视觉大模型 / VLM - arXivDaily 专题

2510.00055 2025-10-08 eess.IV cs.CV cs.CY 57%

Adapting Large Language Models to Mitigate Skin Tone Biases in Clinical Dermatology Tasks: A Mixed-Methods Study

Kiran Nijjer, Ryan Bui, Derek Jiu, Adnan Ahmed, Peter Wang, Kevin Zhu, Lilly Zhu

机构 * Stanford University（斯坦福大学）； Algoverse AI Research（Algoverse人工智能研究）

专题命中幻觉与鲁棒性：vision-language model(abstract)；分类 cs.CV

Comments Accepted to EADV (European Academy of Dermatology) and SID (Society for Investigative Dermatology)

2510.04560 2025-10-07 cs.AI 57%

ContextNav: Towards Agentic Multimodal In-Context Learning

Honghao Fu, Yuan Ouyang, Kai-Wei Chang, Yiwei Wang, Zi Huang, Yujun Cai

机构 * The University of Queensland（昆士兰大学）； Nanjing University（南京大学）； University of California, Los Angeles（加州大学洛杉矶分校）； University of California, Merced（加州大学默塞德分校）

专题命中幻觉与鲁棒性：multimodal large language model(abstract)；分类 cs.AI

2510.04145 2025-10-07 cs.CV cs.CL cs.IR 57%

Automating construction safety inspections using a multi-modal vision-language RAG framework

Chenxin Wang, Elyas Asadi Shamsabadi, Zhaohui Chen, Luming Shen, Alireza Ahmadian Fard Fini, Daniel Dias-da-Costa

专题命中幻觉与鲁棒性：vision-language model(abstract)；分类 cs.CV

Comments 33 pages, 11 figures, 7 tables

2510.00603 2025-10-02 cs.CV 57%

LVLMs as inspectors: an agentic framework for category-level structural defect annotation

Sheng Jiang, Yuanmin Ning, Bingxi Huang, Peiyin Chen, Zhaohui Chen

专题命中幻觉与鲁棒性：vision-language model(abstract)；分类 cs.CV

2507.04946 2025-10-01 cs.CV cs.CL 57%

Taming the Tri-Space Tension: ARC-Guided Hallucination Modeling and Control for Text-to-Image Generation

Jianjiang Yang, Ziyan Huang, Yanshu li, Da Peng, Huaiyuan Yao

机构 * University of Bristol（布里斯托大学）； South China University of Technology（华南理工大学）； Brown University（布朗大学）； Xi’an Jiaotong University（西安交通大学）； Arizona State University（亚利桑那州立大学）

专题命中幻觉与鲁棒性：grounding(abstract)；分类 cs.CV

Comments 9 pages,6 figures,7 tables

2509.00310 2025-09-30 cs.RO cs.AI 57%

TReF-6: Inferring Task-Relevant Frames from a Single Demonstration for One-Shot Skill Generalization

Yuxuan Ding, Shuangge Wang, Tesca Fitzgerald

机构 * Yale University（耶鲁大学）

专题命中幻觉与鲁棒性：vision-language model(abstract)；分类 cs.AI

2507.23284 2025-09-30 cs.CV 57%

Bidirectional Likelihood Estimation with Multi-Modal Large Language Models for Text-Video Retrieval

Dohwan Ko, Ji Soo Lee, Minhyuk Choi, Zihang Meng, Hyunwoo J. Kim

机构 * Korea University（韩国大学）； Meta GenAI（Meta 生成人工智能）； KAIST（韩国科学技术院）

专题命中幻觉与鲁棒性：MLLM(abstract)；分类 cs.CV

Comments ICCV 2025 Highlight

2509.22356 2025-09-29 cs.RO cs.CV 57%

RoboView-Bias: Benchmarking Visual Bias in Embodied Agents for Robotic Manipulation

Enguang Liu, Siyuan Liang, Liming Lu, Xiyu Zeng, Xiaochun Cao, Aishan Liu, Shuchao Pang

