomposition (ADD) pipeline that orchestrates agents and tools to synthesize layered data without manual intervention. Utilizing this pipeline, we construct a large-scale dataset, named LiWi-100k, with over 100,000 high-quality layered in-the-wild images. Second, we present a novel framework that jointly improves photometric fidelity and alpha boundary accuracy. Specifically, shadow-guided learning explicitly models the illumination effects, and degradation-restoration objective provides boundary-correction supervision by recovering clean foreground image from degraded one. Extensive experiments demonstrate that our framework achieves state-of-the-art (SoTA) performance in natural image decomposition, outperforming existing models in RGB L1 and Alpha IoU metrics. We will soon release our code and dataset.
Authors: Sukju Oh, Sukkyu Sun
Abstract: Online surgical phase recognition (SPR) underpins context-aware operating-room systems and requires committing to a prediction at every frame from past context alone. Surgical video poses three demands that natural-video recognizers do not jointly address: procedures span tens of thousands of frames, time flows non-uniformly as long routine stretches are punctuated by brief phase-defining transitions, and the visual domain is narrow so backbone features are strongly correlated across channels. Existing recognizers either let per-frame cost grow with elapsed length, or hold cost bounded but advance state at a uniform rate with channel-independent dynamics, leaving the latter two demands unaddressed. We present SurgicalMamba, a causal SPR model built on Mamba2's structured state-space duality (SSD) that holds per-frame cost at O(d). It introduces three SSD-compatible components that jointly address these demands: a dual-path SSD block that separates long- and short-term regimes at the level of recurrent state; intensity-modulated stepping, a continuous-time time-warp that adapts the slow path's effective rate to phase-relevant information; and state regramming, a per-chunk Cayley rotation that opens cross-channel mixing in the otherwise axis-aligned SSM recurrence. The learned rotation planes inherit a phase-aligned structure without any direct supervision, offering an interpretable internal signature of surgical workflow. Across seven public SPR benchmarks, SurgicalMamba reaches state-of-the-art accuracy and phase-level Jaccard under strict online evaluation: 94.6%/82.7% on Cholec80 (+0.7 pp/+2.2 pp over the strongest prior) and 89.5%/68.9% on AutoLaparo (+1.7 pp/+2.0 pp), at 238.74 fps on a single GPU. Ablations isolate the contribution of each component. The code is publicly available at https://github.com/sukjuoh/Surgical-Mamba.
Authors: Qinwu Xu, Yifan Jiang, Haoyu Ren
Abstract: Optical character recognition (OCR) and multilingual text understanding remain major failure modes of multimodal large language models (MLLMs), particularly in real-world images containing cluttered layouts, small fonts, blur, occlusion, and complex typography. We present an OCR-aware multilingual multimodal training framework that combines (i) large-scale synthetic OCR-to-translation data generation, (ii) OCR-aware supervised fine-tuning (SFT) with LoRA adaptation, and (iii) structured visual chain-of-thought (CoT) prompting for reasoning under uncertain visual conditions. Using a LLaMA-based multimodal architecture, the proposed framework substantially improves OCR completeness, multilingual translation accuracy, and robustness under degraded visual conditions. Experimental results on multilingual receipts, menus, posters, signs, handwritten text, and document images demonstrate significantly improved visual-text grounding compared with the baseline model. In particular, the proposed OCR-aware post-training framework improves extraction of small, blurred, spatially scattered, and partially occluded text while reducing reliance on language priors under uncertain OCR conditions. Qualitative comparisons with frontier multimodal systems, including GPT-5-class and Gemini-family models, further suggest improved OCR grounding and reduced hallucination under noisy and visually ambiguous OCR scenarios. Overall, the results indicate that data-centric OCR-aware multimodal post-training provides an effective and scalable direction for improving multilingual OCR and OCR-based visual question answering systems.
Authors: Jihwan Kim, Nikhil Parthasarathy, Danfeng Qin, Junhwa Hur, Deqing Sun, Bohyung Han, Ming-Hsuan Yang, Boqing Gong
Abstract: The fundamental challenge in scaling Video Large Language Models (Video LLMs) to long-form video lies in managing the explosion of visual-token context length. Existing strategies predominantly focus on "post-hoc" token reduction -- reducing visual tokens after feature extraction to alleviate the LLM's computational overhead. While these methods effectively reduce the number of visual tokens, we observe that the primary latency bottleneck then shifts from the LLM to the expensive per-frame processing of the vision encoder. To address this, we introduce LiteFrame, a strong, yet highly efficient video encoder backbone for Video LLMs. To train LiteFrame, we propose Compressed Token Distillation (CTD), a novel training framework that teaches a compact student vision encoder to directly predict information-dense, spatio-temporally compressed representations produced by a large teacher vision model, effectively bypassing redundant computation. When coupled with further Language Model Adaptation (LMA), this approach results in a new latency-accuracy Pareto frontier -- compared with InternVL3-8B, LiteFrame provides a 35% reduction in end-to-end latency while processing 8$\times$ more frames and improves average video understanding accuracy across multiple benchmarks. Our results demonstrate a new potential path to unlocking longer-form video understanding under fixed compute budgets.
Authors: Yuting Yang, Haichao Jiang, Tianming Liang, Quan Zhang, Jian-Fang Hu
Abstract: Referring segmentation aims to segment the target objects in images or videos based on the textual query. Despite remarkable progress over the past years, existing works always assume that the user-provided queries are already precise and clear. However, this assumption is impractical. In real-world scenarios, it is unrealistic to expect all users to thoroughly review their visual content and carefully ensure their queries are unique and unambiguous. When encountering such cases, existing segmentation models tend to arbitrarily guess the user preferences, often resulting in undesired outcomes. To address this limitation, we propose IC-Seg, a novel agentic framework that proactively clarifies user intent through multi-turn conversation before segmentation. To effectively incentivize this capability, we further introduce Hi-GRPO, a new hierarchical optimization strategy that injects dense and informative supervision signals at the trajectory, turn, and step levels. This strategy encourages efficient intent clarification, effectively eliminating redundant interactions and improving overall dialogue quality. For evaluation, we establish Ambi-RVOS, a referring video object segmentation benchmark with ambiguous user queries. Extensive experiments demonstrate that IC-Seg not only outperforms existing methods by a large margin in resolving ambiguous queries, but also maintains state-of-the-art performance on standard reasoning segmentation benchmarks. Code and data will be released at https://github.com/iSEE-Laboratory/IC-Seg.
Authors: Jeongeun Park, Janghyeok Han, Geonung Kim, Hyun-Seung Lee, Kyuha Choi, Youngseok Han, Sunghyun Cho
Abstract: Video outpainting generates plausible visual content beyond the original spatial extent of a video, playing a key role in adapting videos to diverse display formats. To support such use cases, it must enable large spatial extrapolation over long sequences. However, most existing methods address only one of these challenges or lack explicit mechanisms for ensuring global spatio-temporal consistency, leading to notable limitations. In this paper, we propose HL-OutPaint, a high-resolution video outpainting framework for long sequences. Our approach follows a coarse-to-fine strategy with a two-stage pipeline. We first construct Global Coarse Guidance (GCG), a low-resolution representation that captures global structure and dominant motion across the video. Unlike naive downsampling, GCG is built via a novel global-local frame swapping mechanism that couples sparse global keyframes with local temporal windows and exchanges information during sampling. This enables GCG to encode both long-term structural consistency and short-term temporal dynamics in a unified representation. Guided by this representation, HL-OutPaint then performs high-resolution outpainting to generate spatially detailed and temporally consistent content. By separating global structure modeling from fine-grained synthesis, our framework achieves stable, coherent generation for large spatial expansion and long video sequences. Extensive experiments show that HL-OutPaint outperforms existing methods in challenging scenarios involving wide spatial extrapolation and long video sequences.
Authors: Lijun Zhou, Hongcheng Luo, Zhenxin Zhu, Cheng Chi, Mingfei Tu, Kaixin Xiong, Lei Gong, Zhanqian Wu, Zehan Zhang, Fangzhen Li, Hao Li, Yingying Shen, Jiale He, Haohui Zhu, Shan Zhao, Kai Wang, Zhiwei Zhan, Yuechuan Pu, Kaiyuan Tan, Ruiling Yang, Xianqi Wang, Tianyi Yan, Jiawei Zhou, Lei Zhang, Jingyang Zhao, Xi Zhou, Chitian Sun, Chenming Wu, Jiong Deng, Hongwei Xie, Ming Lu, Kun Ma, Long Chen, Guang Chen, Hangjun Ye, Bing Wang, Haiyang Sun
Abstract: This report presents a unified technical system addressing the two core capabilities of world models for autonomous driving: world representation and world generation. For world representation, we propose WorldRec, a feed-forward reconstruction architecture driven by sparse scene queries. WorldRec initializes structured queries in 3D space, leveraging them to aggregate cross-view, cross-temporal features, thereby naturally enforcing spatial consistency across frames and yielding compact yet high-fidelity 3D Gaussian scene representations. For world generation, we propose WorldGen, a two-stage training framework of bidirectional pretraining followed by causal fine-tuning through three progressive stages (Teacher Forcing, ODE distillation, and DMD), enabling high-quality online causal video generation in as few as 4 denoising steps. Building on both modules, we further introduce the JWM, which deeply integrates WorldRec and WorldGen to achieve synergistic gains in generation stability, cross-frame consistency, and visual fidelity, providing a solid foundation for closed-loop simulation, data synthesis, and end-to-end training in autonomous driving.
