Peer Revenue Fully funded

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science Computer Vision

cs.CV Watch Computer Vision

Thursday 26 March

Computer Vision

Pixelis: Reasoning in Pixels, from Seeing to Acting

Yunpeng Zhou

Most vision-language systems are static observers: they describe pixels, do not act, and cannot safely improve under shift. This passivity limits generalizable, physically grounded visual intelligence. Learning through action, not static description, is essential beyond curated data. We present Pixelis, a pixel-space agent that operates directly on images and videos via a compact set of executable operations (zoom/crop, segment, track, OCR, temporal localization) and learns from its consequences. Pixelis trains in three phases: (1) Supervised Fine-Tuning learns a pixel-tool grammar from Chain-of-Thought-Action traces with a masked imitation loss that upweights operation/argument tokens and auxiliary heads to stabilize pixel-grounded arguments; (2) Curiosity-Coherence Reward Fine-Tuning optimizes a dual-drive objective marrying prediction-error curiosity with adjacent-step coherence and a mild efficiency prior under a KL anchor, yielding short, valid, structured toolchains; (3) Pixel Test-Time RL performs label-free adaptation by retrieving neighbors, voting over complete trajectories rather than answers, and updating toward short, high-fidelity exemplars while constraining drift with a KL-to-EMA safety control. Across six public image and video benchmarks, Pixelis yields consistent improvements: the average relative gain is +4.08% over the same 8B baseline (peaking at +6.03% on VSI-Bench), computed as (ours-baseline)/baseline, while producing shorter, auditable toolchains and maintaining in-corridor KL during test-time learning. Acting within pixels, rather than abstract tokens, grounds multimodal perception in the physical world, linking visual reasoning with actionable outcomes, and enables embodied adaptation without external feedback.
Read the full abstract

Computer Vision

THEMIS: Towards Holistic Evaluation of MLLMs for Scientific Paper Fraud Forensics

Tzu-Yen Ma, Bo Zhang, Zichen Tang et al. (+20 more)

We present THEMIS, a novel multi-task benchmark designed to comprehensively evaluate multimodal large language models (MLLMs) on visual fraud reasoning within real-world academic scenarios. Compared to existing benchmarks, THEMIS introduces three major advances. (1) Real-World Scenarios and Complexity: Our benchmark comprises over 4,000 questions spanning seven scenarios, derived from authentic retracted-paper cases and carefully curated multimodal synthetic data. With 60.47% complex-texture images, THEMIS bridges the critical gap between existing benchmarks and the complexity of real-world academic fraud. (2) Fraud-Type Diversity and Granularity: THEMIS systematically covers five challenging fraud types and introduces 16 fine-grained manipulation operations. On average, each sample undergoes multiple stacked manipulation operations, with the diversity and difficulty of these manipulations demanding a high level of visual fraud reasoning from the models. (3) Multi-Dimensional Capability Evaluation: We establish a mapping from fraud types to five core visual fraud reasoning capabilities, thereby enabling an evaluation that reveals the distinct strengths and specific weaknesses of different models across these core capabilities. Experiments on 16 leading MLLMs show that even the best-performing model, GPT-5, achieves an overall performance of only 56.15%, demonstrating that our benchmark presents a stringent test. We expect THEMIS to advance the development of MLLMs for complex, real-world fraud reasoning tasks.
Read the full abstract

All authors Tzu-Yen Ma, Bo Zhang, Zichen Tang, Junpeng Ding, Haolin Tian, Yuanze Li, Zhuodi Hao, Zixin Ding, Zirui Wang, Xinyu Yu, Shiyao Peng, Yizhuo Zhao, Ruomeng Jiang, Yiling Huang, Peizhi Zhao, Jiayuan Chen, Weisheng Tan, Haocheng Gao, Yang Liu, Jiacheng Liu, Zhongjun Yang, Jiayu Huang, Haihong E

Computer Vision

Visual Attention Drifts,but Anchors Hold:Mitigating Hallucination in Multimodal Large Language Models via Cross-Layer Visual Anchors

Chengxu Yang, Jingling Yuan, Chuang Hu et al. (+1 more)

Multimodal Large Language Models often suffer from object hallucination. While existing research utilizes attention enhancement and visual retracing, we find these works lack sufficient interpretability regarding attention drift in final model stages. In this paper, we investigate the layer wise evolution of visual features and discover that hallucination stems from deep layer attention regressing toward initial visual noise from early layers. We observe that output reliability depends on acquiring visual anchors at intermediate layers rather than final layers. Based on these insights, we propose CLVA, which stands for Cross-Layer Visual Anchors, a training free method that reinforces critical mid layer features while suppressing regressive noise. This approach effectively pulls deep layer attention back to correct visual regions by utilizing essential anchors captured from attention dynamics. We evaluate our method across diverse architectures and benchmarks, demonstrating outstanding performance without significant increase in computational time and GPU memory.
Read the full abstract

All authors Chengxu Yang, Jingling Yuan, Chuang Hu, Jiawei Jiang

Computer Vision

Learning domain-invariant features through channel-level sparsification for Out-Of Distribution Generalization

Haoran Pei, Yuguang Yang, Kexin Liu et al. (+2 more)

Out-of-Distribution (OOD) generalization has become a primary metric for evaluating image analysis systems. Since deep learning models tend to capture domain-specific context, they often develop shortcut dependencies on these non-causal features, leading to inconsistent performance across different data sources. Current techniques, such as invariance learning, attempt to mitigate this. However, they struggle to isolate highly mixed features within deep latent spaces. This limitation prevents them from fully resolving the shortcut learning problem.In this paper, we propose Hierarchical Causal Dropout (HCD), a method that uses channel-level causal masks to enforce feature sparsity. This approach allows the model to separate causal features from spurious ones, effectively performing a causal intervention at the representation level. The training is guided by a Matrix-based Mutual Information (MMI) objective to minimize the mutual information between latent features and domain labels, while simultaneously maximizing the information shared with class labels.To ensure stability, we incorporate a StyleMix-driven VICReg module, which prevents the masks from accidentally filtering out essential causal data. Experimental results on OOD benchmarks show that HCD performs better than existing top-tier methods.
Read the full abstract