机构 * School of Cyber Science and Engineering, Nanjing University of Science and Technology（南京理工大学计算机科学与工程学院）； National University of Singapore（新加坡国立大学）； Sun Yat-sen University（中山大学）； Beihang University（北京航空航天大学）

专题命中幻觉与鲁棒性：grounding(abstract)；分类 cs.CV

2505.11029 2025-09-29 cs.LG 57%

Exploiting the Asymmetric Uncertainty Structure of Pre-trained VLMs on the Unit Hypersphere

Li Ju, Max Andersson, Stina Fredriksson, Edward Glöckner, Andreas Hellander, Ekta Vats, Prashant Singh

机构 * Department of Information Technology, Uppsala University（信息科技系，乌普萨拉大学）； Science for Life Laboratory, Uppsala University（生命科学实验室，乌普萨拉大学）

专题命中幻觉与鲁棒性：vision-language model(abstract)；分类 cs.LG

2509.19688 2025-09-25 cs.RO cs.LG cs.SY eess.SY math.OC 57%

Formal Safety Verification and Refinement for Generative Motion Planners via Certified Local Stabilization

Devesh Nath, Haoran Yin, Glen Chou

机构 * Georgia Institute of Technology（佐治亚理工学院）

专题命中幻觉与鲁棒性：vision-language model(abstract)；分类 cs.LG

Comments 10 pages, 12 figures

2509.19203 2025-09-24 cs.CV 57%

Vision-Free Retrieval: Rethinking Multimodal Search with Textual Scene Descriptions

Ioanna Ntinou, Alexandros Xenos, Yassine Ouali, Adrian Bulat, Georgios Tzimiropoulos

机构 * Queen Mary University of London（伦敦女王大学）； Samsung AI Centre（三星人工智能中心）； Technical University of Iași（伊阿苏技术大学）

专题命中幻觉与鲁棒性：vision-language model(abstract)；分类 cs.CV

Comments Accepted at EMNLP 2025

2509.18998 2025-09-24 math.AP cs.LG q-bio.CB q-bio.QM 57%

Bayesian Calibration and Model Assessment of Cell Migration Dynamics with Surrogate Model Integration

Christina Schenk, Jacobo Ayensa Jiménez, Ignacio Romero

机构 * IMDEA Materials Institute（IMDEA材料研究所）； Universidad Politécnica de Madrid（马德里理工大学）； Aragón Institute of Engineering Research (I3A)（阿伦工程技术研究所（I3A））

专题命中幻觉与鲁棒性：grounding(abstract)；分类 cs.LG

Comments 31 pages, 13 figures, 1 table

2504.11669 2025-09-23 cs.CV 57%

Co-STAR: Collaborative Curriculum Self-Training with Adaptive Regularization for Source-Free Video Domain Adaptation

Amirhossein Dadashzadeh, Parsa Esmati, Majid Mirmehdi

机构 * University of Bristol, UK（布里斯托大学）

专题命中幻觉与鲁棒性：vision-language model(abstract)；分类 cs.CV

2502.19269 2025-09-23 cs.CV 57%

Neural Antidote: Class-Wise Prompt Tuning for Purifying Backdoors in CLIP

Jiawei Kong, Hao Fang, Sihang Guo, Chenxi Qing, Kuofeng Gao, Bin Chen, Shu-Tao Xia, Ke Xu

机构 * Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院，清华大学）； School of Computer Science and Technology, Harbin Institute of Technology（哈尔滨工业大学计算机科学与技术学院）； Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）

专题命中幻觉与鲁棒性：vision-language model(abstract)；分类 cs.CV

2507.07620 2025-09-22 cs.CV 57%

ViLU: Learning Vision-Language Uncertainties for Failure Prediction

Marc Lafon, Yannis Karmim, Julio Silva-Rodríguez, Paul Couairon, Clément Rambour, Raphaël Fournier-Sniehotta, Ismail Ben Ayed, Jose Dolz, Nicolas Thome