Authors: Longtao Jiang, Jianmin Bao, Zhendong Wang, Xin Tao, Pengfei Wan, Zhihui Li, Xiaojun Chang
Abstract: Normalizing flows (NFs) provide exact likelihoods and deterministic invertible sampling, but have historically lagged behind diffusion models for large-scale image generation. We identify a key obstacle: NFs are required to learn a single invertible transport over the full ambient space, making them highly sensitive to high-dimensional representations. This leads to a semantic-capacity mismatch in modern visual representation spaces, where semantic information is compact but encoded in overcomplete features. We propose SRC-Flow, which introduces a Semantic Representation Compressor (SRC) to compact high-dimensional RAE features into a low-dimensional semantic space before flow modeling and preserve reconstruction through the frozen RAE decoder. This compact space reduces the modeling burden of NFs and enables effective likelihood-based generation in semantic representation space. We further adopt constant noise regularization tailored to the fixed unconditional bijection learned by flows. On ImageNet $256 \times 256$ and $512 \times 512$, SRC-Flow achieves state-of-the-art generation quality among normalizing flow methods, with gFID scores of 1.65 and 2.07 under classifier-free guidance, while retaining exact likelihood computation in the compact semantic representation space and deterministic invertible sampling at the flow level. Codes and models will be available at https://github.com/longtaojiang/SRC-Flow.
Authors: Yining Hong, Jiageng Liu, Han Yin, Manling Li, Leonidas Guibas, Li Fei-Fei, Jiajun Wu, Yejin Choi
Abstract: Spatial intelligence unfolds through a perception-action loop: agents act to acquire observations, and reason about how observations vary as a function of action. Rather than passively processing what is seen, they actively uncover what is unseen - occluded structure, dynamics, containment, and functionality that cannot be resolved from passive sensing alone. We move beyond prior formulations of spatial intelligence that assume oracle observations by recasting the observer as an actor. We introduce ESI-BENCH, a comprehensive benchmark for embodied spatial intelligence spanning 10 task categories and 29 subcategories built on OmniGibson, grounded in Spelke's core knowledge systems. Agents must decide what abilities to deploy - perception, locomotion, and manipulation - and how to sequence them to actively accumulate task-relevant evidence. We conduct extensive experiments on state-of-the-art MLLMs and find that active exploration substantially outperforms passive counterparts, with agents spontaneously discovering emergent spatial strategies without explicit instructions, while random multi-view often adds noise rather than signal despite consuming far more images. Most failures stem not from weak perception but from action blindness: poor action choices lead to poor observations, which in turn drive cascading errors. While explicit 3D grounding stabilizes reasoning on depth-sensitive tasks, imperfect 3D representation proves more harmful than 2D baselines by distorting spatial relations. Human studies further reveal that unlike humans who seek falsifying viewpoints and revise beliefs under contradiction, models commit prematurely with high confidence regardless of evidence quality, exposing a metacognitive gap that neither better perception nor more embodied interaction alone can close.
Authors: Xiangxiang Cui, Tianjin Huang, Yifang Wang, Lijie Hu, Lu Yin
Abstract: Medical foundation models have achieved remarkable clinical performance, yet their robustness under real-world perturbations remains underexplored. We present a robustness benchmark comprising 40 perturbation types (12 base, 28 medical-specific) across eight imaging modalities, evaluating five VLMs (LLaVA-Med, MedGemma, MedGemma-1.5, Gemini-2.5-flash and GPT-4o-mini) on VQA, visual grounding, and captioning, alongside two segmentation models (MedSAM, SAM-Med2D) with five fine-tuning strategies. Our findings reveal: (1) Fine-tuning strategy dominates robustness, with LoRA exhibiting nearly double the degradation of full fine-tuning, while SAM-Med2D's Adapter offers favorable efficiency-robustness trade-off. (2) Medical-specific perturbations disproportionately damage segmentation, with 9 of 15 top corruptions being domain-specific. (3) LoRA-tuned visual grounding drops over 40 points, whereas zero-shot captioning remains stable (<7% drop). Zero-shot VQA shows model-dependent robustness--medical models drop under 20% while Gemini-2.5-flash drops 54%. General-purpose VLMs achieve higher VQA accuracy but fail on grounding; among medical VLMs, MedGemma demonstrates the best overall stability. These results provide deployment guidelines and underscore the necessity of domain-specific robustness evaluation for medical AI. Our code is available at: https://abnerai.github.io/MedFM-Robust.
Authors: Jiusong Ge, Yingkang Zhan, Wenjie Zhao, Di Zhang, Ke Wang, Jiashuai Liu, Chunze Yang, Chengzu Li, Jian Zhang, Yuxin Dong, Ni Zhang, Qidong Liu, Mireia Crispin-Ortuzar, Huazhu Fu, Chen Li, Zeyu Gao
Abstract: Traditional whole slide image (WSI) analysis methods typically rely on the multiple instance learning (MIL) paradigm, which extracts patch-level features at high magnification and aggregates them for slide-level prediction. However, such exhaustive patch-level processing is computationally expensive, severely limiting the efficiency and scalability of WSI analysis. To address this challenge, we propose PathCTM (a Pathology-oriented Continuous Thought Model) that enables token-efficient scale-space continuous reasoning for gigapixel WSIs. PathCTM formulates diagnostic inference as a dynamic sequential information pursuit. It progressively transitions from low-magnification global to high-magnification local inspection, and adaptively terminates inference when sufficient evidence is gathered to effectively bound decision uncertainty. Specifically, it uses conditional computation for dynamic scale switching with attention-guided region pruning, coupled with confidence-aware early stopping. Extensive experiments demonstrate that, compared with standard MIL-based methods, PathCTM reduces the number of required image patches by 95.95% and shortens inference time by approximately 95.62%, while maintaining AUC without degradation. Code is available at https://github.com/JSGe-AI/PathCTM.
Authors: Yi Sun, Zhiqi Zhang, Xinhao Zhong, Yimin Zhou, Shuoyang Sun, Bin Chen, Shu-Tao Xia, Ke Xu
Abstract: Recent advances in flow matching models have significantly improved text-to-image generation quality, but also introduce growing safety risks due to the generation of harmful or undesirable content. Existing concept erasure methods are either inference-time interventions with limited effectiveness or rely on supervised fine-tuning (SFT), which requires precisely aligned data and struggles with scalability and multi-concept settings. In this paper, we propose \emph{FlowErase-RL}, the first GRPO-based framework for concept erasure in flow matching models. We reformulate concept erasure as a reward optimization problem and introduce a \textbf{dynamic dual-path reward mechanism} that jointly optimizes (i) a Concept Erasure (CE) reward to suppress target concepts and (ii) a Non-target Space (NS) reward to preserve generative fidelity. The two reward paths are adaptively balanced during training via a performance-driven switching strategy, enabling stable optimization without explicit supervision. Extensive experiments on nudity, object, and artistic style erasure demonstrate that our method achieves state-of-the-art erasure performance while maintaining strong image quality and semantic alignment. Moreover, it exhibits robust resistance to adversarial attacks and scales effectively to multi-concept scenarios. Our results establish a new paradigm for safe and controllable generation in flow matching models.
Authors: Gueter Josmy Faure, Min-Hung Chen, Jia-Fong Yeh, Hung-Ting Su, Winston H. Hsu
Abstract: Vision-Language Models (VLMs) have demonstrated remarkable capabilities in general video understanding, yet they often struggle with the fine-grained comprehension crucial for real-world applications requiring nuanced interpretation of human actions and interactions. While some recent human-centric benchmarks evaluate aspects of model behaviour such as fairness/ethics, emotion perception, and broader human-centric metrics, they do not combine long-form videos, very dense QA coverage, and frame-level spatial/temporal grounding at scale. To bridge this gap, we introduce FineBench, a human-centric video question answering (VQA) benchmark specifically designed to assess fine-grained understanding. FineBench comprises 199,420 multiple-choice QA pairs densely annotated across 64 long-form videos (15 minutes each), focusing on detailed person movement, person interaction, and object manipulation, including compositional actions. Our extensive evaluation reveals that while proprietary models like GPT-5 achieve respectable performance, current open-source VLMs significantly underperform, struggling particularly with spatial reasoning in multi-person scenes and distinguishing subtle differences in human movements and interactions. To address these identified weaknesses, we propose FineAgent, a modular framework that enhances VLMs by leveraging a Localizer and a Descriptor. Experiments show that FineAgent consistently improves the performance of various open VLMs on FineBench. FineBench provides a rigorous testbed for future research into fine-grained human-centric video understanding, while FineAgent offers a practical approach to enhance such reasoning in current VLMs. Project page and code at https://joslefaure.github.io/assets/html/finebench.html.
URLs: https://joslefaure.github.io/assets/html/finebench.html.