All authors Haoran Pei, Yuguang Yang, Kexin Liu, Juan Zhang, Baochang Zhang

Computer Vision

Bridging Perception and Reasoning: Token Reweighting for RLVR in Multimodal LLMs

Jinda Lu, Junkang Wu, Jinghan Li et al. (+6 more)

Extending Reinforcement Learning with Verifiable Rewards (RLVR) to multimodal large language models (MLLMs) faces a fundamental challenge: their responses inherently interleave perception-related tokens, which ground visual content, with reasoning-related tokens, which construct reasoning chains. These token types instantiate distinct yet interdependent capacities – visual grounding and symbolic reasoning – making isolated optimization insufficient. Through token-level empirical analysis, we demonstrate that optimizing either perception- or reasoning-only tokens consistently underperforms full optimization, underscoring their inherent coupling. To address this, we propose a plug-and-play Token-Reweighting (ToR) strategy that explicitly models this interdependence by identifying critical tokens of both types and dynamically reweighting them during RLVR training. Applied on top of existing methods (e.g., GRPO and DAPO), ToR delivers consistent performance gains across multiple multi-modal reasoning benchmarks, achieving state-of-the-art performance with both accurate visual grounding and coherent reasoning.
Read the full abstract

All authors Jinda Lu, Junkang Wu, Jinghan Li, Kexin Huang, Shuo Yang, Guoyin Wang, Jiancan Wu, Xiang Wang, Xiangnan He

Computer Vision

Z-Erase: Enabling Concept Erasure in Single-Stream Diffusion Transformers

Nanxiang Jiang, Zhaoxin Fan, Baisen Wang et al. (+8 more)

Concept erasure serves as a vital safety mechanism for removing unwanted concepts from text-to-image (T2I) models. While extensively studied in U-Net and dual-stream architectures (e.g., Flux), this task remains under-explored in the recent emerging paradigm of single-stream diffusion transformers (e.g., Z-Image). In this new paradigm, text and image tokens are processed as a single unified sequence via shared parameters. Consequently, directly applying prior erasure methods typically leads to generation collapse. To bridge this gap, we introduce Z-Erase, the first concept erasure method tailored for single-stream T2I models. To guarantee stable image generation, Z-Erase first proposes a Stream Disentangled Concept Erasure Framework that decouples updates and enables existing methods on single-stream models. Subsequently, within this framework, we introduce Lagrangian-Guided Adaptive Erasure Modulation, a constrained algorithm that further balances the sensitive erasure-preservation trade-off. Moreover, we provide a rigorous convergence analysis proving that Z-Erase can converge to a Pareto stationary point. Experiments demonstrate that Z-Erase successfully overcomes the generation collapse issue, achieving state-of-the-art performance across a wide range of tasks.
Read the full abstract

All authors Nanxiang Jiang, Zhaoxin Fan, Baisen Wang, Daiheng Gao, Junhang Cheng, Jifeng Guo, Yalan Qin, Yeying Jin, Hongwei Zheng, Faguo Wu, Wenjun Wu

Computer Vision

GIFT: Global Irreplaceability Frame Targeting for Efficient Video Understanding

Junpeng Ma, Sashuai Zhou, Guanghao Li et al. (+9 more)

Video Large Language Models (VLMs) have achieved remarkable success in video understanding, but the significant computational cost from processing dense frames severely limits their practical application. Existing methods alleviate this by selecting keyframes, but their greedy decision-making, combined with a decoupled evaluation of relevance and diversity, often falls into local optima and results in erroneously selecting irrelevant noise frames. To address these challenges, we propose GIFT: Global Irreplaceability Frame Targeting, a novel training-free framework that selects frames by assessing their intrinsic irreplaceability. Specifically, we first introduce Directed Diversity to quantify a frame's uniqueness conditioned on relevance, which allows us to formulate a unified irreplaceability score. Subsequently, our Budget-Aware Refinement strategy employs a adaptive iterative process that first secures a core set of frames with the highest irreplaceability, and then shifts its priority to building crucial temporal context around these selections as the budget expands. Extensive experiments demonstrate that GIFT achieves a maximum average improvement of 12.5% across long-form video benchmarks on LLaVA-Video-7B compared to uniform sampling. Code is available at https://github.com/ylnxxts/GIFT.
Read the full abstract

All authors Junpeng Ma, Sashuai Zhou, Guanghao Li, Xin Gao, Yue Cao, Hengyu Zeng, Yuxiang Yan, Zhibin Wang, Jun Song, Bo Zheng, Shanghang Zhang, Jian Pu

Computer Vision

Learning Explicit Continuous Motion Representation for Dynamic Gaussian Splatting from Monocular Videos

Xuankai Zhang, Junjin Xiao, Shangwei Huang et al. (+2 more)

We present an approach for high-quality dynamic Gaussian Splatting from monocular videos. To this end, we in this work go one step further beyond previous methods to explicitly model continuous position and orientation deformation of dynamic Gaussians, using an SE(3) B-spline motion bases with a compact set of control points. To improve computational efficiency while enhancing the ability to model complex motions, an adaptive control mechanism is devised to dynamically adjust the number of motion bases and control points. Besides, we develop a soft segment reconstruction strategy to mitigate long-interval motion interference, and employ a multi-view diffusion model to provide multi-view cues for avoiding overfitting to training views. Extensive experiments demonstrate that our method outperforms state-of-the-art methods in novel view synthesis. Our code is available at https://github.com/hhhddddddd/se3bsplinegs.
Read the full abstract

All authors Xuankai Zhang, Junjin Xiao, Shangwei Huang, Wei-shi Zheng, Qing Zhang

Computer Vision

Synergistic Event-SVE Imaging for Quantitative Propellant Combustion Diagnostics

Jing Tao, Taihang Lei, Banglei Guan et al. (+5 more)

