视觉大模型 / VLM - arXivDaily 专题

2509.20119 2025-09-25 cs.CV 70%

A Simple Data Augmentation Strategy for Text-in-Image Scientific VQA

Belal Shoer, Yova Kementchedjhieva

机构 * MBZUAI（穆罕默德·本·拉希德智能研究院）

专题命中视觉问答：vision-language model(abstract)；visual question answering(abstract)；分类 cs.CV

Comments Accepted at WiNLP, 2025

2509.09254 2025-09-12 cs.CV cs.MM 70%

Towards Better Dental AI: A Multimodal Benchmark and Instruction Dataset for Panoramic X-ray Analysis

Jing Hao, Yuxuan Fan, Yanpeng Sun, Kaixin Guo, Lizhuo Lin, Jinrong Yang, Qi Yong H. Ai, Lun M. Wong, Hao Tang, Kuo Feng Hung

机构 * Faculty of Dentistry, The University of Hong Kong（香港大学牙科学院）； The Hong Kong University of Science and Technology (GZ)（香港科学与技术大学）； National University of Singapore（新加坡国立大学）； CVTE ； Sun Yat-sen University（孙中山大学）； Department of Diagnostic Radiology, The University of Hong Kong（香港大学放射科）； Imaging and Interventional Radiology, Faculty of Medicine, The Chinese University of Hong Kong（香港中文大学医学院影像与介入放射科）； School of Computer Science, Peking University（北京大学计算机科学系）

专题命中视觉问答：vision-language model(abstract)；visual question answering(abstract)；分类 cs.CV

Comments 40 pages, 26 figures, 9 tables

2509.02164 2025-09-03 cs.CV 70%

Omnidirectional Spatial Modeling from Correlated Panoramas

Xinshen Zhang, Tongxi Fu, Xu Zheng

机构 * The Hong Kong Polytechnic University（香港理工大学）； Zhejiang Sci-Tech University（浙江科技学院）

专题命中视觉问答：visual question answering(abstract)；MLLM(abstract)；分类 cs.CV

2508.16652 2025-08-28 cs.CV 70%

Do VLMs Have Bad Eyes? Diagnosing Compositional Failures via Mechanistic Interpretability

Ashwath Vaithinathan Aravindan, Abha Jha, Mihir Kulkarni

机构 * University of Southern California（南加州大学）

专题命中视觉问答：vision-language model(abstract)；visual question answering(abstract)；分类 cs.CV

Comments To be published in Explainable Computer Vision: Quo Vadis? workshop at ICCV'25

2507.05520 2025-08-27 cs.AI 70%

Architecting Clinical Collaboration: Multi-Agent Reasoning Systems for Multimodal Medical VQA

Karishma Thakrar, Shreyas Basavatia, Akshay Daftardar

机构 * Georgia Institute of Technology Atlanta, GA, USA（佐治亚理工学院）

专题命中视觉问答：vision-language model(abstract)；visual question answering(abstract)；分类 cs.AI

2508.13192 2025-08-20 eess.IV cs.CV 70%

Benchmarking GPT-5 for Zero-Shot Multimodal Medical Reasoning in Radiology and Radiation Oncology

Mingzhe Hu, Zach Eidex, Shansong Wang, Mojtaba Safari, Qiang Li, Xiaofeng Yang

专题命中视觉问答：visual question answering(abstract)；grounding(abstract)；分类 cs.CV

2508.13086 2025-08-19 cs.CV 70%

Checkmate: interpretable and explainable RSVQA is the endgame

Lucrezia Tosato, Christel Tartini Chappuis, Syrielle Montariol, Flora Weissgerber, Sylvain Lobry, Devis Tuia

专题命中视觉问答：visual reasoning(abstract)；visual question answering(abstract)；分类 cs.CV

2508.11975 2025-08-19 cs.AI 70%

Chart-CoCa: Self-Improving Chart Understanding of Vision LMs via Code-Driven Synthesis and Candidate-Conditioned Answering

Gongyao Jiang, Qiong Luo

机构 * The Hong Kong University of Science

专题命中视觉问答：vision language model(abstract)；VLM(abstract)；分类 cs.AI

Comments Accepted to CIKM 2025

2508.06496 2025-08-12 cs.CV cs.MA 70%

Med-GRIM: Enhanced Zero-Shot Medical VQA using prompt-embedded Multimodal Graph RAG

Rakesh Raj Madavan, Akshat Kaimal, Hashim Faisal, Chandrakala S

机构 * Shiv Nadar University Chennai（施瓦斯纳大学钦奈）

专题命中视觉问答：vision-language model(abstract)；visual question answering(abstract)；分类 cs.CV

2504.07454 2025-08-06 cs.CV 70%

How Can Objects Help Video-Language Understanding?