Authors: Jiayi Chen, Benteng Ma, Zehui Liao, Winston Chong, Yasmeen George, Jianfei Cai
Abstract: While medical Multimodal Large Language Models (MLLMs) have shown promise in assisting diagnosis, they still frequently generate hallucinated responses that appear linguistically plausible but lack visual evidence. Such hallucinations pose risks to clinical decision-making and necessitate effective detection. Existing introspective detection methods primarily perform uncertainty estimation or logical verification by analyzing model responses conditioned on original or perturbed inputs. However, such external perturbations are often heuristic and context-agnostic, which overlooks the internal cross-modal dependency between generated tokens and related visual tokens during decoding. To address this issue, we propose VIHD, a Visual Intervention-based Hallucination Detection method that leverages targeted visual token masking to calibrate semantic entropy for more effective hallucination detection. VIHD locates visually dominant decoder layers via Visual Dependency Probing (VDP), executes Visual Intervention Decoding (VID) via token masking to calibrate the semantic distribution, and quantifies the resulting Calibrated Semantic Entropy (CSE) as a reliable hallucination signal. Extensive experiments on three medical VQA benchmarks with two medical MLLMs demonstrate that VIHD consistently outperforms state-of-the-art methods, underscoring the importance of fine-grained visual dependency for hallucination detection. The code will be available at https://github.com/Jiayi-Chen-AU/VIHD
Authors: Rajarshi Roy, Nasrin Imanpour, Ashhar Aziz, Shashwat Bajpai, Gurpreet Singh, Shwetangshu Biswas, Kapil Wanaskar, Parth Patwa, Subhankar Ghosh, Shreyas Dixit, Nilesh Ranjan Pal, Vipula Rawte, Ritvik Garimella, Amitava Das, Amit Sheth, Vasu Sharma, Aishwarya Naresh Reganti, Vinija Jain, Aman Chadha
Abstract: The rapid advancements in generative AI technologies, such as Stable Diffusion, DALL-E, and Midjourney, have significantly transformed the creation of synthetic visual content. While these models enable innovation across industries, they also pose serious challenges, including misinformation, disinformation, and biased content generation. The increasing realism of AI-generated images makes their detection a pressing concern for researchers, policymakers, and industry stakeholders. In this paper, we present the findings of the Defactify 4.0 workshop, which introduced the Counter Turing Test (CT2) for AI-Generated Image Detection. The competition consisted of two key tasks: (1) binary classification of images as either AI-generated or real and (2) identification of the specific generative model responsible for an AI-generated image. To support both tasks, we employed the MS COCOAI dataset, a benchmark of 96000 real and synthetic images generated by five state-of-the-art models alongside real images from MS COCO. Participants employed diverse detection strategies, including convolutional neural networks (CNNs), Vision Transformers (ViTs), frequency-based analysis, contrastive learning, and multimodal techniques. The results demonstrated that while AI-generated images can be detected with high accuracy (F1-score > 0.83), identifying the exact model used remains significantly more challenging (highest F1-score: 0.4986). These findings highlight the need for improved model fingerprinting, adversarial robustness, and real-time detection mechanisms.
Authors: Liangsi Lu, Minzhe Guo, Xuhang Chen, Yang Shi
Abstract: Despite the generative capabilities of diffusion and flow models, real-image editing remains constrained by a persistent trade-off between semantic editability and structural fidelity. We trace a primary cause of this limitation to the implicit coupling of edit progress with model scale in existing paradigms. Under this coupling, stronger edits typically require visiting noisier states, which spends computation on destabilizing layout before the semantic change is well localized. We introduce NaviEdit, a training-free inference-time controller that decouples edit progress from model scale traversal through a strict self-consistency contract. NaviEdit operates at the rollout level and leaves the underlying pretrained model unchanged. It treats scale as a control input and reallocates a fixed step budget toward semantically responsive intermediate scales instead of destructive high-noise regimes. Experiments show positive average gains across compatible editors and flow backbones, supporting decoupling as a portable inference-time control principle.
Authors: Junghyun Lee, Hyunseo Kim, Hanna Jang, Junhyug Noh
Abstract: Blended emotion recognition is challenging because emotions are often expressed as mixtures of subtle and overlapping multimodal cues rather than a single dominant signal. We propose a rank-aware multi-encoder framework that selectively combines complementary representations from diverse pre-extracted video and audio encoders. Our method projects heterogeneous encoder features into a shared latent space, estimates sample-wise encoder importance through an attention-based gating module, and fuses only the top-n most informative encoders. To better model blended emotions, we decouple prediction into presence and salience heads and align them through probability-level fusion. We further incorporate feature-level unsupervised domain adaptation without pseudo-labeling to improve robustness under distribution shift. Experiments on the BlEmoRE challenge show that the proposed framework outperforms strong individual encoders and na\"ive multi-encoder fusion baselines. Our final system ranked 2nd in the competition, supporting the effectiveness of rank-aware selective fusion for fine-grained blended emotion recognition.
Authors: Yue Zhou, Erxuan Wu, Yikang Sun, Hongjoo Lee, Yuan Bi, Huixiong Xu, Nassir Navab, Zhongliang Jiang
Abstract: Vision-Language Models (VLMs) have significantly advanced medical visual question answering, yet their performance in ultrasound remains suboptimal. In clinical practice, sonographers explicitly focus on lesion regions to formulate reports, though diagnostic interpretations sometimes vary due to inherent subjectivity. However, existing VLMs are not explicitly structured to interactively zoom into lesions prior to diagnosis; moreover, they typically treat annotations as unbiased ground truths, failing to account for their inherent subjectivity and ambiguity. In this paper, we propose a framework specifically designed to consider the sonographer's cognitive workflow. We first introduce a structured Zoom-then-Diagnose paradigm, which replicates the interactive search process to enable lesion-focused reasoning. Furthermore, within the Group Relative Policy Optimization (GRPO) framework, we introduce an uncertainty-aware reward derived from stochastic group-wise rollouts to estimate prediction consistency as a proxy for model confidence. Together, these two components encourage the model to reinforce accurate predictions on clear cases while remaining cautious under ambiguity. Experiments across liver, breast, and thyroid datasets show that our framework improves lesion localization by 39.3\%, demonstrating that our model has learned the ability to actively look closer and diagnose.
Authors: Yongjin Cui, Xiaohui Fan
Abstract: We observe that existing model interpretation methods generally ignore the baseline, and such neglect often results in imprecise or even incorrect interpretation. In this paper, we reformulate the task of model interpretation and the interpretation principles for model interpretation results to demonstrate the importance of the baseline. We further unify gradient-based methods, Integrated Gradients (IG) methods, and Taylor expansion, clarifying the connections among them and explicitly identifying the baseline for each method. On this basis, we analyze the flaws and errors in related model interpretation methods (IG, LayerCAM, ODAM, Difference Map). We advocate evaluating the quality of model interpretation results precisely through the attribution error between the attribution result and the attribution target, rather than adopting flawed evaluation methods, such as those based on marginal-effect or the assumption of perfect model performance. We revise IG and develope a model interpretation method with a clear and reasonable baseline, achieving better results. Our method supports model interpretation based on features from any layer. Interpretation based on features from different layers are all reasonable, and the differences among these results reflect varying degrees of feature extraction at different feature extraction stages.
Authors: Xingtian Pei, Yukun Song, Changwei Wang, Shunpeng Chen, Rongtao Xu, Shengpeng Xu, Shibiao Xu
Abstract: Composed Image Retrieval (CIR) requires both preserving the visual continuity of the reference image and faithfully executing the semantic variables specified in the modification text, which constitute the core challenge of the task. Existing methods often suffer from Perception Myopia in a single space, or fall into Logic Drift in iterative collaboration due to the perception ceiling of the underlying retriever. To address this issue, we propose a one-stop hierarchical Perception-to-Deliberation Framework (PDF), which, to the best of our knowledge, is the first to introduce experience self-evolution and Test-Time Scaling Laws (TTS) into CIR. Relying on a hierarchical multi-agent architecture, PDF first utilizes an Intent Routing Manager to dynamically dispatch multi-view Worker perception signals based on modification intents to construct a high-recall candidate pool. Subsequently, the Decision Manager combines a Training-free Reasoning Policy Distillation mechanism with a Tournament-style TTS (T-TTS) strategy to achieve self-evolving fine-grained reasoning, yielding the final retrieval results. Experimental results demonstrate that PDF achieves SOTA performance on three benchmark datasets: CIRR, CIRCO, and FashionIQ. This study indicates that experience-driven self-evolution and TTS represent a highly promising and scalable path for achieving zero-shot fine-grained multimedia retrieval. The code will be made publicly available upon acceptance.
Authors: Baiyu Chen, Zechen Li, Wilson Wongso, Lihuan Li, Xiachong Lin, Hao Xue, Benjamin Tag, Flora Salim
Abstract: As wearable and mobile devices become increasingly embedded in daily life, they offer a practical way to continuously sense human motion in the wild. But inertial signals are highly dependent on the sensing setup, including body location, mounting position, sensor orientation, device hardware, and sampling protocol. This setup dependence makes it difficult to learn motion representations that transfer across devices and datasets, and limits the broader use of wearable IMUs beyond closed-set recognition. We introduce AnyMo, a geometry-aware framework for setup-agnostic human motion modeling. AnyMo uses physics-grounded IMU simulation over dense body-surface placements to generate diverse and plausible synthetic signals, pre-trains a graph encoder from paired synthetic placement views and masked partial observations, tokenizes multi-position IMU into full-body motion tokens, and aligns these tokens with an LLM for motion-language understanding. We evaluate AnyMo on three complementary tasks: zero-shot activity recognition across 14 unseen downstream datasets, cross-modal retrieval, and wearable IMU motion captioning, where it improves average Accuracy/F1/R@2 by 11.7\%/11.6\%/22.6\% on HAR, increases zero-shot IMU-to-text and text-to-IMU retrieval MRR by 15.9\% and 28.6\%, respectively, and improves zero-shot captioning BERT-F1 by 18.8\%. These results support AnyMo as a generalist model for wearable motion understanding in the wild. Project page: https://baiyuchen.com/project/AnyMo.