Real-time monitoring of high-energy propellant combustion is difficult. Extreme high dynamic range (HDR), microsecond-scale particle motion, and heavy smoke often occur together. These conditions drive saturation, motion blur, and unstable particle extraction in conventional imaging. We present a closed-loop Event–SVE measurement system that couples a spatially variant exposure (SVE) camera with a stereo pair of neuromorphic event cameras. The SVE branch produces HDR maps with an explicit smoke-aware fusion strategy. A multi-cue smoke-likelihood map is used to separate particle emission from smoke scattering, yielding calibrated intensity maps for downstream analysis. The resulting HDR maps also provide the absolute-intensity reference missing in event cameras. This reference is used to suppress smoke-driven event artifacts and to improve particle-state discrimination. Based on the cleaned event observations, a stereo event-based 3D pipeline estimates separation height and equivalent particle size through feature extraction and triangulation (maximum calibration error 0.56%). Experiments on boron-based propellants show multimodal equivalent-radius statistics. The system also captures fast separation transients that are difficult to observe with conventional sensors. Overall, the proposed framework provides a practical, calibration-consistent route to microsecond-resolved 3D combustion measurement under smoke-obscured HDR conditions.
Read the full abstract

All authors Jing Tao, Taihang Lei, Banglei Guan, Ying Qu, Xudong Na, Likun Ma, Yang Shang, Qifeng Yu

Computer Vision

GaussFusion: Improving 3D Reconstruction in the Wild with A Geometry-Informed Video Generator

Liyuan Zhu, Manjunath Narayana, Michal Stary et al. (+3 more)

We present GaussFusion, a novel approach for improving 3D Gaussian splatting (3DGS) reconstructions in the wild through geometry-informed video generation. GaussFusion mitigates common 3DGS artifacts, including floaters, flickering, and blur caused by camera pose errors, incomplete coverage, and noisy geometry initialization. Unlike prior RGB-based approaches limited to a single reconstruction pipeline, our method introduces a geometry-informed video-to-video generator that refines 3DGS renderings across both optimization-based and feed-forward methods. Given an existing reconstruction, we render a Gaussian primitive video buffer encoding depth, normals, opacity, and covariance, which the generator refines to produce temporally coherent, artifact-free frames. We further introduce an artifact synthesis pipeline that simulates diverse degradation patterns, ensuring robustness and generalization. GaussFusion achieves state-of-the-art performance on novel-view synthesis benchmarks, and an efficient variant runs in real time at 15 FPS while maintaining similar performance, enabling interactive 3D applications.
Read the full abstract

All authors Liyuan Zhu, Manjunath Narayana, Michal Stary, Will Hutchcroft, Gordon Wetzstein, Iro Armeni

Computer Vision

MoRGS: Efficient Per-Gaussian Motion Reasoning for Streamable Dynamic 3D Scenes

Wonjoon Lee, Sungmin Woo, Donghyeong Kim et al. (+3 more)

Online reconstruction of dynamic scenes aims to learn from streaming multi-view inputs under low-latency constraints. The fast training and real-time rendering capabilities of 3D Gaussian Splatting have made on-the-fly reconstruction practically feasible, enabling online 4D reconstruction. However, existing online approaches, despite their efficiency and visual quality, fail to learn per-Gaussian motion that reflects true scene dynamics. Without explicit motion cues, appearance and motion are optimized solely under photometric loss, causing per-Gaussian motion to chase pixel residuals rather than true 3D motion. To address this, we propose MoRGS, an efficient online per-Gaussian motion reasoning framework that explicitly models per-Gaussian motion to improve 4D reconstruction quality. Specifically, we leverage optical flow on a sparse set of key views as lightweight motion cues that regularize per-Gaussian motion beyond photometric supervision. To compensate for the sparsity of flow supervision, we learn a per-Gaussian motion offset field that reconciles discrepancies between projected 3D motion and observed flow across views and time. In addition, we introduce a per-Gaussian motion confidence that separates dynamic from static Gaussians and weights Gaussian attribute residual updates, thereby suppressing redundant motion in static regions for better temporal consistency and accelerating the modeling of large motions. Extensive experiments demonstrate that MoRGS achieves state-of-the-art reconstruction quality and motion fidelity among online methods, while maintaining streamable performance.
Read the full abstract

All authors Wonjoon Lee, Sungmin Woo, Donghyeong Kim, Jungho Lee, Sangheon Park, Sangyoun Lee

Computer Vision · Cross-listed from cs.LG

Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale

Yicheng Zou, Dongsheng Zhu, Lin Zhu et al. (+174 more)

We introduce Intern-S1-Pro, the first one-trillion-parameter scientific multimodal foundation model. Scaling to this unprecedented size, the model delivers a comprehensive enhancement across both general and scientific domains. Beyond stronger reasoning and image-text understanding capabilities, its intelligence is augmented with advanced agent capabilities. Simultaneously, its scientific expertise has been vastly expanded to master over 100 specialized tasks across critical science fields, including chemistry, materials, life sciences, and earth sciences. Achieving this massive scale is made possible by the robust infrastructure support of XTuner and LMDeploy, which facilitates highly efficient Reinforcement Learning (RL) training at the 1-trillion parameter level while ensuring strict precision consistency between training and inference. By seamlessly integrating these advancements, Intern-S1-Pro further fortifies the fusion of general and specialized intelligence, working as a Specializable Generalist, demonstrating its position in the top tier of open-source models for general capabilities, while outperforming proprietary models in the depth of specialized scientific tasks.
Read the full abstract