Zitian Tang, Shijie Wang, Junho Cho, Jaewook Yoo, Chen Sun

机构 * Brown University（布朗大学）； Samsung Electronics（三星电子）

专题命中视觉问答：multimodal large language model(abstract)；MLLM(abstract)；分类 cs.CV

2508.01546 2025-08-05 cs.CV 70%

E-VRAG: Enhancing Long Video Understanding with Resource-Efficient Retrieval Augmented Generation

Zeyu Xu, Junkang Zhang, Qiang Wang, Yi Liu

机构 * Zeyu Xu（作者）； Junkang Zhang（作者）； Qiang Wang（作者）； Yi Liu（作者）

专题命中视觉问答：vision-language model(abstract)；VLM(abstract)；分类 cs.CV

2508.01274 2025-08-05 cs.AI cs.CL 70%

Multi-TW: Benchmarking Multimodal Models on Traditional Chinese Question Answering in Taiwan

Jui-Ming Yao, Bing-Cheng Xie, Sheng-Wei Peng, Hao-Yuan Chen, He-Rong Zheng, Bing-Jia Tan, Peter Shaojui Wang, Shun-Feng Su

机构 * National Taiwan University of Science and Technology（台湾科技大学）； University of London（伦敦大学）； National Taiwan University（台湾大学）

专题命中视觉问答：vision-language model(abstract)；multimodal large language model(abstract)；分类 cs.AI

2503.06271 2025-08-05 cs.CV 70%

SplatTalk: 3D VQA with Gaussian Splatting

Anh Thai, Songyou Peng, Kyle Genova, Leonidas Guibas, Thomas Funkhouser

机构 * Georgia Institute of Technology（佐治亚理工学院）； Google DeepMind（谷歌DeepMind）

专题命中视觉问答：vision-language model(abstract)；visual question answering(abstract)；分类 cs.CV

Comments Accepted at ICCV 2025

2507.13411 2025-07-21 cs.CL cs.AI 70%

Aligning Knowledge Graphs and Language Models for Factual Accuracy

Nur A Zarin Nishat, Andrea Coletta, Luigi Bellomarini, Kossi Amouzouvi, Jens Lehmann, Sahar Vahdati

机构 * TIB – Leibniz Information Centre for Science and Technology（莱比锡信息科学与技术研究中心）； Amazon, Germany（亚马逊公司）

专题命中视觉问答：LLaVA(abstract)；grounding(abstract)；分类 cs.AI

2502.05928 2025-07-14 cs.CV 70%

ClinKD: Cross-Modal Clinical Knowledge Distiller For Multi-Task Medical Images

Hongyu Ge, Longkun Hao, Zihui Xu, Zhenxin Lin, Bin Li, Shoujun Zhou, Hongjin Zhao, Yihang Liu

机构 * The Hong Kong University of Sciences and Technology, Guangzhou（香港科学与技术大学（广州））； Beihang University（北航大学）； Shandong University（山东大学）； Hubei University（湖北大学）； Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究所）； Australian National University（澳大利亚国立大学）

专题命中视觉问答：visual question answering(abstract)；multimodal large language model(abstract)；分类 cs.CV

2507.07902 2025-07-11 cs.CV 70%

MIRA: A Novel Framework for Fusing Modalities in Medical RAG

Jinhong Wang, Tajamul Ashraf, Zongyan Han, Jorma Laaksonen, Rao Mohammad Anwer

机构 * Department of Computer Vision, MBZUAI（视觉计算系，MBZUAI）； Department of Computer Science, Aalto University（计算机科学系，阿alto大学）

专题命中视觉问答：multimodal large language model(abstract)；MLLM(abstract)；分类 cs.CV

Comments ACM Multimedia 2025

2507.07079 2025-07-10 cs.CV 70%

Evaluating Attribute Confusion in Fashion Text-to-Image Generation

Ziyue Liu, Federico Girella, Yiming Wang, Davide Talon

机构 * University of Verona（威尼斯大学）； Polytechnic University of Turin（都灵理工大学）； Fondazione Bruno Kessler（布鲁诺·科塞勒基金会）

专题命中视觉问答：vision-language model(abstract)；visual question answering(abstract)；分类 cs.CV

Comments Accepted to ICIAP25. Project page: site [https://intelligolabs.github.io/L-VQAScore/\

2412.15484 2025-07-08 cs.CV 70%

Toward Robust Hyper-Detailed Image Captioning: A Multiagent Approach and Dual Evaluation Metrics for Factuality and Coverage

