arXivDaily arXiv每日学术速递 周一至周五更新

AI 大模型

视觉大模型 / VLM

视觉语言模型、视觉推理、视觉问答、图文理解和视觉 grounding。

共收录 2260 信号源:cs.CV, cs.AI, cs.LG

1. 幻觉与鲁棒性 2260 篇

2509.04459 2026-01-21 cs.CL cs.LG 70%

Uncertainty-Aware Collaborative System of Large and Small Models for Multimodal Sentiment Analysis

面向大规模和小规模模型的不确定性感知协作系统用于多模态情感分析

Shiqin Han, Manning Gao, Menghua Jiang, Yuncheng Jiang, Haifeng Hu, Sijie Mai

机构 * School of Computer Science, South China Normal University(计算机科学学院,华南师范大学) School of Artificial Intelligence, South China Normal University(人工智能学院,华南师范大学) School of Electronics and Information Technology, Sun Yat-sen University(电子与信息工程学院,中山大学)

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

AI总结 本文提出U-ACS系统,通过整合UBM与MLLMs,利用不确定性感知机制提升多模态情感分析的效率与性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.05611 2026-01-19 cs.CL cs.AI 70%

MADIAVE: Multi-Agent Debate for Implicit Attribute Value Extraction

MADIAVE:多智能体辩论用于隐式属性值提取

Wei-Chieh Huang, Cornelia Caragea

机构 * University of Illinois Chicago(伊利诺伊大学芝加哥分校)

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

AI总结 MADIAVE通过多智能体辩论框架提升隐式属性值提取的准确性和鲁棒性,适用于多模态电子商务场景。

Comments Accepted by EACL 2026 (Findings)

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.06224 2026-01-14 cs.CV 70%

Ground What You See: Hallucination-Resistant MLLMs via Caption Feedback, Diversity-Aware Sampling, and Conflict Regularization

在所见之地接地:通过标题反馈、多样性感知采样和冲突正则化实现抗幻觉的MLLMs

Miao Pan, Wangjie Gan, Jintao Chen, Wenqi Zhang, Bing Sun, Jianwei Yin, Xuhong Zhang

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

AI总结 本文提出抗幻觉的MLLMs方法,通过标题反馈、多样性感知采样和冲突正则化减少幻觉,提升推理准确性。

Comments AAAI-2026 Poster

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.01592 2026-01-13 cs.CR cs.CV 70%

OpenRT: An Open-Source Red Teaming Framework for Multimodal LLMs

OpenRT: 一种用于多模态大语言模型的开源红队框架

Xin Wang, Yunhao Chen, Juncheng Li, Yixu Wang, Yang Yao, Tianle Gu, Jie Li, Yan Teng, Yingchun Wang, Xia Hu

机构 * Shanghai Artificial Intelligence Laboratory(上海人工智能实验室)

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

AI总结 OpenRT框架通过模块化设计和高吞吐量运行时,系统性评估多模态大语言模型的安全性,揭示了前沿模型在复杂攻击下的脆弱性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.03011 2026-01-07 cs.CV cs.MA 70%

ReCCur: A Recursive Corner-Case Curation Framework for Robust Vision-Language Understanding in Open and Edge Scenarios

ReCCur:一种递归角落案例校准框架,用于开放和边缘场景中的鲁棒视觉-语言理解

Yihan Wei, Shenghai Yuan, Tianchen Deng, Boyang Lou, Enwen Hu

机构 * Nanyang Technological University(南洋理工大学) Shanghai Jiao Tong University(上海交通大学) Beijing University of Posts and Telecommunications(北京邮电大学)

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

AI总结 ReCCur通过递归框架实现低计算量的角落案例校准,提升开放和边缘场景下的视觉-语言理解鲁棒性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.21699 2025-12-29 cs.AI 70%

Towards Responsible and Explainable AI Agents with Consensus-Driven Reasoning

迈向负责任和可解释的AI代理:基于共识驱动的推理

Eranga Bandara, Tharaka Hewa, Ross Gore, Sachin Shetty, Ravi Mukkamala, Peter Foytik, Abdul Rahman, Safdar H. Bouk, Xueping Liang, Amin Hass, Sachini Rajapakse, Ng Wee Keong, Kasun De Zoysa, Aruna Withanage, Nilaan Loganathan