All authors Yicheng Zou, Dongsheng Zhu, Lin Zhu, Tong Zhu, Yunhua Zhou, Peiheng Zhou, Xinyu Zhou, Dongzhan Zhou, Zhiwang Zhou, Yuhao Zhou, Bowen Zhou, Zhanping Zhong, Zhijie Zhong, Haiteng Zhao, Penghao Zhao, Xiaomeng Zhao, Zhiyuan Zhao, Yechen Zhang, Jin Zhang, Wenwei Zhang, Hongjie Zhang, Zhuo Zhang, Wenlong Zhang, Bo Zhang, Chao Zhang, Chen Zhang, Yuhang Zang, Fei Yuan, Jiakang Yuan, Jiashuo Yu, Jinhui Yin, Haochen Ye, Qian Yao, Bowen Yang, Danni Yang, Kaichen Yang, Ziang Yan, Jun Xu, Yicheng Xu, Wanghan Xu, Xuenan Xu, Chao Xu, Ruiliang Xu, Shuhao Xing, Long Xing, Xinchen Xie, Ling-I Wu, Zijian Wu, Zhenyu Wu, Lijun Wu, Yue Wu, Jianyu Wu, Wen Wu, Fan Wu, Xilin Wei, Qi Wei, Bingli Wang, Rui Wang, Ziyi Wang, Zun Wang, Yi Wang, Haomin Wang, Yizhou Wang, Lintao Wang, Yiheng Wang, Longjiang Wang, Bin Wang, Jian Tong, Zhongbo Tian, Huanze Tang, Chen Tang, Shixiang Tang, Yu Sun, Qiushi Sun, Xuerui Su, Qisheng Su, Chenlin Su, Demin Song, Jin Shi, Fukai Shang, Yuchen Ren, Pengli Ren, Xiaoye Qu, Yuan Qu, Jiantao Qiu, Yu Qiao, Biqing Qi, Runyu Peng, Tianshuo Peng, Jiahui Peng, Qizhi Pei, Zhuoshi Pan, Linke Ouyang, Wenchang Ning, Yichuan Ma, Zerun Ma, Ningsheng Ma, Runyuan Ma, Chengqi Lyu, Haijun Lv, Han Lv, Lindong Lu, Kuikun Liu, Jiangning Liu, Yuhong Liu, Kai Liu, Hongwei Liu, Zhoumianze Liu, Mengjie Liu, Ziyu Liu, Wenran Liu, Yang Liu, Liwei Liu, Kaiwen Liu, Junyao Lin, Junming Lin, Tianyang Lin, Dahua Lin, Jianze Liang, Linyang Li, Peiji Li, Zonglin Li, Zehao Li, Pengze Li, Guoyan Li, Lingkai Kong, Linglin Jing, Zhenjiang Jin, Feifei Jiang, Qian Jiang, Junhao Huang, Zixian Huang, Haian Huang, Zhouqi Hua, Ermo Hua, Han Hu, Linfeng Hou, Yinan He, Conghui He, Tianyao He, Xu Guo, Qipeng Guo, Aijia Guo, Yuzhe Gu, Lixin Gu, Jingyang Gong, Qiming Ge, Jiaye Ge, Songyang Gao, Jianfei Gao, Xinyu Fang, Caihua fan, Yue Fan, Yanhui Duan, Zichen Ding, Shengyuan Ding, Ning Ding, Xuanlang Dai, Erfei Cui, Ganqu Cui, Pei Chu, Tao Chu, Guangran Cheng, Yu Cheng, Kai Chen, Yongkang Chen, Chiyu Chen, Guanzhou Chen, Qiaosheng Chen, Sitao Chen, Xin Chen, Haojiong Chen, Yicheng Chen, Weihan Cao, Yuhang Cao, Qinglong Cao, Lei Bai

Computer Vision

GeoNDC: A Queryable Neural Data Cube for Planetary-Scale Earth Observation

Jianbo Qi, Mengyao Li, Baogui Jiang et al. (+3 more)

Satellite Earth observation has accumulated massive spatiotemporal archives essential for monitoring environmental change, yet these remain organized as discrete raster files, making them costly to store, transmit, and query. We present GeoNDC, a queryable neural data cube that encodes planetary-scale Earth observation data as a continuous spatiotemporal implicit neural field, enabling on-demand queries and continuous-time reconstruction without full decompression. Experiments on a 20-year global MODIS MCD43A4 reflectance record ($8016 \times 4008$ pixels, 7 bands, 915 temporal frames) show that the learned representation supports direct spatiotemporal queries on consumer hardware. On Sentinel-2 imagery (10 m), continuous temporal parameterization recovers cloud-free dynamics with high fidelity ($R^2 > 0.85$) under simulated 2-km cloud occlusion. On HiGLASS biophysical products (LAI and FPAR), GeoNDC attains near-perfect accuracy ($R^2 > 0.98$). The representation compresses the 20-year MODIS archive to 0.44\,GB – approximately 95:1 relative to an optimized Int16 baseline – with high spectral fidelity (mean $R^2 > 0.98$, mean RMSE $= 0.021$). These results suggest GeoNDC offers a unified AI-native representation for planetary-scale Earth observation, complementing raw archives with a compact, analysis-ready data layer integrating query, reconstruction, and compression in a single framework.
Read the full abstract

All authors Jianbo Qi, Mengyao Li, Baogui Jiang, Yidan Chen, Xihan Mu, Qiao Wang

Computer Vision

CARE: Training-Free Controllable Restoration for Medical Images via Dual-Latent Steering

Xu Liu

Medical image restoration is essential for improving the usability of noisy, incomplete, and artifact-corrupted clinical scans, yet existing methods often rely on task-specific retraining and offer limited control over the trade-off between faithful reconstruction and prior-driven enhancement. This lack of controllability is especially problematic in clinical settings, where overly aggressive restoration may introduce hallucinated details or alter diagnostically important structures. In this work, we propose CARE, a training-free controllable restoration framework for real-world medical images that explicitly balances structure preservation and prior-guided refinement during inference. CARE uses a dual-latent restoration strategy, in which one branch enforces data fidelity and anatomical consistency while the other leverages a generative prior to recover missing or degraded information. A risk-aware adaptive controller dynamically adjusts the contribution of each branch based on restoration uncertainty and local structural reliability, enabling conservative or enhancement-focused restoration modes without additional model training. We evaluate CARE on noisy and incomplete medical imaging scenarios and show that it achieves strong restoration quality while better preserving clinically relevant structures and reducing the risk of implausible reconstructions and show that it achieves strong restoration quality while better preserving clinically relevant structures and reducing the risk of implausible reconstructions. The proposed approach offers a practical step toward safer, more controllable, and more deployment-ready medical image restoration.
Read the full abstract

