视觉大模型 / VLM - arXivDaily 专题

2506.15755 2025-06-23 cs.CV cs.CL 83%

VLMInferSlow: Evaluating the Efficiency Robustness of Large Vision-Language Models as a Service

Xiasi Wang, Tianliang Yao, Simin Chen, Runqi Wang, Lei YE, Kuofeng Gao, Yi Huang, Yuan Yao

机构 * The Hong Kong University of Science and Technology（香港科学与技术大学）； Tongji University（同济大学）； Beijing Jiaotong University（北京交通大学）； Huawei（华为）； Tsinghua University（清华大学）； University of Chinese Academy of Sciences（中国科学院大学）

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

Comments Accepted by ACL 2025

2506.02242 2025-06-19 cs.LG cs.CY 83%

From Street Views to Urban Science: Discovering Road Safety Factors with Multimodal Large Language Models

Yihong Tang, Ao Qu, Xujing Yu, Weipeng Deng, Jun Ma, Jinhua Zhao, Lijun Sun

机构 * McGill University（麦吉尔大学）； Massachusetts Institute of Technology（麻省理工学院）； The University of Hong Kong（香港大学）

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

2506.14808 2025-06-19 cs.LG 83%

PARC: A Quantitative Framework Uncovering the Symmetries within Vision Language Models

Jenny Schmalfuss, Nadine Chang, Vibashan VS, Maying Shen, Andres Bruhn, Jose M. Alvarez

机构 * University of Stuttgart（斯图加特大学）； NVIDIA（NVIDIA公司）； Johns Hopkins University（约翰霍普金斯大学）

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

Comments Accepted to CVPR 2025

2410.14669 2025-06-11 cs.CV cs.CL 83%

NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples

Baiqi Li, Zhiqiu Lin, Wenxuan Peng, Jean de Dieu Nyandwi, Daniel Jiang, Zixian Ma, Simran Khanuja, Ranjay Krishna, Graham Neubig, Deva Ramanan

机构 * Carnegie Mellon University（卡内基梅隆大学）； University of Washington（华盛顿大学）

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

Comments Accepted to NeurIPS 24; We open-source our dataset at: https://huggingface.co/datasets/BaiqiL/NaturalBench ; Project page at: https://linzhiqiu.github.io/papers/naturalbench/

2506.01307 2025-06-03 cs.CR cs.AI 83%

Align is not Enough: Multimodal Universal Jailbreak Attack against Multimodal Large Language Models

Youze Wang, Wenbo Hu, Yinpeng Dong, Jing Liu, Hanwang Zhang, Richang Hong

机构 * School of Computer Science and Information Engineering, Hefei University of Technology（合肥工业大学计算机科学与信息工程学院）； Tsinghua University（清华大学）； Institute of automation, Chinese academy of science（中国科学院自动化研究所）； School of Computer Science and Engineering, Nanyang Technological University（南洋理工大学计算机科学与工程学院）

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

2505.23793 2025-06-02 cs.CR cs.AI 83%

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models

Baolin Zheng, Guanlin Chen, Hongqiong Zhong, Qingyang Teng, Yingshui Tan, Zhendong Liu, Weixun Wang, Jiaheng Liu, Jian Yang, Huiyun Jing, Jincheng Wei, Wenbo Su, Xiaoyong Zhu, Bo Zheng, Kaifu Zhang

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

2505.20236 2025-05-27 cs.CV 83%

Seeing is Believing, but How Much? A Comprehensive Analysis of Verbalized Calibration in Vision-Language Models

Weihao Xuan, Qingcheng Zeng, Heli Qi, Junjue Wang, Naoto Yokoya

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

2505.16990 2025-05-27 cs.CV 83%

Dimple: Discrete Diffusion Multimodal Large Language Model with Parallel Decoding

Runpeng Yu, Xinyin Ma, Xinchao Wang

机构 * National University of Singapore（新加坡国立大学）

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

2410.03577 2025-05-09 cs.CV 83%

Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models

Xin Zou, Yizhou Wang, Yibo Yan, Yuanhuiyi Lyu, Kening Zheng, Sirui Huang, Junkai Chen, Peijie Jiang, Jia Liu, Chang Tang, Xuming Hu

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

Comments Accepted by ICML 2025

2505.02087 2025-05-06 cs.AI 83%

Retrieval-augmented in-context learning for multimodal large language models in disease classification

Zaifu Zhan, Shuang Zhou, Xiaoshan Zhou, Yongkang Xiao, Jun Wang, Jiawen Deng, He Zhu, Yu Hou, Rui Zhang