Authors: Jiahao Wang, Bo Sun, Yijing Bai, Vincent Casser, Songyou Peng, Zehao Zhu, Meng-Li Shih, Xander Masotto, Shih-Yang Su, Kanaad V Parvate, Tiancheng Ge, Linn Bieske, Dragomir Anguelov, Mingxing Tan, Chiyu Max Jiang
Abstract: Robust training and validation of Autonomous Driving Systems (ADS) require massive, diverse datasets. Proprietary data collected by Autonomous Vehicle (AV) fleets, while high-fidelity, are limited in scale, diversity of sensor configurations, as well as geographic and long-tail-behavioral coverage. In contrast, in-the-wild data from sources like dashcams offers immense scale and diversity, capturing critical long-tail scenarios and novel environments. However, this unstructured, in-the-wild video data is incompatible with ADS expecting structured, multi-modal sensor inputs for validation and training. To bridge this data gap, we propose Sensor2Sensor, a novel generative modeling paradigm that translates in-the-wild monocular dashcam videos into a high-fidelity, multi-modal sensor suite (AV logs) comprising multi-view camera images and LiDAR point clouds. A core challenge is the lack of paired training data. We address this by converting real AV logs into dashcam-style videos via 4D Gaussian Splatting (4DGS) reconstruction and novel-view rendering. Sensor2Sensor then utilizes a diffusion architecture to perform the generative conversion. We perform comprehensive quantitative evaluations on the fidelity and realism of the generated sensor data. We demonstrate Sensor2Sensor's practical utility by converting challenging in-the-wild internet and dashcam footage into realistic, multi-modal data formats, further unlocking vast external data sources for AV development.
Authors: Xiang Fang, Yuchong Hu, Pan Zhou, Dapeng Oliver Wu
Abstract: Real data often appear in the form of multiple incomplete views. Incomplete multi-view clustering is an effective method to integrate these incomplete views. Previous methods only learn the consistent information between different views and ignore the unique information of each view, which limits their clustering performance and generalizations. To overcome this limitation, we propose a novel View Variation and View Heredity approach (V3H). Inspired by the variation and the heredity in genetics, V3H first decomposes each subspace into a variation matrix for the corresponding view and a heredity matrix for all the views to represent the unique information and the consistent information respectively. Then, by aligning different views based on their cluster indicator matrices, V3H integrates the unique information from different views to improve the clustering performance. Finally, with the help of the adjustable low-rank representation based on the heredity matrix, V3H recovers the underlying true data structure to reduce the influence of the large incompleteness. More importantly, V3H presents possibly the first work to introduce genetics to clustering algorithms for learning simultaneously the consistent information and the unique information from incomplete multi-view data. Extensive experimental results on fifteen benchmark datasets validate its superiority over other state-of-the-arts.
Authors: Xiang Fang, Daizong Liu, Pan Zhou, Zichuan Xu, Ruixuan Li
Abstract: This paper studies the multimedia problem of temporal sentence grounding (TSG), which aims to accurately determine the specific video segment in an untrimmed video according to a given sentence query. Traditional TSG methods mainly follow the top-down or bottom-up framework and are not end-to-end. They severely rely on time-consuming post-processing to refine the grounding results. Recently, some transformer-based approaches are proposed to efficiently and effectively model the fine-grained semantic alignment between video and query. Although these methods achieve significant performance to some extent, they equally take frames of the video and words of the query as transformer input for correlating, failing to capture their different levels of granularity with distinct semantics. To address this issue, in this paper, we propose a novel Hierarchical Local-Global Transformer (HLGT) to leverage this hierarchy information and model the interactions between different levels of granularity and different modalities for learning more fine-grained multi-modal representations. Specifically, we first split the video and query into individual clips and phrases to learn their local context (adjacent dependency) and global correlation (long-range dependency) via a temporal transformer. Then, a global-local transformer is introduced to learn the interactions between the local-level and global-level semantics for better multi-modal reasoning. Besides, we develop a new cross-modal cycle-consistency loss to enforce interaction between two modalities and encourage the semantic alignment between them. Finally, we design a brand-new cross-modal parallel transformer decoder to integrate the encoded visual and textual features for final grounding. Extensive experiments on three challenging datasets show that our proposed HLGT achieves a new state-of-the-art performance.
Authors: Ruinan Jin, Minghui Chen, Qiong Zhang, Xiaoxiao Li
Abstract: Federated Learning (FL) enables collaborative model training across distributed clients while preserving user privacy. Recently, Federated Unlearning (FU) has emerged to address the "right to be forgotten" and to remove the influence of poisoned or target clients without retraining the entire FL system. However, many FU methods require communication with retained or target clients, introduce additional security risks, or store historical models, limiting their efficiency and practicality. Moreover, most FU methods for deep neural networks (DNNs) lack theoretical certification due to the complexity of nonlinear models and their training dynamics. In this work, we introduce Forgettable Federated Linear Learning, a training and unlearning framework for DNNs. Our approach uses pre-trained models to linearly approximate DNNs and achieve performance comparable to the original networks through Federated Linear Training. We further present a certified, efficient, and secure unlearning strategy that enables the server to remove a target client's influence without additional client communication or storage. Extensive experiments on small- to large-scale datasets, using both convolutional neural networks and modern foundation models, show that our method balances model accuracy with effective target-client unlearning. This work provides a practical pipeline for efficient and trustworthy FU. Code: https://github.com/Nanboy-Ronan/2F2L-Federated-Unlearning
URLs: https://github.com/Nanboy-Ronan/2F2L-Federated-Unlearning
Authors: Anton Fran\c{c}ois, Rapha\"el Tinarrage
Abstract: We investigate a framework for train-free MRI segmentation based on Topological Data Analysis. The pipeline proceeds in three steps, first identifying the whole object to segment via automatic thresholding, then detecting a distinctive subset whose topology is known in advance, and finally deducing the various components of the segmentation. A key ingredient is the extraction of approximate representative cycles from persistence diagrams, which provides an interpretable link between persistent features and anatomical components. To clarify the method's scope, we make the underlying topological and intensity assumptions explicit, quantify when they hold on real data, and analyze typical failure modes. We evaluate the approach on glioblastoma and on fetal cortical plate segmentation, with comparisons to unsupervised and deep-learning references. By operating without large annotated datasets, the method is well suited to scarce-data settings and provides an interpretable baseline and practical initialization for expert refinement or learning-based pipelines.
Authors: Jonathan von Rad, Florian Seuffert
Abstract: Deep Neural Networks (DNNs) are often over-parameterized for their tasks and can be compressed quite drastically by removing weights, a process called pruning. We investigate the impact of different pruning techniques on the classification performance and interpretability of GoogLeNet. We systematically apply unstructured and structured pruning, as well as connection sparsity (pruning of input weights) methods to the network and analyze the outcomes regarding the network's performance on the validation set of ImageNet. We also compare different retraining strategies, such as iterative pruning and one-shot pruning. We find that with sufficient retraining epochs, the performance of the networks can approximate the performance of the default GoogLeNet - and even surpass it in some cases. To assess interpretability, we employ the Mechanistic Interpretability Score (MIS) developed by Zimmermann et al. . Our experiments reveal that there is no significant relationship between interpretability and pruning rate when using MIS as a measure. Additionally, we observe that networks with extremely low accuracy can still achieve high MIS scores, suggesting that the MIS may not always align with intuitive notions of interpretability, such as understanding the basis of correct decisions.
Authors: Xing Hu, Xiangcheng Liu, Qianqian Duan, Lian Zhang, Huiliang Shang, Linghua Jiang, Haima Yang, Dawei Zhang
Abstract: Hyperspectral image (HSI) analysis plays a critical role in remote sensing, agriculture, and environmental monitoring. However, traditional methods often struggle to handle the high dimensionality, spectral redundancy, and noise inherent in HSI data, limiting their accuracy and scalability. Recently, diffusion models including denoising diffusion probabilistic models and other generative frameworks based on stochastic differential equations have shown strong potential in capturing complex spectral spatial structures and generating high fidelity HSI data. These models offer effective solutions for tasks such as noise supression, data augmentation, classification, and anomaly detection. This review presents a systematic summary of recent advances in diffusion models for HSI processing. We categorize existing methods, highlight their strengths in handling high dimensional data, and compare their performance with conventional approaches. Special attention is given to critical applications such as change detection and post disaster anomaly identification. The review also discusses current limitations, such as computational cost and training stability, and outlines potential research directions. Our main contributions can be summarized as follows: we provide a systematic taxonomy of diffusion based HSI methods, examine their applications across major remote sensing tasks, and offer perspectives on potential directions for future research. With these efforts, this review seeks to support the community in harnessing deep learning models to achieve more effective and efficient hyperspectral image analysis.