专题命中幻觉与鲁棒性：vision-language model(abstract)；分类 cs.CV

Journal ref International Conference on Computer Vision, ICCV 2025

2509.10570 2025-09-16 cs.RO cs.AI 57%

Large Foundation Models for Trajectory Prediction in Autonomous Driving: A Comprehensive Survey

Wei Dai, Shengen Wu, Wei Wu, Zhenhao Wang, Sisuo Lyu, Haicheng Liao, Limin Yu, Weiping Ding, Runwei Guan, Yutao Yue

机构 * Department of Mathematical Sciences, School of Physical sciences, University of Liverpool（利物浦大学数学科学系）； Department of Communications and Networking, School of Advanced Technology, Xi’an Jiaotong-Liverpool University（西安交通大学利物浦大学通讯与网络系）； Thrust of Artificial Intelligence, The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）人工智能方向）； Deep Interdisciplinary Intelligence Lab, The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）深度跨学科智能实验室）； School of Mathematics and Statistics, Shandong University（山东大学数学与统计学院）； School of Artificial Intelligence and Computer Science, Nantong University（南通大学人工智能与计算机科学学院）； Thrust of Data Science and Analytics, The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）数据科学与分析方向）； Institute of Deep Perception Technology, Jiangsu（江苏深度感知技术研究院）

专题命中幻觉与鲁棒性：multimodal large language model(abstract)；分类 cs.AI

Comments 22 pages, 6 figures

2509.09397 2025-09-12 cs.CV 57%

Decoupling Clinical and Class-Agnostic Features for Reliable Few-Shot Adaptation under Shift

Umaima Rahman, Raza Imam, Mohammad Yaqub, Dwarikanath Mahapatra

机构 * Mohamed Bin Zayed University of Artificial Intelligence（莫扎德人工智能大学）； Khalifa University（卡利法大学）

专题命中幻觉与鲁棒性：vision-language model(abstract)；分类 cs.CV

2405.03486 2025-09-12 cs.CR cs.CV cs.SI 57%

UnsafeBench: Benchmarking Image Safety Classifiers on Real-World and AI-Generated Images

Yiting Qu, Xinyue Shen, Yixin Wu, Michael Backes, Savvas Zannettou, Yang Zhang

机构 * CISPA Helmholtz Center for Information Security（CISPA赫尔姆霍茨信息安全中心）； TU Delft（代尔夫特理工大学）

专题命中幻觉与鲁棒性：visual language model(abstract)；分类 cs.CV

Comments To Appear in the ACM Conference on Computer and Communications Security (CCS), October 13, 2025

2505.10993 2025-09-09 eess.IV cs.CV 57%

Content Generation Models in Computational Pathology: A Comprehensive Survey on Methods, Applications, and Challenges

Yuan Zhang, Xinfeng Zhang, Xiaoming Qi, Xinyu Wu, Feng Chen, Guanyu Yang, Huazhu Fu

机构 * Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, Nanjing, China（新型一代人工智能技术及其交叉应用重点实验室（东南大学），教育部，南京，中国）； School of Biomedical Engineering, Tsinghua University（生物医学工程学院，清华大学）； Department of Biomedical Engineering and Department of Electrical and Computer Engineering, National University of Singapore（生物医学工程系和电子与计算机工程系，新加坡国立大学）； School of Information Science and Engineering, Southeast University（信息科学与工程学院，东南大学）； Department of Biostatistics, Center for Global Health, School of Public Health, Nanjing Medical University（流行病学系，全球健康中心，公共卫生学院，南京医科大学）； Institute of High-Performance Computing, Agency for Science, Technology and Research, Singapore（高性能计算研究所，科技研究局，新加坡）

专题命中幻觉与鲁棒性：vision-language model(abstract)；分类 cs.CV

Comments 20 pages, 8 figures

2508.03864 2025-09-09 cs.AI 57%

Evo-MARL: Co-Evolutionary Multi-Agent Reinforcement Learning for Internalized Safety