Computer Vision

VideoTIR: Accurate Understanding for Long Videos with Efficient Tool-Integrated Reasoning

Zhe Gao, Shiyu Shen, Taifeng Chai et al. (+7 more)

Existing Multimodal Large Language Models (MLLMs) often suffer from hallucinations in long video understanding (LVU), primarily due to the imbalance between textual and visual tokens. Observing that MLLMs handle short visual inputs well, recent LVU works alleviate hallucinations by automatically parsing the vast visual data into manageable segments that can be effectively processed by MLLMs. SFT-based tool-calling methods can serve this purpose, but they typically require vast amounts of fine-grained, high-quality data and suffer from constrained tool-calling trajectories. We propose a novel VideoTIR that leverages Reinforcement Learning (RL) to encourage proper usage of comprehensive multi-level toolkits for efficient long video understanding. VideoTIR explores both Zero-RL and SFT cold-starting to enable MLLMs to retrieve and focus on meaningful video segments/images/regions, enhancing long video understanding both accurately and efficiently. To reduce redundant tool-calling, we propose Toolkit Action Grouped Policy Optimization (TAGPO), which enhances the efficiency of the calling process through stepwise reward assignment and reuse of failed rollouts. Additionally, we develop a sandbox-based trajectory synthesis framework to generate high-quality trajectories data. Extensive experiments on three long-video QA benchmarks demonstrate the effectiveness and efficiency of our method.
Read the full abstract

All authors Zhe Gao, Shiyu Shen, Taifeng Chai, Weinong Wang, Haotian Xu, Xing Wu, Wenbin Li, Qi Fan, Yang Gao, Dacheng Tao

Computer Vision

GDPO-Listener: Expressive Interactive Head Generation via Auto-Regressive Flow Matching and Group reward-Decoupled Policy Optimization

Zhangyu Jin, Maksim Siniukov, Deuksin Kwon et al. (+2 more)

Generating realistic 3D head motion for dyadic interactions is a significant challenge in virtual human synthesis. While recent methods achieve impressive results with speaking heads, they frequently suffer from the `Regression-to-the-Mean' problem in listener motions, collapsing into static faces, and lack the parameter space for complex nonverbal motions. In this paper, we propose GDPO-Listener, a novel framework that achieves highly expressive speaking and listening motion generation. First, we introduce an Auto-Regressive Flow Matching architecture enabling stable supervised learning. Second, to overcome kinematic stillness, we apply the Group reward-Decoupled Policy Optimization (GDPO). By isolating reward normalization across distinct FLAME parameter groups, GDPO explicitly incentivizes high variance expressive generations. Finally, we enable explicit semantic text control for customizable responses. Extensive evaluations across the Seamless Interaction and DualTalk datasets demonstrate superior performance compared to existing baselines on long-term kinematic variance, visual expressivity and semantic controllability.
Read the full abstract

All authors Zhangyu Jin, Maksim Siniukov, Deuksin Kwon, Ashutosh Chaubey, Mohammad Soleymani

Computer Vision

Few TensoRF: Enhance the Few-shot on Tensorial Radiance Fields

Thanh-Hai Le, Hoang-Hau Tran and Trong-Nghia Vu

This paper presents Few TensoRF, a 3D reconstruction framework that combines TensorRF's efficient tensor based representation with FreeNeRF's frequency driven few shot regularization. Using TensorRF to significantly accelerate rendering speed and introducing frequency and occlusion masks, the method improves stability and reconstruction quality under sparse input views. Experiments on the Synthesis NeRF benchmark show that Few TensoRF method improves the average PSNR from 21.45 dB (TensorRF) to 23.70 dB, with the fine tuned version reaching 24.52 dB, while maintaining TensorRF's fast \(\approx10-15\) minute training time. Experiments on the THuman 2.0 dataset further demonstrate competitive performance in human body reconstruction, achieving 27.37 - 34.00 dB with only eight input images. These results highlight Few TensoRF as an efficient and data effective solution for real-time 3D reconstruction across diverse scenes.
Read the full abstract

Computer Vision

Improving Fine-Grained Rice Leaf Disease Detection via Angular-Compactness Dual Loss Learning

Md. Rokon Mia, Rakib Hossain Sajib, Abdullah Al Noman et al. (+2 more)

Early detection of rice leaf diseases is critical, as rice is a staple crop supporting a substantial share of the world's population. Timely identification of these diseases enables more effective intervention and significantly reduces the risk of large-scale crop losses. However, traditional deep learning models primarily rely on cross entropy loss, which often struggles with high intra-class variance and inter-class similarity, common challenges in plant pathology datasets. To tackle this, we propose a dual-loss framework that combines Center Loss and ArcFace Loss to enhance fine-grained classification of rice leaf diseases. The method is applied into three state-of-the-art backbone architectures: InceptionNetV3, DenseNet201, and EfficientNetB0 trained on the public Rice Leaf Dataset. Our approach achieves significant performance gains, with accuracies of 99.6%, 99.2% and 99.2% respectively. The results demonstrate that angular margin-based and center-based constraints substantially boost the discriminative strength of feature embeddings. In particular, the framework does not require major architectural modifications, making it efficient and practical for real-world deployment in farming environments.
Read the full abstract

All authors Md. Rokon Mia, Rakib Hossain Sajib, Abdullah Al Noman, Abir Ahmed, B M Taslimul Haque

Computer Vision

Interpretable Zero-shot Referring Expression Comprehension with Query-driven Scene Graphs

Yike Wu, Necva Bolucu, Stephen Wan et al. (+3 more)