Authors: Weiqing Xiao, Hao Huang, Chonghao Zhong, Yujie Lin, Nan Wang, Xiaoxue Chen, Zhaoxi Chen, Saining Zhang, Shuocheng Yang, Pierre Merriaux, Lei Lei, Hao Zhao
Abstract: Autonomous driving simulators still lack high-fidelity radar, even though radar is critical for robust perception in adverse weather. A key obstacle is that raw radar point clouds are extremely sparse and stochastic, making it difficult to model; we argue that simulating the full range-azimuth-Doppler cube is a more principled target. Existing radar cube simulators either rely purely on neural generators, which are opaque and offer little control over sensor attributes, or on detailed electromagnetic pipelines, which are slow, require proprietary hardware specifications, and still struggle to capture real-world complexity. We introduce Ctrl-RS, a controllable radar cube simulation framework that combines the strengths of both worlds. First, we build an environment reflection tensor from diverse sensor sources (including LiDAR, monocular cameras, and existing radar). Second, we abstract radar physics into a compact set of waveform parameters that characterize the 3D point spread function, yielding an intuitive embedding of radar attributes such as range resolution, Doppler broadening, and azimuth beam shape. Third, we train a WARP-Net on a large mixed dataset that fuses real, analytically synthesized, and simulator-generated radar cubes to cover a wide distribution of radar attributes. Ctrl-RS supports viewpoint changes, actor removal, and attribute editing. Experiments on RADDet, Carrada, and nuScenes show that our simulated data can match or surpass real radar in 2D detection and semantic segmentation, and consistently boosts performance in 3D detection when combined with real data. The Project is available at https://github.com/zhuxing0/Ctrl-RS.
Authors: Shangpin Peng, Weinong Wang, Zhuotao Tian, Senqiao Yang, Xing Wu, Haotian Xu, Chengquan Zhang, Takashi Isobe, Baotian Hu, Min Zhang
Abstract: Direct Preference Optimization (DPO) has emerged as a cornerstone of reinforcement learning from human feedback (RLHF) due to its simplicity and efficiency. However, existing DPO-based methods typically treat all preference pairs equally, overlooking substantial variations in data quality and learning difficulty, which leads to inefficient data utilization and suboptimal performance. To address this limitation, we propose Uni-DPO, a unified dynamic preference optimization framework that jointly considers (a) the inherent quality of preference pairs and (b) the model's evolving performance during training. By adaptively reweighting samples based on both factors, Uni-DPO enables more effective use of preference data and achieves superior performance. Extensive experiments across models and benchmarks demonstrate the effectiveness and generalization of Uni-DPO. On textual tasks, Gemma-2-9B-IT fine-tuned with Uni-DPO surpasses the leading LLM, Claude 3 Opus, by 6.7 points on Arena-Hard. On mathematical and multimodal tasks, Uni-DPO consistently outperforms baseline methods across all benchmarks, providing strong empirical evidence of its effectiveness and robustness.
Authors: Peiting Tian, Xi Chen, Haixia Bi, Fan Li
Abstract: Medical image segmentation plays a crucial role in clinical diagnosis and treatment planning, where accurate boundary delineation is essential for precise lesion localization, organ identification, and quantitative assessment. In recent years, deep learning-based methods have significantly advanced segmentation accuracy. However, two major challenges remain. First, the performance of these methods heavily relies on large-scale annotated datasets, which are often difficult to obtain in medical scenarios due to privacy concerns and high annotation costs. Second, clinically challenging scenarios, such as low contrast in certain imaging modalities and blurry lesion boundaries caused by malignancy, still pose obstacles to precise segmentation. To address these challenges, we propose MedSAM-CA, an architecture-level fine-tuning approach that mitigates reliance on extensive manual annotations by adapting the pretrained foundation model, Medical Segment Anything (MedSAM). MedSAM-CA introduces two key components: the Convolutional Attention-Enhanced Boundary Refinement Network (CBR-Net) and the Attention-Enhanced Feature Fusion Block (Atte-FFB). CBR-Net operates in parallel with the MedSAM encoder to recover boundary information potentially overlooked by long-range attention mechanisms, leveraging hierarchical convolutional processing. Atte-FFB, embedded in the MedSAM decoder, fuses multi-level fine-grained features from skip connections in CBR-Net with global representations upsampled within the decoder to enhance boundary delineation accuracy. Experiments on publicly available datasets covering dermoscopy, CT, and MRI imaging modalities validate the effectiveness of MedSAM-CA. On dermoscopy dataset, MedSAM-CA achieves 94.43% Dice with only 2% of full training data, reaching 97.25% of full-data training performance, demonstrating strong effectiveness in low-resource clinical settings.
Authors: Cassandra Tong Ye, Shamus Li, Tyler King, Kristina Monakhova
Abstract: While deep learning offers tremendous promise for scientific and medical imaging, any failures and hallucinations (predictions that do not coincide with reality) are hard to pinpoint and can have serious downstream consequences. Uncertainty estimation techniques, such as conformal prediction, can help by predicting statistically valid error bars for a model's prediction. However, popular conformal prediction methods were not designed for high-dimensional image-valued problems and do not take into account spatial correlations within an image during conformal calibration, resulting in larger-than-necessary uncertainty intervals. We propose a practical simultaneous quantile regression method that enables non-linear, spatially-adaptive scaling during conformal calibration. Our method, QUTCC uses a U-Net architecture with a quantile embedding to learn a full conditional quantile distribution during training, and then leverages this non-linear, learned function for spatially-adaptive conformal calibration. At test time, our method can efficiently estimate uncertainty intervals with pixel-marginal coverage guarantees. In addition, QUTCC can also predict pixel-wise conditional probability density estimates without any built-in distributional assumptions. We evaluate our method on several denoising problems, accelerated magnetic resonance imaging, and quantitative phase microscopy. Our method consistently produces tighter uncertainty intervals than prior conformal methods at the same coverage level, can predict plausible conditional distributions for different tasks, and in some cases, high-uncertainty regions can help us locate hallucinations in a model's prediction.
Authors: Kateryna Lutsai
Abstract: Digitization projects in humanities often generate vast quantities of page images from historical documents, presenting significant challenges for manual sorting and analysis. These archives contain diverse content, including various text types (handwritten, typed, printed), graphical elements (drawings, maps, photos), and layouts (plain text, tables, forms). Efficiently processing this heterogeneous data requires automated methods to categorize pages based on their content, enabling tailored downstream analysis pipelines. This project addresses this need by developing and evaluating an image classification system specifically designed for historical document pages, leveraging advancements in artificial intelligence and machine learning. The set of categories was chosen to facilitate content-specific processing workflows, separating pages requiring different analysis techniques (e.g., OCR for text, image analysis for graphics)
Authors: Thomas A. Buckley, Riccardo Conci, Peter G. Brodeur, Jason Gusdorf, Sourik Beltr\'an, Bita Behrouzi, Byron Crowe, Jacob Dockterman, Muzzammil Muhammad, Sarah Ohnigian, Andrew Sanchez, James A. Diao, Aashna P. Shah, Daniel Restrepo, Eric S. Rosenberg, Andrew S. Lea, Emily Glanton, Kimberly LeBlanc, Undiagnosed Diseases Network, Marinka Zitnik, Scott H. Podolsky, Zahir Kanjee, Raja-Elie E. Abdulnour, Jacob M. Koshy, Adam Rodman, Arjun K. Manrai
Abstract: Differential diagnosis is an iterative process that integrates patient information with broader medical knowledge. Clinical case series such as the NEJM Clinicopathologic Conferences (CPCs), published continuously since 1923, feature expert physicians who demonstrate diagnostic reasoning to peers, and have been used for decades to evaluate AI. However, prior AI evaluations have largely focused on final diagnostic accuracy rather than nuanced clinical reasoning. Here, we introduce Dr. CaBot, an agentic AI system that emulates an expert diagnostician by generating written and narrated slide-based presentations from an initial case description alone. CaBot recently generated the first AI diagnosis published in the 100+ year history of the NEJM CPCs. In blinded evaluations, physicians misclassified the source of the differential (CaBot vs. physician-written) in 46/62 (74%) of trials and rated them favorably across quality dimensions. When tasked with solving cases for 72 patients with undiagnosed disease from the NIH Undiagnosed Diseases Network, CaBot identified the working diagnosis in 50/72 (69%) of cases from referral notes alone. To promote transparency and research, we also developed CPC-Bench, a physician-validated benchmark based on 7,102 CPCs and 47,648 questions across 10 tasks. We show that CaBot outperforms frontier models on CPC-Bench, and release both CaBot and CPC-Bench publicly to foster progress in clinical AI.