Zhenyu Pan, Yiting Zhang, Yutong Zhang, Jianshu Zhang, Haozheng Luo, Yuwei Han, Dennis Wu, Hong-Yu Chen, Philip S. Yu, Manling Li, Han Liu

机构 * Northwestern University（西北大学）； University of Illinois at Chicago（伊利诺伊大学香槟分校）

专题命中幻觉与鲁棒性：multimodal large language model(abstract)；分类 cs.AI

Comments accepted by the Trustworthy FMs workshop in ICCV 2025

2507.19346 2025-09-05 cs.LG 57%

Short-Form Video Recommendations with Multimodal Embeddings: Addressing Cold-Start and Bias Challenges

Andrii Dzhoha, Katya Mirylenka, Egor Malykh, Marco-Andrea Buchmann, Francesca Catino

机构 * Zalando SE Berlin Germany（泽尔安多德国分公司）； Zalando Switzerland AG Zürich Switzerland（泽尔安多瑞士分公司）

专题命中幻觉与鲁棒性：vision-language model(abstract)；分类 cs.LG

2411.15537 2025-09-05 cs.CV 57%

MUNBa: Machine Unlearning via Nash Bargaining

Jing Wu, Mehrtash Harandi

机构 * Department of Data Science & AI（数据科学与人工智能系）； Department of Electrical and Computer Systems Engineering（电气与计算机系统工程系）

专题命中幻觉与鲁棒性：vision-language model(abstract)；分类 cs.CV

2509.00723 2025-09-03 cs.AI cs.MM 57%

OmniDPO: A Preference Optimization Framework to Address Omni-Modal Hallucination

Junzhe Chen, Tianshu Zhang, Shiyu Huang, Yuwei Niu, Chao Sun, Rongzhou Zhang, Guanyu Zhou, Lijie Wen, Xuming Hu

机构 * Tsinghua University（清华大学）； The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））； OpenRL ； Chongqing University（重庆大学）

专题命中幻觉与鲁棒性：grounding(abstract)；分类 cs.AI

2509.00371 2025-09-03 cs.CV 57%

Two Causes, Not One: Rethinking Omission and Fabrication Hallucinations in MLLMs

Guangzong Si, Hao Yin, Xianfei Li, Qing Ding, Wenlong Liao, Tao He, Pai Peng

专题命中幻觉与鲁棒性：multimodal large language model(abstract)；分类 cs.CV

Comments Preprint,Underreview

2508.17750 2025-08-26 cs.CV 57%

From Global to Local: Social Bias Transfer in CLIP

Ryan Ramos, Yusuke Hirota, Yuta Nakashima, Noa Garcia

机构 * The University of Osaka（大阪大学）； NVIDIA（英伟达）

专题命中幻觉与鲁棒性：visual question answering(abstract)；分类 cs.CV

2507.20077 2025-08-22 cs.CV cs.CL 57%

The Devil is in the EOS: Sequence Training for Detailed Image Captioning

Abdelrahman Mohamed, Yova Kementchedjhieva

机构 * Mohamed bin Zayed University of Artificial Intelligence（Mohamed bin Zayed人工智能大学）

专题命中幻觉与鲁棒性：vision-language model(abstract)；分类 cs.CV

Comments Accepted to COLM 2025

2508.08038 2025-08-19 cs.CV 57%

TRIDE: A Text-assisted Radar-Image weather-aware fusion network for Depth Estimation

Huawei Sun, Zixu Wang, Hao Feng, Julius Ott, Lorenzo Servadei, Robert Wille

专题命中幻觉与鲁棒性：vision-language model(abstract)；分类 cs.CV

Comments Accepted by TMLR (2025.08)

2506.12609 2025-08-19 cs.CV 57%

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation

Lexiang Tang, Xianwei Zhuang, Bang Yang, Zhiyuan Hu, Hongxiang Li, Lu Ma, Jinghan Ru, Yuexian Zou