机构 * Old Dominion University, Norfolk, VA, USA(老奥本大学) Center for Wireless Communications, University of Oulu, Finland(无线通信中心,奥卢大学) Florida International University, USA(佛罗里达国际大学) Nanyang Technological University, Singapore(南洋理工大学) University of Colombo, Sri Lanka(科伦坡大学) Accenture Technology Labs, Arlington, VA, USA(Accenture技术实验室)

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

AI总结 本文提出了一种基于多模型共识和推理层治理的负责任和可解释的AI代理架构,通过结构化整合不同模型的输出以提升系统鲁棒性、透明度和责任性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.15528 2025-12-22 cs.CV 70%

EmoCaliber: Advancing Reliable Visual Emotion Comprehension via Confidence Verbalization and Calibration

EmoCaliber: 通过置信度 verbalization 和校准推进可靠的视觉情绪理解

Daiqing Wu, Dongbao Yang, Can Ma, Yu Zhou

机构 * IIE, Chinese Academy of Sciences(中国科学院信息研究所) Nankai University(南开大学) University of Chinese Academy of Sciences(中国科学院大学)

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

AI总结 EmoCaliber通过置信度 verbalization 和校准提升视觉情绪理解的可靠性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.03087 2025-12-04 cs.MM cs.AI 70%

When Harmful Content Gets Camouflaged: Unveiling Perception Failure of LVLMs with CamHarmTI

当有害内容被伪装时:通过CamHarmTI揭示LVLMs的感知失败

Yanhui Li, Qi Zhou, Zhihong Xu, Huizhong Guo, Wenhai Wang, Dongxia Wang

机构 * Zhejiang University(浙江大学)

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

AI总结 本文提出CamHarmTI基准,揭示LVLMs在识别伪装有害内容时的感知不足,并通过微调提升模型性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.22777 2025-12-01 cs.RO cs.AI 70%

Improving Robotic Manipulation Robustness via NICE Scene Surgery

通过NICE场景手术提升机器人操作的鲁棒性

Sajjad Pakdamansavoji, Mozhgan Pourkeshavarz, Adam Sigal, Zhiyuan Li, Rui Heng Yang, Amir Rasouli

机构 * Huawei Technologies Canada(华为技术加拿大公司)

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

AI总结 NICE通过增强场景上下文减少分布外差距,提升机器人操作在复杂环境中的鲁棒性和安全性。

Comments 11 figures, 3 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.19834 2025-11-26 cs.CV 70%

Large Language Model Aided Birt-Hogg-Dube Syndrome Diagnosis with Multimodal Retrieval-Augmented Generation

基于多模态检索增强生成的大型语言模型辅助Birt-Hogg-Dube综合征诊断

Haoqing Li, Jun Shi, Xianmeng Chen, Qiwei Jia, Rui Wang, Wei Wei, Hong An, Xiaowen Hu

机构 * School of Computer Science and Technology(计算机科学与技术学院) Department of Pulmonary and Critical Care Medicine(呼吸与危重症医学科) Center for Diagnosis and Management of Rare Diseases(罕见病诊断与管理中心) the First Affiliated Hospital of USTC(USTC第一附属医院) Division of Life Sciences and Medicine(生命科学与医学系) USTC WanNan Medical College(皖南医学院)

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

AI总结 本研究提出BHD-RAG框架,通过整合多模态检索增强生成与领域专业知识,提升Birt-Hogg-Dube综合征的CT影像诊断准确性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.10510 2025-11-25 cs.NI cs.AI cs.HC cs.MM 70%

Chat with AI: The Surprising Turn of Real-time Video Communication from Human to AI

与AI聊天:从人类到AI的实时视频通信惊人转变

Jiangkai Wu, Zhiyuan Ren, Liming Liu, Xinggong Zhang

机构 * Peking University(北京大学)

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

AI总结 本文提出了一种面向AI的实时视频通信方法,通过上下文感知视频流技术降低延迟并提升AI理解视频的准确性。

Comments 9 pages, 10 figures, Proceedings of the 24th ACM Workshop on Hot Topics in Networks (HotNets 2025), College Park, Maryland, USA

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.23518 2025-11-25 cs.AI 70%

TRAP: Targeted Redirecting of Agentic Preferences

TRAP:面向目标的代理偏好重定向

Hangoo Kang, Jehyeok Yeon, Gagandeep Singh

机构 * University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)