Authors: Nishanth Shetty, Madhava Prasath, Chandra Sekhar Seelamantula
Abstract: Exponentiated gradient descent (EGD), a biologically motivated optimisation algorithm that respects Dale's law, produces log-normally distributed synaptic weights at convergence, in alignment with experimental observations in neuroscience. Since the marginal distribution of geometric Brownian motion (GBM) at any fixed time is log-normal, this convergence property reveals a natural connection between EGD and GBM-based stochastic processes. We propose a multiplicative score-based generative model with GBM as a forward noising process and derive its corresponding reverse-time SDE in both the ambient space and in the $\log$-transformed space. We derive two multiplicative samplers by discretising the corresponding reverse-time SDEs: a sign-agnostic sampler obtained directly from the ambient-space reverse-time SDE, and a sign-preserving sampler, which we refer to as the Dale-Langevin sampler, obtained via the Lamperti transform. We connect the framework to Mirrored Langevin Dynamics, showing that the convex function driving EGD in optimisation precisely governs the Dale-Langevin sampler. While the standard Stein score, defined as $\nabla \log p_{\boldsymbol{X}}(\boldsymbol{x})$ for a random vector $\boldsymbol{X}$ evaluated at $\boldsymbol{x}$, comes up naturally in the additive noise based diffusion models, in the multiplicative setting, we encounter a modified version of the Stein score for sampling, which we refer to as the {\it Hyv\"arinen score}: $\boldsymbol{x} \circ \nabla \log p_{\boldsymbol{X}}(\boldsymbol{x})$. To estimate the score, we propose a new multiplicative denoising score-matching objective (M-DSM), prove its equivalence to the multiplicative explicit score-matching loss and show that it subsumes the non-negative score matching loss. Experimental results on MNIST, Fashion-MNIST, Kuzushiji-MNIST, and CIFAR-10 to validate the generative capability of the proposed framework.
Authors: Shanmin Wang, Dongdong Zhao
Abstract: Knowledge Distillation (KD) is essential for compressing large models, yet relying on pre-trained "teacher" models downloaded from third-party repositories introduces serious security risks--most notably backdoor attacks. Existing KD backdoor methods are typically complex and computationally intensive: they employ surrogate student models and simulated distillation to guarantee transferability, and construct triggers similar to universal adversarial perturbations (UAPs), which being not stealthy in magnitude, inherently exhibit strong adversarial behavior. This work questions whether such complexity is necessary and constructs stealthy "weak" triggers--imperceptible perturbations that have negligible adversarial effect. We propose BackWeak, a simple, surrogate-free attack paradigm. BackWeak shows that a powerful backdoor can be implanted by simply fine-tuning a benign teacher with a weak trigger using a very small learning rate. We demonstrate that this delicate fine-tuning is sufficient to embed a backdoor that reliably transfers to diverse student architectures during a victim's standard distillation process, yielding high attack success rates. Extensive empirical evaluations on multiple datasets, model architectures, and KD methods show that BackWeak is efficient, simpler, and often more stealthy than previous elaborate approaches. This work calls on researchers studying KD backdoor attacks to pay particular attention to the trigger's potential adversarial characteristics.
Authors: Mingyu Zhang, Lifeng Zhuo, Tianxi Tan, Guocan Xie, Xian Nie, Yan Li, Renjie Zhao, Zizhu He, Ziyu Wang, Jiting Cai, Yong-Lu Li
Abstract: Humans learn by observing, interacting with environments, and internalizing physics and causality. Here, we aim to ask whether an agent can similarly acquire human-like reasoning from interaction and keep improving with more experience. To study this, we introduce a Game-to-Unseen (G2U) benchmark of 1,000+ heterogeneous games that exhibit significant visual domain gaps. Existing approaches, including VLMs and world models, struggle to capture underlying physics and causality since they are not focused on core mechanisms and overfit to visual details. VLM/VLA agents reason but lack look-ahead in interactive settings, while world models imagine but imitate visual patterns rather than analyze physics and causality. We therefore propose IPR (Interactive Physical Reasoner), using world-model rollouts to score and reinforce a VLM's policy, and introduce PhysCode, a physics-centric action code aligning semantic intent with dynamics to provide a shared action space for prediction and reasoning. Pretrained on 1,000+ games, our IPR performs robustly on levels from primitive intuition to goal-driven reasoning, and even surpasses GPT-5 overall. We find that performance improves with more training games and interaction steps, and that the model also zero-shot transfers to unseen games. These results support physics-centric interaction as a path to steadily improving physical reasoning. Further demos and project details can be found at https://mybearyzhang.github.io/ipr-1.
Authors: Zhongtao Wang, Jiaqi Dai, Qingtian Zhu, Yilong Li, Mai Su, Fei Zhu, Meng Gai, Shaorong Wang, Chengwei Pan, Yisong Chen, Guoping Wang
Abstract: Multi-period image collections are common in real-world applications. Cities are re-scanned for mapping, construction sites are revisited for progress tracking, and natural regions are monitored for environmental change. Such data form multi-period scenes, where geometry and appearance evolve. Reconstructing such scenes is an important yet underexplored problem. Existing pipelines rely on incompatible assumptions: static and in-the-wild methods enforce a single geometry, while dynamic ones assume smooth motion, both failing under long-term, discontinuous changes. To solve this problem, we introduce ChronoGS, a temporally modulated Gaussian representation that reconstructs all periods within a unified anchor scaffold. It's also designed to disentangle stable and evolving components, achieving temporally consistent reconstruction of multi-period scenes. To catalyze relevant research, we release ChronoScene dataset, a benchmark of real and synthetic multi-period scenes, capturing geometric and appearance variation. Experiments demonstrate that ChronoGS consistently outperforms baselines in reconstruction quality and temporal consistency. Our code and the ChronoScene dataset are publicly available at https://github.com/ZhongtaoWang/ChronoGS.
Authors: Tharindu Wickremasinghe, Chenyang Qi, Harshana Weligampola, Zhengzhong Tu, Stanley H. Chan
Abstract: Flow-based text-to-image (T2I) models excel at prompt-driven image generation, but falter on Image Restoration (IR), often "drifting away" from being faithful to the measurement. Prior work mitigate this drift with data-specific flows or task-specific adapters that are computationally heavy and not scalable across tasks. This raises the question "Can't we efficiently manipulate the existing generative capabilities of a flow model?" To this end, we introduce FlowSteer (FS), an operator-aware conditioning scheme that injects measurement priors along the sampling path,coupling a frozed flow's implicit guidance with explicit measurement constraints. Across super-resolution, deblurring, denoising, and colorization, FS improves measurement consistency and identity preservation in a strictly zero-shot setting-no retrained models, no adapters. We show how the nature of flow models and their sensitivities to noise inform the design of such a scheduler. FlowSteer, although simple, achieves a higher fidelity of reconstructed images, while leveraging the rich generative priors of flow models. All data and code will be publicly available \href{https://tharindu-nirmal.github.io/FlowSteer/}{in this link}.
Authors: Jyun-Ping Kao, Jiaxin Yang, C. -C. Jay Kuo, Jonghye Woo
Abstract: Echocardiography is a cornerstone for managing heart failure (HF), with Left Ventricular Ejection Fraction (LVEF) being a critical metric for guiding therapy. However, manual LVEF assessment suffers from high inter-observer variability, while existing Deep Learning (DL) models are often computationally intensive and data-hungry "black boxes" that impede clinical trust and adoption. Here, we propose a backpropagation-free multi-task Green Learning (MTGL) framework that performs simultaneous Left Ventricle (LV) segmentation and LVEF classification. Our framework integrates an unsupervised VoxelHop encoder for hierarchical spatio-temporal feature extraction with a multi-level regression decoder and an XG-Boost classifier. On the EchoNet-Dynamic dataset, our MTGL model achieves state-of-the-art classification and segmentation performance, attaining a classification accuracy of 94.3% and a Dice Similarity Coefficient (DSC) of 0.912, significantly outperforming several advanced 3D DL models. Crucially, our model achieves this with over an order of magnitude fewer parameters, demonstrating exceptional computational efficiency. This work demonstrates that the GL paradigm can deliver highly accurate, efficient, and interpretable solutions for complex medical image analysis, paving the way for more sustainable and trustworthy artificial intelligence in clinical practice.
Authors: Jiacheng Yang, Jun Wu, Yaoyao Ding, Zhiying Xu, Yida Wang, Gennady Pekhimenko
Abstract: Diffusion Transformers (DiTs) have gained increasing adoption in high-quality image and video generation. As demand for higher-resolution images and longer videos increases, single-GPU inference becomes inefficient due to increased latency and large activation sizes. Current frameworks employ sequence parallelism (SP) techniques such as Ulysses Attention and Ring Attention to scale inference. However, these implementations have three primary limitations: (1) suboptimal communication patterns for network topologies on modern GPU machines, (2) latency bottlenecks from all-to-all operations in inter-machine communication, and (3) GPU sender-receiver synchronization and computation overheads from using two-sided communication libraries. To address these issues, we present StreamFusion, a topology-aware efficient DiT serving engine. StreamFusion incorporates three key innovations: (1) a topology-aware sequence parallelism technique that accounts for inter- and intra-machine bandwidth differences, (2) Torus Attention, a novel SP technique enabling overlapping of inter-machine all-to-all operations with computation, and (3) a one-sided communication implementation that minimizes GPU sender-receiver synchronization and computation overheads. Our experiments demonstrate that StreamFusion outperforms the state-of-the-art approach by an average of $1.35\times$ (up to $1.77\times$).