专题命中幻觉与鲁棒性：vision-language model(abstract)；分类 cs.CV

2508.09584 2025-08-15 cs.CV 57%

SHALE: A Scalable Benchmark for Fine-grained Hallucination Evaluation in LVLMs

Bei Yan, Zhiyuan Chen, Yuecong Min, Jie Zhang, Jiahao Wang, Xiaozhen Wang, Shiguang Shan

机构 * Key Laboratory of AI Safety of CAS, Institute of Computing Technology, Chinese Academy of Sciences (CAS)（中国科学院计算技术研究所人工智能安全重点实验室）； University of Chinese Academy of Sciences（中国科学院大学）； Trustworthy Technology and Engineering Laboratory, Huawei（华为可信技术与工程实验室）

专题命中幻觉与鲁棒性：vision-language model(abstract)；分类 cs.CV

2508.00399 2025-08-15 cs.CV 57%

iSafetyBench: A video-language benchmark for safety in industrial environment

Raiyaan Abdullah, Yogesh Singh Rawat, Shruti Vyas

机构 * University of Central Florida（中央佛罗里达大学）

专题命中幻觉与鲁棒性：vision-language model(abstract)；分类 cs.CV

Comments Accepted to VISION'25 - ICCV 2025 workshop

1. 幻觉与鲁棒性 2251 篇

Adapting Large Language Models to Mitigate Skin Tone Biases in Clinical Dermatology Tasks: A Mixed-Methods Study

ContextNav: Towards Agentic Multimodal In-Context Learning

Automating construction safety inspections using a multi-modal vision-language RAG framework

LVLMs as inspectors: an agentic framework for category-level structural defect annotation

Taming the Tri-Space Tension: ARC-Guided Hallucination Modeling and Control for Text-to-Image Generation

TReF-6: Inferring Task-Relevant Frames from a Single Demonstration for One-Shot Skill Generalization

Bidirectional Likelihood Estimation with Multi-Modal Large Language Models for Text-Video Retrieval

RoboView-Bias: Benchmarking Visual Bias in Embodied Agents for Robotic Manipulation

Exploiting the Asymmetric Uncertainty Structure of Pre-trained VLMs on the Unit Hypersphere

Formal Safety Verification and Refinement for Generative Motion Planners via Certified Local Stabilization

Vision-Free Retrieval: Rethinking Multimodal Search with Textual Scene Descriptions

Bayesian Calibration and Model Assessment of Cell Migration Dynamics with Surrogate Model Integration

Co-STAR: Collaborative Curriculum Self-Training with Adaptive Regularization for Source-Free Video Domain Adaptation

Neural Antidote: Class-Wise Prompt Tuning for Purifying Backdoors in CLIP

ViLU: Learning Vision-Language Uncertainties for Failure Prediction

Large Foundation Models for Trajectory Prediction in Autonomous Driving: A Comprehensive Survey

Decoupling Clinical and Class-Agnostic Features for Reliable Few-Shot Adaptation under Shift

UnsafeBench: Benchmarking Image Safety Classifiers on Real-World and AI-Generated Images

Content Generation Models in Computational Pathology: A Comprehensive Survey on Methods, Applications, and Challenges

Evo-MARL: Co-Evolutionary Multi-Agent Reinforcement Learning for Internalized Safety

Short-Form Video Recommendations with Multimodal Embeddings: Addressing Cold-Start and Bias Challenges

MUNBa: Machine Unlearning via Nash Bargaining

OmniDPO: A Preference Optimization Framework to Address Omni-Modal Hallucination

Two Causes, Not One: Rethinking Omission and Fabrication Hallucinations in MLLMs

From Global to Local: Social Bias Transfer in CLIP

The Devil is in the EOS: Sequence Training for Detailed Image Captioning

TRIDE: A Text-assisted Radar-Image weather-aware fusion network for Depth Estimation

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation

SHALE: A Scalable Benchmark for Fine-grained Hallucination Evaluation in LVLMs

iSafetyBench: A video-language benchmark for safety in industrial environment