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

AI总结 TRAP通过语义引导的跨模态操纵,诱导代理AI系统产生一致的选择偏见,揭示了语义层面的安全漏洞。

Comments Accepted to NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.06251 2025-11-18 cs.CV 70%

Physics Knowledge in Frontier Models: A Diagnostic Study of Failure Modes

Ieva Bagdonaviciute, Vibhav Vineet

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

Comments 8 pages, 7 figures. Preprint. v2: Updated experiments and diagnostics; formatting fixes

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.10074 2025-11-14 cs.CV cs.SY eess.SY 70%

VLF-MSC: Vision-Language Feature-Based Multimodal Semantic Communication System

Gwangyeon Ahn, Jiwan Seo, Joonhyuk Kang

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

Comments To appear in the AI4NextG Workshop at NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.09228 2025-11-13 cs.CV cs.CL 70%

Taming Object Hallucinations with Verified Atomic Confidence Estimation

Jiarui Liu, Weihao Xuan, Zhijing Jin, Mona Diab

机构 * CMU(卡内基梅隆大学) The University of Tokyo(东京大学) The University of Toronto(多伦多大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.04514 2025-11-07 cs.CL cs.CV 70%

DAMRO: Dive into the Attention Mechanism of LVLM to Reduce Object Hallucination

Xuan Gong, Tianshi Ming, Xinpeng Wang, Zhihua Wei

机构 * Department of Computer Science and Technology, Tongji University(计算机科学与技术系,同济大学)

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

Comments Accepted by EMNLP2024 (Main Conference), add GitHub link

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.00509 2025-11-04 cs.AI cs.CR 70%

Reimagining Safety Alignment with An Image

Yifan Xia, Guorui Chen, Wenqian Yu, Zhijiang Li, Philip Torr, Jindong Gu

机构 * School of Information Management, Wuhan University, Wuhan, China(武汉大学信息管理学院) Torr Vision Group, University of Oxford, Oxford, United Kingdom(牛津大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.10466 2025-10-14 cs.CV 70%

When Images Speak Louder: Mitigating Language Bias-induced Hallucinations in VLMs through Cross-Modal Guidance

Jinjin Cao, Zhiyang Chen, Zijun Wang, Liyuan Ma, Weijian Luo, Guojun Qi

机构 * MAPLE Lab, Westlake University(西溪大学MAPLE实验室)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.14670 2025-10-14 cs.HC cs.AI 70%

StreetLens: Enabling Human-Centered AI Agents for Neighborhood Assessment from Street View Imagery

Jina Kim, Leeje Jang, Yao-Yi Chiang, Guanyu Wang, Michelle C. Pasco

机构 * University of Minnesota(明尼苏达大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.01534 2025-10-06 cs.CV 70%

Toward a Holistic Evaluation of Robustness in CLIP Models

Weijie Tu, Weijian Deng, Tom Gedeon

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

Comments Accepted to IEEE TPAMI, extension of NeurIPS'23 work: A Closer Look at the Robustness of Contrastive Language-Image Pre-Training (CLIP)

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.20862 2025-10-01 cs.CV 70%

AVCD: Mitigating Hallucinations in Audio-Visual Large Language Models through Contrastive Decoding

Chaeyoung Jung, Youngjoon Jang, Joon Son Chung

机构 * Korea Advanced Institute of Science and Technology (KAIST)(韩国科学技术院)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.25177 2025-09-30 cs.CV 70%

Mitigating Hallucination in Multimodal LLMs with Layer Contrastive Decoding

Bingkui Tong, Jiaer Xia, Kaiyang Zhou

机构 * Mohamed bin Zayed University of Artificial Intelligence(莫扎德·本·扎耶德人工智能大学) Hong Kong Baptist University(香港 Baptist大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.21997 2025-09-29 cs.CV 70%

Exposing Hallucinations To Suppress Them: VLMs Representation Editing With Generative Anchors

Youxu Shi, Suorong Yang, Dong Liu

机构 * University of Science and Technology of China(中国科学技术大学) Nanjing University(南京大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.12521 2025-09-17 cs.LG 70%

Phi: Preference Hijacking in Multi-modal Large Language Models at Inference Time

Yifan Lan, Yuanpu Cao, Weitong Zhang, Lu Lin, Jinghui Chen

机构 * The Pennsylvania State University(宾夕法尼亚州立大学) The University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.06989 2025-08-29 cs.CR cs.CV 70%