Zero-shot referring expression comprehension (REC) aims to locate target objects in images given natural language queries without relying on task-specific training data, demanding strong visual understanding capabilities. Existing Vision-Language Models~(VLMs), such as CLIP, commonly address zero-shot REC by directly measuring feature similarities between textual queries and image regions. However, these methods struggle to capture fine-grained visual details and understand complex object relationships. Meanwhile, Large Language Models~(LLMs) excel at high-level semantic reasoning, their inability to directly abstract visual features into textual semantics limits their application in REC tasks. To overcome these limitations, we propose SGREC, an interpretable zero-shot REC method leveraging query-driven scene graphs as structured intermediaries. Specifically, we first employ a VLM to construct a query-driven scene graph that explicitly encodes spatial relationships, descriptive captions, and object interactions relevant to the given query. By leveraging this scene graph, we bridge the gap between low-level image regions and higher-level semantic understanding required by LLMs. Finally, an LLM infers the target object from the structured textual representation provided by the scene graph, responding with detailed explanations for its decisions that ensure interpretability in the inference process. Extensive experiments show that SGREC achieves top-1 accuracy on most zero-shot REC benchmarks, including RefCOCO val (66.78%), RefCOCO+ testB (53.43%), and RefCOCOg val (73.28%), highlighting its strong visual scene understanding.
Read the full abstract

All authors Yike Wu, Necva Bolucu, Stephen Wan, Dadong Wang, Jiahao Xia, Jian Zhang

Computer Vision

Distributed Real-Time Vehicle Control for Emergency Vehicle Transit: A Scalable Cooperative Method

WenXi Wang and JunQi Zhang

Rapid transit of emergency vehicles is critical for saving lives and reducing property loss but often relies on surrounding ordinary vehicles to cooperatively adjust their driving behaviors. It is important to ensure rapid transit of emergency vehicles while minimizing the impact on ordinary vehicles. Centralized mathematical solver and reinforcement learning are the state-of-the-art methods. The former obtains optimal solutions but is only practical for small-scale scenarios. The latter implicitly learns through extensive centralized training but the trained model exhibits limited scalability to different traffic conditions. Hence, existing methods suffer from two fundamental limitations: high computational cost and lack of scalability. To overcome above limitations, this work proposes a scalable distributed vehicle control method, where vehicles adjust their driving behaviors in a distributed manner online using only local instead of global information. We proved that the proposed distributed method using only local information is approximately equivalent to the one using global information, which enables vehicles to evaluate their candidate states and make approximately optimal decisions in real time without pre-training and with natural adaptability to varying traffic conditions. Then, a distributed conflict resolution mechanism is further proposed to guarantee vehicles' safety by avoiding their decision conflicts, which eliminates the single-point-of-failure risk of centralized methods and provides deterministic safety guarantees that learned methods cannot offer. Compared with existing methods, simulation experiments based on real-world traffic datasets demonstrate that the proposed method achieves faster decision-making, less impact on ordinary vehicles, and maintains much stronger scalability across different traffic densities and road configurations.
Read the full abstract

Computer Vision

Relaxed Rigidity with Ray-based Grouping for Dynamic Gaussian Splatting

Junoh Lee, Junmyeong Lee, Yeon-Ji Song et al. (+4 more)

The reconstruction of dynamic 3D scenes using 3D Gaussian Splatting has shown significant promise. A key challenge, however, remains in modeling realistic motion, as most methods fail to align the motion of Gaussians with real-world physical dynamics. This misalignment is particularly problematic for monocular video datasets, where failing to maintain coherent motion undermines local geometric structure, ultimately leading to degraded reconstruction quality. Consequently, many state-of-the-art approaches rely heavily on external priors, such as optical flow or 2D tracks, to enforce temporal coherence. In this work, we propose a novel method to explicitly preserve the local geometric structure of Gaussians across time in 4D scenes. Our core idea is to introduce a view-space ray grouping strategy that clusters Gaussians intersected by the same ray, considering only those whose $\alpha$-blending weights exceed a threshold. We then apply constraints to these groups to maintain a consistent spatial distribution, effectively preserving their local geometry. This approach enforces a more physically plausible motion model by ensuring that local geometry remains stable over time, eliminating the reliance on external guidance. We demonstrate the efficacy of our method by integrating it into two distinct baseline models. Extensive experiments on challenging monocular datasets show that our approach significantly outperforms existing methods, achieving superior temporal consistency and reconstruction quality.
Read the full abstract

All authors Junoh Lee, Junmyeong Lee, Yeon-Ji Song, Inhwan Bae, Jisu Shin, Hae-Gon Jeon, Jin-Hwa Kim

Computer Vision

C2W-Tune: Cavity-to -Wall Transfer Learning for Thin Atrial Wall Segmentation in 3D LGE-MRI

Yusri Al-Sanaani, Rebecca Thornhill and Sreeraman Rajan

Accurate segmentation of the left atrial (LA) wall in 3D late gadolinium-enhanced MRI (LGE-MRI) is essential for wall thickness mapping and fibrosis quantification, yet it remains challenging due to the wall's thin geometry, complex anatomy, and low contrast. We propose C2W-Tune, a two-stage cavity-to-wall transfer framework that leverages a high-accuracy LA cavity model as an anatomical prior to improve thin-wall delineation. Using a 3D U-Net with a ResNeXt encoder and instance normalization, Stage 1 pre-trains the network to segment the LA cavity, learning robust atrial representations. Stage 2 transfers these weights and adapts the network to LA wall segmentation using a progressive layer-unfreezing schedule to preserve cavity features while enabling wall-specific refinement. On the 2018 LA Segmentation Challenge dataset, C2W-Tune outperformed an architecture-matched baseline trained from scratch. The wall Dice score increased from 0.623 to 0.814, surface Dice at 1 mm increased from 0.553 to 0.731, 95th-percentile Hausdorff distance (HD95) decreased from 2.95 mm to 2.55 mm, and average symmetric surface distance (ASSD) decreased from 0.71 mm to 0.63 mm. Under reduced supervision using 70 training volumes sampled from the same training set, C2W-Tune achieved a Dice of 0.78, remaining competitive with recent multi-class bi-atrial benchmarks, typically 0.6-0.7. These results show that anatomically grounded task transfer with controlled fine-tuning improves accuracy for thin LA wall segmentation in 3D LGE-MRI.
Read the full abstract