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

Comments 17 Pages, 1 figure, 7 tables

2505.01958 2025-05-06 cs.CV cs.CL 83%

A Comprehensive Analysis for Visual Object Hallucination in Large Vision-Language Models

Liqiang Jing, Guiming Hardy Chen, Ehsan Aghazadeh, Xin Eric Wang, Xinya Du

机构 * University of Texas at Dallas（德克萨斯大学达拉斯分校）； University of Massachusetts at Amherst（马萨诸塞大学阿姆赫斯特分校）； University of California, Santa Cruz（加州大学圣克鲁兹分校）

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

2405.20152 2025-05-01 cs.CV 83%

Uncovering Bias in Large Vision-Language Models at Scale with Counterfactuals

Phillip Howard, Kathleen C. Fraser, Anahita Bhiwandiwalla, Svetlana Kiritchenko

机构 * Intel Labs（英特尔实验室）； National Research Council Canada（加拿大国家研究理事会）

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

Comments Accepted to NAACL 2025 main track (oral)

2504.16134 2025-04-24 cs.CV cs.CL 83%

Multimodal Large Language Models for Enhanced Traffic Safety: A Comprehensive Review and Future Trends

Mohammad Abu Tami, Mohammed Elhenawy, Huthaifa I. Ashqar

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

2504.09083 2025-04-15 cs.CV 83%

Using Vision Language Models for Safety Hazard Identification in Construction

Muhammad Adil, Gaang Lee, Vicente A. Gonzalez, Qipei Mei

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

2504.08205 2025-04-14 cs.CV cs.CR 83%

EO-VLM: VLM-Guided Energy Overload Attacks on Vision Models

Minjae Seo, Myoungsung You, Junhee Lee, Jaehan Kim, Hwanjo Heo, Jintae Oh, Jinwoo Kim

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

Comments Presented as a poster at ACSAC 2024

2410.13146 2025-04-01 cs.CL cs.CV 83%

debiaSAE: Benchmarking and Mitigating Vision-Language Model Bias

Kuleen Sasse, Shan Chen, Jackson Pond, Danielle Bitterman, John Osborne

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

Comments Under Review at COLM 2025

2503.16566 2025-03-24 cs.CV 83%

REVAL: A Comprehension Evaluation on Reliability and Values of Large Vision-Language Models

Jie Zhang, Zheng Yuan, Zhongqi Wang, Bei Yan, Sibo Wang, Xiangkui Cao, Zonghui Guo, Shiguang Shan, Xilin Chen

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

Comments 45 pages, 5 figures, 18 tables

2503.15202 2025-03-24 cs.RO cs.AI 83%

A Unified Framework for Real-Time Failure Handling in Robotics Using Vision-Language Models, Reactive Planner and Behavior Trees

Faseeh Ahmad, Hashim Ismail, Jonathan Styrud, Maj Stenmark, Volker Krueger

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

2503.06903 2025-03-24 cs.CV 83%

When Lighting Deceives: Exposing Vision-Language Models' Illumination Vulnerability Through Illumination Transformation Attack

Hanqing Liu, Shouwei Ruan, Yao Huang, Shiji Zhao, Xingxing Wei

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

2503.11750 2025-03-18 cs.CV cs.CR 83%

Making Every Step Effective: Jailbreaking Large Vision-Language Models Through Hierarchical KV Equalization

Shuyang Hao, Yiwei Wang, Bryan Hooi, Jun Liu, Muhao Chen, Zi Huang, Yujun Cai

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

2412.03002 2025-03-11 cs.CV 83%

AdvDreamer Unveils: Are Vision-Language Models Truly Ready for Real-World 3D Variations?

Shouwei Ruan, Hanqing Liu, Yao Huang, Xiaoqi Wang, Caixin Kang, Hang Su, Yinpeng Dong, Xingxing Wei

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

2410.00982 2025-03-11 cs.CV 83%

ScVLM: Enhancing Vision-Language Model for Safety-Critical Event Understanding

Liang Shi, Boyu Jiang, Tong Zeng, Feng Guo

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

Comments To appear in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2025

Journal ref Proceedings of the Winter Conference on Applications of Computer Vision (WACV) Workshops, 2025, pp. 1061-1071

2503.05093 2025-03-10 cs.CV 83%

Visual Cues of Gender and Race are Associated with Stereotyping in Vision-Language Models

Messi H. J. Lee, Soyeon Jeon, Jacob M. Montgomery, Calvin K. Lai

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

2402.10340 2025-03-10 cs.RO cs.AI 83%

On the Vulnerability of LLM/VLM-Controlled Robotics

Xiyang Wu, Souradip Chakraborty, Ruiqi Xian, Jing Liang, Tianrui Guan, Fuxiao Liu, Brian M. Sadler, Dinesh Manocha, Amrit Singh Bedi