Probabilistic Modeling of Jailbreak on Multimodal LLMs: From Quantification to Application

Wenzhuo Xu, Zhipeng Wei, Xiongtao Sun, Zonghao Ying, Deyue Zhang, Dongdong Yang, Xiangzheng Zhang, Quanchen Zou

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.14533 2025-08-12 cs.CV 70%

ArtiMuse: Fine-Grained Image Aesthetics Assessment with Joint Scoring and Expert-Level Understanding

Shuo Cao, Nan Ma, Jiayang Li, Xiaohui Li, Lihao Shao, Kaiwen Zhu, Yu Zhou, Yuandong Pu, Jiarui Wu, Jiaquan Wang, Bo Qu, Wenhai Wang, Yu Qiao, Dajuin Yao, Yihao Liu

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

Comments 43 pages, 31 figures, 13 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.17722 2025-07-24 cs.CV 70%

BetterCheck: Towards Safeguarding VLMs for Automotive Perception Systems

Malsha Ashani Mahawatta Dona, Beatriz Cabrero-Daniel, Yinan Yu, Christian Berger

机构 * University of Gothenburg(哥德堡大学) Chalmers University of Technology(查尔姆斯理工大学)

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

Comments Accepted in The IEEE International Conference on Intelligent Transportation Systems (ITSC)2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.19697 2025-07-18 cs.CV 70%

Prompt-driven Transferable Adversarial Attack on Person Re-Identification with Attribute-aware Textual Inversion

Yuan Bian, Min Liu, Yunqi Yi, Xueping Wang, Yaonan Wang

机构 * School of Artificial Intelligence and Robotics, Hunan University(湖南大学人工智能与机器人学院) National Engineering Research Center of Robot Visual Perception and Control Technology(机器人视觉感知与控制技术国家工程研究中心) College of Information Science and Engineering, Hunan Normal University(湖南师范大学信息科学与工程学院)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.12430 2025-07-14 cs.CR cs.CV 70%

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025

Zonghao Ying, Siyang Wu, Run Hao, Peng Ying, Shixuan Sun, Pengyu Chen, Junze Chen, Hao Du, Kaiwen Shen, Shangkun Wu, Jiwei Wei, Shiyuan He, Yang Yang, Xiaohai Xu, Ke Ma, Qianqian Xu, Qingming Huang, Shi Lin, Xun Wang, Changting Lin, Meng Han, Yilei Jiang, Siqi Lai, Yaozhi Zheng, Yifei Song, Xiangyu Yue, Zonglei Jing, Tianyuan Zhang, Zhilei Zhu, Aishan Liu, Jiakai Wang, Siyuan Liang, Xianglong Kong, Hainan Li, Junjie Mu, Haotong Qin, Yue Yu, Lei Chen, Felix Juefei-Xu, Qing Guo, Xinyun Chen, Yew Soon Ong, Xianglong Liu, Dawn Song, Alan Yuille, Philip Torr, Dacheng Tao

机构 * Beihang University(北航) Zhongguancun Laboratory(中关村实验室) Hefei Comprehensive National Science Center(合肥综合性国家科学中心) ETH Zürich(苏黎世联邦理工学院) Pengcheng Laboratory(鹏城实验室) Tsinghua University(清华大学) University of California, Berkeley(加州大学伯克利分校) Johns Hopkins University(约翰霍普金斯大学) University of Oxford(牛津大学) Meta Google Brain(谷歌脑) Nanyang Technological University(南洋理工大学) Aarhus University(哥本哈根大学) China University of Mining(中国矿业大学) University of Electronic Science(电子科学大学) School of Electronic, Electrical(电子、电气与通信工程学院) Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, CAS(智能信息处理国家重点实验室) School of Computer Science(计算机科学学院) Key Laboratory of Big Data Mining(大数据挖掘国家重点实验室) Zhejiang Gongshang University(浙江工商大学) Binjiang Institute of Zhejiang University(浙江大学滨江学院) Zhejiang University(浙江大学) The Chinese University of Hong Kong(香港中文大学)

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

Comments AdvML@CVPR Challenge Report

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.07731 2025-07-11 cs.CV 70%

Energy-Guided Decoding for Object Hallucination Mitigation

Xixi Liu, Ailin Deng, Christopher Zach

机构 * Chalmers University of Technology(查尔姆斯理工大学) National University of Singapore(新加坡国立大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