Authors: Woosung Koh, Sungjun Han, Segyu Lee, Se-Young Yun, Jamin Shin
Abstract: Mobile Graphical User Interface (GUI) World Models (WMs) offer a promising path for improving mobile GUI agent performance at train- and inference-time. However, current approaches face a critical trade-off: text-based WMs sacrifice visual fidelity, while the inability of visual WMs in precise text rendering led to their reliance on slow, complex pipelines dependent on numerous external models. We propose a novel paradigm: visual world modeling via renderable code generation, where a single Vision-Language Model (VLM) predicts the next GUI state as executable web code that renders to pixels, rather than generating pixels directly. This combines the strengths of both approaches: VLMs retain their linguistic priors for precise text rendering while their pre-training on structured web code enables high-fidelity visual generation. We introduce gWorld (8B, 32B), the first open-weight visual mobile GUI WMs built on this paradigm, along with a data generation framework (gWorld) that automatically synthesizes code-based training data. In extensive evaluation across 4 in- and 2 out-of-distribution benchmarks, gWorld sets a new pareto frontier in accuracy versus model size, outperforming 8 frontier open-weight models over 50.25x larger. Further analyses show that (1) scaling training data via gWorld yields meaningful gains, (2) each component of our pipeline improves data quality, and (3) stronger world modeling improves downstream mobile GUI policy performance.
Authors: Weikang Qiu, Huashuo Lei, Tinglin Huang, Rex Ying
Abstract: Vision-Language-Action (VLA) models have recently emerged as a promising paradigm for generalist robotic control. Built upon vision-language model (VLM) architectures, VLAs predict actions conditioned on visual observations and language instructions, achieving strong performance and generalization across tasks. However, VLAs face two major challenges: a limited context window for input frames and inefficient inference due to the quadratic attention complexity and large parameter counts. To this end, we propose DySta, a framework that disentangles visual inputs into multi-level static and dynamic tokens, which enables (1) retaining a single copy of static tokens across frames to significantly reduce context length, and (2) reusing the key-value (KV) cache of static tokens through a lightweight recache gate that updates only when necessary. This design enables efficient multi-frame integration and efficient inference. In addition, we introduce a new benchmark that more effectively evaluates the multi-frame integration ability of VLAs. Experiments show that Dysta improves multi-frame integration by 24.5% across metrics on our benchmark and 23.3% in absolute success rate on real-world memory-dependent tasks, while accelerating inference by 2.0x (with +2.3% success rate) on simulation benchmarks and 2.2x (with +10.6% success rate) on real-world general tasks.
Authors: Xinghao Wang, Pengyu Wang, Xiaoran Liu, Fangxu Liu, Jason Chu, Kai Song, Xipeng Qiu
Abstract: Block-sparse attention is promising for accelerating long-context LLM pre-filling, yet identifying relevant blocks efficiently remains a bottleneck. Existing methods typically employ coarse-grained attention as a proxy for block importance estimation, but often resort to expensive token-level searching or scoring, resulting in significant selection overhead. In this work, we trace the inaccuracy of standard coarse-grained attention via mean pooling to a theoretical root cause: the interaction between mean pooling and Rotary Positional Embeddings (RoPE). We prove that mean pooling acts as a low-pass filter that induces destructive interference in high-frequency dimensions, effectively creating a "blind spot" for local positional information (e.g., slash patterns). To address this, we introduce Prism, a training-free spectral-aware approach that decomposes block selection into high-frequency and low-frequency branches. By applying energy-based temperature calibration, Prism restores the attenuated positional signals directly from pooled representations, enabling block importance estimation using purely block-level operations, thereby improving efficiency. Extensive evaluations confirm that Prism maintains accuracy parity with full attention while delivering up to $\mathbf{5.1\times}$ speedup.
Authors: Xinwei Zhang, Li Bai, Tianwei Zhang, Youqian Zhang, Qingqing Ye, Yingnan Zhao, Ruochen Du, Haibo Hu
Abstract: Large vision-language models (LVLMs) have achieved impressive performance across multimodal tasks, but their reliance on visual inputs exposes them to adversarial threats. Encoder-based attacks provide an efficient alternative to end-to-end optimization by crafting perturbations through the vision encoder alone. However, existing encoder-based attacks often assume that the surrogate encoder is identical or similar to the victim LVLM's vision encoder. In this work, we present a systematic study of their transferability in more realistic black-box deployments with heterogeneous LVLM architectures. We find that model-specific visual evidence is inconsistent across models, whereas text-conditioned grounding regions are more closely tied to caption-relevant evidence and provide a more stable transfer target. However, existing attacks remain weakly aligned with and insufficiently disrupt these regions. Motivated by these findings, we propose Grounding-Driven Attack (GDA), which aligns perturbation optimization with text-grounded evidence. GDA combines Grounding-Aware Perturbation Allocation to concentrate perturbation budget on grounded evidence regions with Grounding-Centric Evidence Disruption to intensify their global and local disruption. Experiments across diverse victim models and tasks show that GDA consistently outperforms existing encoder-based attacks in black-box transfer. These results highlight the central role of text-grounded evidence in adversarial transferability and motivate grounding-aware robustness evaluation and defense design.
Authors: Yining Hong, Huang Huang, Manling Li, Li Fei-Fei, Leonidas Guibas, Jiajun Wu, Yejin Choi
Abstract: Embodied LLMs endow robots with high-level task reasoning, but they cannot reflect on what went wrong or why, turning deployment into a sequence of independent trials where mistakes repeat rather than accumulate into experience. Drawing upon human reflective practitioners, we introduce Reflective Test-Time Planning, which integrates two modes of reflection: \textit{reflection-in-action}, where the agent uses test-time scaling to generate and score multiple candidate actions using internal reflections before execution; and \textit{reflection-on-action}, which uses test-time training to update both its internal reflection model and its action policy based on external reflections after execution. We also include retrospective reflection, allowing the agent to re-evaluate earlier decisions and perform model updates with hindsight for proper long-horizon credit assignment. Experiments on our newly-designed Long-Horizon Household benchmark and MuJoCo Cupboard Fitting benchmark show significant gains over baseline models, with zero-shot generalization to photorealistic HM3D environments and real-robot experiments on a Franka Panda arm. Ablations confirm that reflection-in-action and reflection-on-action are mutually dependent, and that retrospective reflection achieves better credit assignment than step-wise external feedback at lower computational overhead. Qualitative analyses further highlight behavioral correction through reflection.
Authors: Lingfeng He, De Cheng, Huaijie Wang, Xi Yang, Nannan Wang, Xinbo Gao
Abstract: Continual Learning (CL) requires models to sequentially adapt to new tasks without forgetting old knowledge. Recently, Low-Rank Adaptation (LoRA), a representative Parameter-Efficient Fine-Tuning (PEFT) method, has gained increasing attention in CL. Several LoRA-based CL methods reduce interference across tasks by separating their update spaces, typically building the new space from the estimated null space of past tasks. However, they (i) overlook task-shared directions, which suppresses knowledge transfer, and (ii) fail to capture truly effective task-specific directions since these ``null bases" of old tasks can remain nearly inactive for new task under correlated tasks. To address this, we study LoRA learning capability from a projection energy perspective, and propose Low-rank Decomposition and Adaptation (LoDA). It performs a task-driven decomposition to build general and truly task-specific LoRA subspaces by solving two energy-based objectives, decoupling directions for knowledge sharing and isolation. LoDA fixes LoRA down-projections on two subspaces and learns robust up-projections via a Gradient-Aligned Optimization (GAO) approach. After each task, before integrating the LoRA updates into the backbone, LoDA derives a closed-form recalibration for the general update, approximating a feature-level joint optimum along this task-shared direction. Experiments indicate that LoDA outperforms existing CL methods. Our code is available at https://github.com/HHHLF/LoDA_ICML2026.
Authors: Kaiser Sun, Xiaochuang Yuan, Hongjun Liu, Chen Zhao, Cheng Zhang, Mark Dredze, Fan Bai
Abstract: Multimodal large language models (MLLMs) can process text presented as images, yet they often perform worse than when the same content is provided as textual tokens. We systematically diagnose this "modality gap" by evaluating seven MLLMs across seven benchmarks in five input modes, spanning both synthetically rendered text and realistic document images from arXiv PDFs to Wikipedia pages. We find that the gap is highly sensitive to rendering choices such as font and resolution, and that natural document images often exhibit much smaller gaps, suggesting the performance difference partly reflects evaluation artifacts rather than fundamental limitations. Through a grounded-theory error analysis of over 4,000 examples, we identify the primary cause: image input alone suppresses reasoning effort, with models producing 5--19x shorter outputs that skip step-by-step computation or reasoning. The reluctance to reason, not a failure of perception or knowledge retrieval, drives the performance gap, particularly on tasks requiring multi-step reasoning. We show that a simple, lightweight on-policy self-distillation method by fine-tuning models on their own text-mode reasoning traces paired with image inputs closes this gap, raising image-mode accuracy to match or exceed text-mode performance with over 50\% improvement, and the gains transfer to unseen benchmarks without catastrophic forgetting. Overall, our results and analyses provide a systematic understanding of the modality gap and suggest a practical path toward improving visual text understanding in multimodal language models.