Computer Vision

Towards Video Anomaly Detection from Event Streams: A Baseline and Benchmark Datasets

Peng Wu, Yuting Yan, Guansong Pang et al. (+4 more)

Event-based vision, characterized by low redundancy, focus on dynamic motion, and inherent privacy-preserving properties, naturally fits the demands of video anomaly detection (VAD). However, the absence of dedicated event-stream anomaly detection datasets and effective modeling strategies has significantly hindered progress in this field. In this work, we take the first major step toward establishing event-based VAD as a unified research direction. We first construct multiple event-stream based benchmarks for video anomaly detection, featuring synchronized event and RGB recordings. Leveraging the unique properties of events, we then propose an EVent-centric spatiotemporal Video Anomaly Detection framework, namely EWAD, with three key innovations: an event density aware dynamic sampling strategy to select temporally informative segments; a density-modulated temporal modeling approach that captures contextual relations from sparse event streams; and an RGB-to-event knowledge distillation mechanism to enhance event-based representations under weak supervision. Extensive experiments on three benchmarks demonstrate that our EWAD achieves significant improvements over existing approaches, highlighting the potential and effectiveness of event-driven modeling for video anomaly detection. The benchmark datasets will be made publicly available.
Read the full abstract

All authors Peng Wu, Yuting Yan, Guansong Pang, Yujia Sun, Qingsen Yan, Peng Wang, Yanning Zhang

Computer Vision

Few-Shot Left Atrial Wall Segmentation in 3D LGE MRI via Meta-Learning

Yusri Al-Sanaani, Rebecca Thornhill, Pablo Nery et al. (+5 more)

Segmenting the left atrial (LA) wall from late gadolinium enhancement magnetic resonance imaging (LGE-MRI) is challenging because of its thin geometry, low contrast, and limited expert annotations. We propose a model-agnostic meta-learning (MAML) framework with a 3D residual U-Net backbone for K-shot (K = 5, 10, 20) LA wall segmentation. The framework is meta-trained on LA wall tasks together with auxiliary LA and right atrial (RA) cavity tasks and uses a boundary-aware composite loss to improve thin-structure delineation. We evaluated MAML on a held-out clean test set and assessed its robustness under an unseen synthetic domain shift and on a local cohort. On the held-out clean test set, MAML outperformed the K-shot fine-tuning baseline at 5-shot, achieving Dice coefficient (DSC) = 0.54 versus 0.48 and Hausdorff distance (HD95) = 4.60 versus 6.40 mm. At 20-shot, MAML approached the fully supervised model trained from scratch, with DSC = 0.59 versus 0.61. Under unseen shifts, performance decreased relative to clean testing but improved consistently as K increased. At 5-shot, MAML achieved DSC = 0.52 and HD95 = 5.02 mm under the unseen synthetic shift, and DSC = 0.50 and HD95 = 5.43 mm on the local cohort. These results suggest that meta-learning can improve thin-wall delineation in low-shot adaptation and may reduce the annotation burden for atrial remodeling assessment.
Read the full abstract

All authors Yusri Al-Sanaani, Rebecca Thornhill, Pablo Nery, Elena Pena, Robert deKemp, Calum Redpath, David Birnie, Sreeraman Rajan

Computer Vision

MoE-GRPO: Optimizing Mixture-of-Experts via Reinforcement Learning in Vision-Language Models

Dohwan Ko, Jinyoung Park, Seoung Choi et al. (+3 more)

Mixture-of-Experts (MoE) has emerged as an effective approach to reduce the computational overhead of Transformer architectures by sparsely activating a subset of parameters for each token while preserving high model capacity. This paradigm has recently been extended to Vision-Language Models (VLMs), enabling scalable multi-modal understanding with reduced computational cost. However, the widely adopted deterministic top-K routing mechanism may overlook more optimal expert combinations and lead to expert overfitting. To address this limitation and improve the diversity of expert selection, we propose MoE-GRPO, a reinforcement learning (RL)-based framework for optimizing expert routing in MoE-based VLMs. Specifically, we formulate expert selection as a sequential decision-making problem and optimize it using Group Relative Policy Optimization (GRPO), allowing the model to learn adaptive expert routing policies through exploration and reward-based feedback. Furthermore, we introduce a modality-aware router guidance that enhances training stability and efficiency by discouraging the router from exploring experts that are infrequently activated for a given modality. Extensive experiments on multi-modal image and video benchmarks show that MoE-GRPO consistently outperforms standard top-K routing and its variants by promoting more diverse expert selection, thereby mitigating expert overfitting and enabling a task-level expert specialization.
Read the full abstract

All authors Dohwan Ko, Jinyoung Park, Seoung Choi, Sanghyeok Lee, Seohyun Lee, Hyunwoo J. Kim

Computer Vision

PASDiff: Physics-Aware Semantic Guidance for Joint Real-World Low-Light Face Enhancement and Restoration

Yilin Ni, Wenjie Li, Zhengxue Wang et al. (+3 more)

Face images captured in real-world low light suffer multiple degradations-low illumination, blur, noise, and low visibility, etc. Existing cascaded solutions often suffer from severe error accumulation, while generic joint models lack explicit facial priors and struggle to resolve clear face structures. In this paper, we propose PASDiff, a Physics-Aware Semantic Diffusion with a training-free manner. To achieve a plausible illumination and color distribution, we leverage inverse intensity weighting and Retinex theory to introduce photometric constraints, thereby reliably recovering visibility and natural chromaticity. To faithfully reconstruct facial details, our Style-Agnostic Structural Injection (SASI) extracts structures from an off-the-shelf facial prior while filtering out its intrinsic photometric biases, seamlessly harmonizing identity features with physical constraints. Furthermore, we construct WildDark-Face, a real-world benchmark of 700 low-light facial images with complex degradations. Extensive experiments demonstrate that PASDiff significantly outperforms existing methods, achieving a superior balance among natural illumination, color recovery, and identity consistency. Code and dataset will be available at https://github.com/IVIPLab/PASDiff.
Read the full abstract