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

2502.16911 2025-02-25 cs.CV 83%

SPARC: Score Prompting and Adaptive Fusion for Zero-Shot Multi-Label Recognition in Vision-Language Models

Kevin Miller, Samarth Mishra, Aditya Gangrade, Kate Saenko, Venkatesh Saligrama

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

2501.06132 2025-01-13 cs.RO cs.AI cs.MA 83%

CoDriveVLM: VLM-Enhanced Urban Cooperative Dispatching and Motion Planning for Future Autonomous Mobility on Demand Systems

Haichao Liu, Ruoyu Yao, Wenru Liu, Zhenmin Huang, Shaojie Shen, Jun Ma

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

2412.02886 2024-12-17 cs.CV 83%

Patchfinder: Leveraging Visual Language Models for Accurate Information Retrieval using Model Uncertainty

Roman Colman, Minh Vu, Manish Bhattarai, Martin Ma, Hari Viswanathan, Daniel O'Malley, Javier E. Santos

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

Comments This paper has been accepted to IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2025

2412.07518 2024-12-11 cs.CV 83%

Hallucination Elimination and Semantic Enhancement Framework for Vision-Language Models in Traffic Scenarios

Jiaqi Fan, Jianhua Wu, Hongqing Chu, Quanbo Ge, Bingzhao Gao

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

2411.18000 2024-12-02 cs.CV 83%

Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models

Shuyang Hao, Bryan Hooi, Jun Liu, Kai-Wei Chang, Zi Huang, Yujun Cai

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

2410.22888 2024-10-31 cs.CV cs.CL cs.CR 83%

Effective and Efficient Adversarial Detection for Vision-Language Models via A Single Vector

Youcheng Huang, Fengbin Zhu, Jingkun Tang, Pan Zhou, Wenqiang Lei, Jiancheng Lv, Tat-Seng Chua

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

1. 幻觉与鲁棒性 2257 篇

VLMInferSlow: Evaluating the Efficiency Robustness of Large Vision-Language Models as a Service

From Street Views to Urban Science: Discovering Road Safety Factors with Multimodal Large Language Models

PARC: A Quantitative Framework Uncovering the Symmetries within Vision Language Models

NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples

Align is not Enough: Multimodal Universal Jailbreak Attack against Multimodal Large Language Models

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models

Seeing is Believing, but How Much? A Comprehensive Analysis of Verbalized Calibration in Vision-Language Models

Dimple: Discrete Diffusion Multimodal Large Language Model with Parallel Decoding

Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models

Retrieval-augmented in-context learning for multimodal large language models in disease classification

A Comprehensive Analysis for Visual Object Hallucination in Large Vision-Language Models

Uncovering Bias in Large Vision-Language Models at Scale with Counterfactuals

Multimodal Large Language Models for Enhanced Traffic Safety: A Comprehensive Review and Future Trends

Using Vision Language Models for Safety Hazard Identification in Construction

EO-VLM: VLM-Guided Energy Overload Attacks on Vision Models

debiaSAE: Benchmarking and Mitigating Vision-Language Model Bias

REVAL: A Comprehension Evaluation on Reliability and Values of Large Vision-Language Models

A Unified Framework for Real-Time Failure Handling in Robotics Using Vision-Language Models, Reactive Planner and Behavior Trees

When Lighting Deceives: Exposing Vision-Language Models' Illumination Vulnerability Through Illumination Transformation Attack

Making Every Step Effective: Jailbreaking Large Vision-Language Models Through Hierarchical KV Equalization

AdvDreamer Unveils: Are Vision-Language Models Truly Ready for Real-World 3D Variations?

ScVLM: Enhancing Vision-Language Model for Safety-Critical Event Understanding

Visual Cues of Gender and Race are Associated with Stereotyping in Vision-Language Models

On the Vulnerability of LLM/VLM-Controlled Robotics

SPARC: Score Prompting and Adaptive Fusion for Zero-Shot Multi-Label Recognition in Vision-Language Models

CoDriveVLM: VLM-Enhanced Urban Cooperative Dispatching and Motion Planning for Future Autonomous Mobility on Demand Systems

Patchfinder: Leveraging Visual Language Models for Accurate Information Retrieval using Model Uncertainty

Hallucination Elimination and Semantic Enhancement Framework for Vision-Language Models in Traffic Scenarios

Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models

Effective and Efficient Adversarial Detection for Vision-Language Models via A Single Vector