Authors: Abinav Rao, Sujan Rachuri
Abstract: Unified multimodal models share a language model backbone for both understanding and generating images. Can DPO align both capabilities simultaneously? We present the first systematic study of this question, applying DPO to Janus-Pro at 1B and 7B parameters under seven training strategies and two post-hoc methods. The central finding is negative: generation quality resists DPO alignment across all tested conditions on this architecture. No method improves generation CLIPScore at 7B (|Delta| < 0.2, p > 0.5 at n=200 per seed, 3 seeds); at 1B, all methods degrade generation, and the result holds across preference data types (real-vs-generated and model-vs-model) and the data volumes tested (150-288 pairs). Gradient analysis reveals why: understanding and generation gradients are near-orthogonal (cos ~ 0) with ~11-14x magnitude imbalance driven by VQ token count asymmetry (576 generation tokens vs. ~30-100 text tokens). This imbalance is the dominant interference mechanism in multi-task DPO; magnitude-balancing yields directionally positive understanding deltas (+0.01-0.04 VQA, though individually not significant), but the generation gap persists regardless. We identify discrete VQ tokenization as a likely structural bottleneck -- supported by the generation DPO loss converging to ln(2) -- and provide practical guidance for practitioners working with VQ-based unified models.
Authors: Xiao Li, Xiang Zheng, Yifeng Gao, Xinyu Xia, Yixu Wang, Xin Wang, Ye Sun, Yunhan Zhao, Ming Wen, Jiayu Li, Zixing Chen, Xun Gong, Yi Liu, Yige Li, Yutao Wu, Cong Wang, Jun Sun, Yixin Cao, Zhineng Chen, Jingjing Chen, Tao Gui, Qi Zhang, Zuxuan Wu, Xipeng Qiu, Xuanjing Huang, Tiehua Zhang, Zhipeng Wei, Kun Wang, Xinfeng Li, Hanxun Huang, Sarah Erfani, James Bailey, Jianping Wang, Chaowei Xiao, Ran He, Bo Li, Xingjun Ma, Yu-Gang Jiang
Abstract: Embodied Artificial Intelligence (Embodied AI) integrates perception, cognition, planning, and interaction into agents that operate in open-world, safety-critical environments. As these systems gain autonomy and enter domains such as transportation, healthcare, and industrial or assistive robotics, ensuring their safety becomes both technically challenging and socially indispensable. Unlike digital AI systems, embodied agents must act under uncertain sensing, incomplete knowledge, and dynamic human-robot interactions, where failures can directly lead to physical harm. This survey provides a comprehensive and structured review of safety research in embodied AI, examining attacks and defenses across the full embodied pipeline, from perception and cognition to planning, action and interaction, and agentic system. We introduce a multi-level taxonomy that unifies fragmented lines of work and connects embodied-specific safety findings with broader advances in vision, language, and multimodal foundation models. Our review synthesizes insights from over 500 papers spanning adversarial, backdoor, jailbreak, and hardware-level attacks; attack detection, safe training and robust inference; and risk-aware human-agent interaction. This analysis reveals several overlooked challenges, including the fragility of multimodal perception fusion, the instability of planning under jailbreak attacks, and the trustworthiness of human-agent interaction in open-ended scenarios. By organizing the field into a coherent framework and identifying critical research gaps, this survey provides a roadmap for building embodied agents that are not only capable and autonomous but also safe, robust, and reliable in real-world deployment.
Authors: Qingjun Zhang
Abstract: We introduce E = T*H/(O+B), a dimensionless control parameter that predicts whether Mixture-of-Experts (MoE) models will develop a healthy expert ecology or collapse into dead experts. E combines four hyperparameters -- routing temperature T, routing entropy weight H, oracle weight O, and balance weight B -- into a single quantity. Through 12 controlled experiments (8 vision, 4 language) totaling over 11,000 training epochs, we establish that E >= 0.5 alone is sufficient to guarantee zero dead experts, removing the necessity for handcrafted load-balancing auxiliary losses. We validate this cross-modally on CIFAR-10, CIFAR-100, TinyImageNet-200, WikiText-2, and WikiText-103. Six additional findings emerge: (1) dead experts can resuscitate -- triggered by balance loss driving router re-exploration; (2) ortho toxicity is dataset-dependent, not universal; (3) task complexity shifts the critical E threshold; (4) model overfitting is decoupled from expert ecological health; (5) three-tier MoE spontaneously collapses into a two-tier functional structure; (6) ecological structure is temperature-invariant across a 50x range. We propose that E serves as a unified diagnostic for MoE training, analogous to the Reynolds number in fluid dynamics.
Authors: Sibo Jia, Zihang Zhao, Kunrong Li
Abstract: Industrial visual inspection systems increasingly rely on deep classifiers whose heatmap explanations may appear visually plausible while failing to identify the image regions that actually drive model decisions. This paper operationalizes an architecture-aware explanation audit protocol grounded in the native-readout hypothesis: the perturbation-based faithfulness of an explanation method is bounded by its structural distance from the model's native decision mechanism. On WM-811K wafer maps (9 classes, 172k images) under a three-seed zero-fill perturbation protocol, ViT-Tiny + Attention Rollout attains Deletion AUC 0.211 against 0.432-0.525 for Swin-Tiny / ResNet18+CBAM / DenseNet121 + Grad-CAM (abs(Cohen's d) > 1.1), despite lower classification accuracy. Swin-Tiny disentangles architecture family from readout structure: despite being a Transformer, its spatial feature-map hierarchy makes it Grad-CAM compatible, showing that the operative factor is readout structure rather than architecture family. A model-agnostic control (RISE) compresses all families to Deletion AUC about 0.1, indicating the gap arises from the explainer pathway; notably, RISE outperforms all native methods, so native readout is a compatibility principle rather than an optimality guarantee. A blur-fill sensitivity analysis shows that the family ordering reverses under a different perturbation baseline, reinforcing that faithfulness rankings are joint properties of (model, explainer, perturbation operator) triples. An exploratory boundary-condition study on MVTec AD (pretrained models) indicates that audit results are dataset/task dependent and identifies conditions requiring qualification. The protocol yields actionable guidance: explanation pathways should be co-designed with model architectures based on readout structure, and deployed heatmaps should be accompanied by quantitative faithfulness metrics.
Authors: Nicanor Mayumu, Xiaoheng Deng, Patrick Mukala
Abstract: We present the first systematic study of faithfulness in Vision-Language-Action (VLA) driving models, analyzing 300 Alpamayo-R1-10B inferences across 100 diverse PhysicalAI-AV scenarios. Our main finding is that output natural-language rationales with trajectories may be significantly unfaithful: (i) overall reasoning fidelity is only 42.5%, with Chain-of-Causation matching scene reality less than half the time; (ii) 94 missed pedestrians in one-third of pedestrian-relevant scenes; (iii) 97.7% trajectory fragility under mild visual perturbations; and (iv) only 48.3% mean reasoning-action consistency, with 53.3% of inferences exhibiting low consistency, including 37.9% of stop-claimed cases where the model continues instead. We formalize faithfulness information-theoretically, define entity and action fidelity with verification criteria, and outline a four-component safety architecture aligned with these results.
Authors: Gyubin Lee, Junwon Lee, Juhan Nam
Abstract: We investigate Counterfactual Video Foley Generation, which aims to adopt a sound-source identity that contradicts the visual evidence while remaining temporally synchronized to a silent video. Existing Video&Text-to-Audio (VT2A) models struggle with this, often remaining anchored to the visually implied sound source when video and text contents disagree. We present ConterFlow, an inference-time dual-phase sampling scheme for pretrained flow-matching VT2A models. Phase 1 builds a video-derived temporal structure while suppressing the visually implied source; Phase 2 drops video conditioning to focus entirely on shaping audio timbre toward the target prompt. ConterFlow substantially improves counterfactual Video Foley generation compared to naive negative prompting and state-of-the-art baselines. To evaluate replacement quality, we propose a metric leveraging a text-audio co-embedding space to measure both target-prompt evidence and residual visually implied source leakage. Video demonstrations and code are available at https://gyubin-lee.github.io/counterflow-demo/
Authors: Tianle Li, Xuyang Shen, Yan Ma, Rongxin Guo, Shaoxiang Chen, Jiacheng Chen, Haochen Wang, Hongyang Tang, Yucong Zhou, Yu Cheng
Abstract: Long-form image captioning exposes a reward granularity problem in RL: captions are judged as whole sequences, while the important errors occur at the level of individual visual claims. A good dense caption should be both faithful and informative, avoiding hallucination without omitting salient details. Yet pairwise preferences, reference-based metrics, and holistic scalar rewards compress these local errors into a single sequence-level signal, obscuring the tradeoff between factuality and coverage. We introduce ClaimDiff-RL, a framework that uses reference-conditioned atomic claim differences as the reward unit for caption RL. Given an image, an actor caption, and a reference caption, a multimodal judge enumerates visually grounded differences, verifies each difference against the image, assigns open-vocabulary error types and severity levels, and produces per-difference statistics for reward composition. This makes hallucinated claims and omitted salient facts separately measurable and tunable. Experiments show that holistic scalar rewards can reduce hallucination by increasing missing facts, while ClaimDiff-RL exposes this faithfulness and coverage tradeoff and enables more balanced operating points. On a 160-image human-labeled diagnostic benchmark, public captioning benchmarks, and VQA benchmarks, ClaimDiff-RL improves the hallucination--missing-fact balance, preserves general capability, and even surpasses Gemini-3-Pro-Preview on several fine-grained Capability dimensions such as object counting, spatial relations, and scene recognition. These results suggest that typed, verifiable claim differences are an effective reward unit for fine-grained and diagnosable caption RL.