All authors Yilin Ni, Wenjie Li, Zhengxue Wang, Juncheng Li, Guangwei Gao, Jian Yang

Computer Vision

Self-Corrected Image Generation with Explainable Latent Rewards

Yinyi Luo, Hrishikesh Gokhale, Marios Savvides et al. (+2 more)

Despite significant progress in text-to-image generation, aligning outputs with complex prompts remains challenging, particularly for fine-grained semantics and spatial relations. This difficulty stems from the feed-forward nature of generation, which requires anticipating alignment without fully understanding the output. In contrast, evaluating generated images is more tractable. Motivated by this asymmetry, we propose xLARD, a self-correcting framework that uses multimodal large language models to guide generation through Explainable LAtent RewarDs. xLARD introduces a lightweight corrector that refines latent representations based on structured feedback from model-generated references. A key component is a differentiable mapping from latent edits to interpretable reward signals, enabling continuous latent-level guidance from non-differentiable image-level evaluations. This mechanism allows the model to understand, assess, and correct itself during generation. Experiments across diverse generation and editing tasks show that xLARD improves semantic alignment and visual fidelity while maintaining generative priors. Code is available at https://yinyiluo.github.io/xLARD/.
Read the full abstract

All authors Yinyi Luo, Hrishikesh Gokhale, Marios Savvides, Jindong Wang, Shengfeng He

Computer Vision · Cross-listed from cs.AI

Can MLLMs Read Students' Minds? Unpacking Multimodal Error Analysis in Handwritten Math

Dingjie Song, Tianlong Xu, Yi-Fan Zhang et al. (+6 more)

Assessing student handwritten scratchwork is crucial for personalized educational feedback but presents unique challenges due to diverse handwriting, complex layouts, and varied problem-solving approaches. Existing educational NLP primarily focuses on textual responses and neglects the complexity and multimodality inherent in authentic handwritten scratchwork. Current multimodal large language models (MLLMs) excel at visual reasoning but typically adopt an "examinee perspective", prioritizing generating correct answers rather than diagnosing student errors. To bridge these gaps, we introduce ScratchMath, a novel benchmark specifically designed for explaining and classifying errors in authentic handwritten mathematics scratchwork. Our dataset comprises 1,720 mathematics samples from Chinese primary and middle school students, supporting two key tasks: Error Cause Explanation (ECE) and Error Cause Classification (ECC), with seven defined error types. The dataset is meticulously annotated through rigorous human-machine collaborative approaches involving multiple stages of expert labeling, review, and verification. We systematically evaluate 16 leading MLLMs on ScratchMath, revealing significant performance gaps relative to human experts, especially in visual recognition and logical reasoning. Proprietary models notably outperform open-source models, with large reasoning models showing strong potential for error explanation. All evaluation data and frameworks are publicly available to facilitate further research.
Read the full abstract

All authors Dingjie Song, Tianlong Xu, Yi-Fan Zhang, Hang Li, Zhiling Yan, Xing Fan, Haoyang Li, Lichao Sun, Qingsong Wen

Computer Vision

Select, Hypothesize and Verify: Towards Verified Neuron Concept Interpretation

ZeBin Ji, Yang Hu, Xiuli Bi et al. (+2 more)

It is essential for understanding neural network decisions to interpret the functionality (also known as concepts) of neurons. Existing approaches describe neuron concepts by generating natural language descriptions, thereby advancing the understanding of the neural network's decision-making mechanism. However, these approaches assume that each neuron has well-defined functions and provides discriminative features for neural network decision-making. In fact, some neurons may be redundant or may offer misleading concepts. Thus, the descriptions for such neurons may cause misinterpretations of the factors driving the neural network's decisions. To address the issue, we introduce a verification of neuron functions, which checks whether the generated concept highly activates the corresponding neuron. Furthermore, we propose a Select-Hypothesize-Verify framework for interpreting neuron functionality. This framework consists of: 1) selecting activation samples that best capture a neuron's well-defined functional behavior through activation-distribution analysis; 2) forming hypotheses about concepts for the selected neurons; and 3) verifying whether the generated concepts accurately reflect the functionality of the neuron. Extensive experiments show that our method produces more accurate neuron concepts. Our generated concepts activate the corresponding neurons with a probability approximately 1.5 times that of the current state-of-the-art method.
Read the full abstract

All authors ZeBin Ji, Yang Hu, Xiuli Bi, Bo Liu, Bin Xiao

Computer Vision

BiFM: Bidirectional Flow Matching for Few-Step Image Editing and Generation

Yasong Dai, Zeeshan Hayder, David Ahmedt-Aristizabal et al. (+1 more)

Recent diffusion and flow matching models have demonstrated strong capabilities in image generation and editing by progressively removing noise through iterative sampling. While this enables flexible inversion for semantic-preserving edits, few-step sampling regimes suffer from poor forward process approximation, leading to degraded editing quality. Existing few-step inversion methods often rely on pretrained generators and auxiliary modules, limiting scalability and generalization across different architectures. To address these limitations, we propose BiFM (Bidirectional Flow Matching), a unified framework that jointly learns generation and inversion within a single model. BiFM directly estimates average velocity fields in both “image $\to$ noise" and “noise $\to$ image" directions, constrained by a shared instantaneous velocity field derived from either predefined schedules or pretrained multi-step diffusion models. Additionally, BiFM introduces a novel training strategy using continuous time-interval supervision, stabilized by a bidirectional consistency objective and a lightweight time-interval embedding. This bidirectional formulation also enables one-step inversion and can integrate seamlessly into popular diffusion and flow matching backbones. Across diverse image editing and generation tasks, BiFM consistently outperforms existing few-step approaches, achieving superior performance and editability.
Read the full abstract

All authors Yasong Dai, Zeeshan Hayder, David Ahmedt-Aristizabal, Hongdong Li