Saehyung Lee, Seunghyun Yoon, Trung Bui, Jing Shi, Sungroh Yoon

机构 * Department of Electrical and Computer Engineering, Seoul National University（电气与计算机工程系，首尔国立大学）； Interdisciplinary Program in Artificial Intelligence, Seoul National University（人工智能交叉学科项目，首尔国立大学）； Adobe Research（Adobe研究）

专题命中视觉问答：multimodal large language model(abstract)；MLLM(abstract)；分类 cs.CV

Comments ICML 2025

2507.02001 2025-07-04 cs.LG 70%

Temporal Chain of Thought: Long-Video Understanding by Thinking in Frames

Anurag Arnab, Ahmet Iscen, Mathilde Caron, Alireza Fathi, Cordelia Schmid

机构 * Google DeepMind（谷歌DeepMind）

专题命中视觉问答：vision-language model(abstract)；VLM(abstract)；分类 cs.LG

2506.17664 2025-06-24 cs.CV 70%

MDSAM:Memory-Driven Sparse Attention Matrix for LVLMs Hallucination Mitigation

Shuaiye Lu, Linjiang Zhou, Xiaochuan Shi

机构 * Wuhan University（武汉大学）

专题命中视觉问答：vision-language model(abstract)；visual question answering(abstract)；分类 cs.CV

2506.07837 2025-06-10 cs.AI 70%

HAIBU-ReMUD: Reasoning Multimodal Ultrasound Dataset and Model Bridging to General Specific Domains

Shijie Wang, Yilun Zhang, Zeyu Lai, Dexing Kong

机构 * School of Mathematical Sciences, Zhejiang University（浙江大学数学科学学院）

专题命中视觉问答：visual question answering(abstract)；multimodal large language model(abstract)；分类 cs.AI

2506.06279 2025-06-09 cs.CV 70%

CoMemo: LVLMs Need Image Context with Image Memory

Shi Liu, Weijie Su, Xizhou Zhu, Wenhai Wang, Jifeng Dai

机构 * Shi Liu ； Weijie Su ； Xizhou Zhu ； Wenhai Wang ； Jifeng Dai

专题命中视觉问答：vision-language model(abstract)；visual question answering(abstract)；分类 cs.CV

Comments ICML 2025

2503.18034 2025-06-02 cs.CV cs.CL 70%

Expanding the Boundaries of Vision Prior Knowledge in Multi-modal Large Language Models

Qiao Liang, Yanjiang Liu, Weixiang Zhou, Ben He, Yaojie Lu, Hongyu Lin, Jia Zheng, Xianpei Han, Le Sun, Yingfei Sun

机构 * University of Chinese Academy of Sciences（中国科学院大学）； Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所信息处理实验室）

专题命中视觉问答：visual question answering(abstract)；MLLM(abstract)；分类 cs.CV

2504.13199 2025-05-28 cs.CR cs.AI 70%

Building Trustworthy Multimodal AI: A Review of Fairness, Transparency, and Ethics in Vision-Language Tasks

Mohammad Saleh, Azadeh Tabatabaei

专题命中视觉问答：vision-language model(abstract)；visual question answering(abstract)；分类 cs.AI

Journal ref International Journal of Web Research, vol.8, no.2,pp.11-24, 2025,

2505.15529 2025-05-22 cs.CV 70%

Clapper: Compact Learning and Video Representation in VLMs

Lingyu Kong, Hongzhi Zhang, Jingyuan Zhang, Jianzhao Huang, Kunze Li, Qi Wang, Fuzheng Zhang

机构 * University of Chinese Academy of Sciences（中国科学院大学）； Kuaishou Technology（快手科技）； Xi’an Jiaotong University（西安交通大学）

专题命中视觉问答：vision-language model(abstract)；VLM(abstract)；分类 cs.CV

2409.15477 2025-05-22 cs.CV 70%

MediConfusion: Can you trust your AI radiologist? Probing the reliability of multimodal medical foundation models

Mohammad Shahab Sepehri, Zalan Fabian, Maryam Soltanolkotabi, Mahdi Soltanolkotabi

机构 * Department of Electrical and Computer Engineering, University of Southern California（电气与计算机工程系，南加州大学）； Department of Radiology and Imaging Sciences, University of Utah（放射学与影像科学系，犹他大学）

专题命中视觉问答：visual question answering(abstract)；multimodal large language model(abstract)；分类 cs.CV

Comments 24 Pages, 9 figures, The Thirteenth International Conference on Learning Representations (ICLR) 2025

2505.14627 2025-05-21 cs.AI cs.CL 70%

Debating for Better Reasoning: An Unsupervised Multimodal Approach

Ashutosh Adhikari, Mirella Lapata

专题命中视觉问答：vision-language model(abstract)；visual question answering(abstract)；分类 cs.AI

2505.02413 2025-05-06 cs.AI 70%

Task-Oriented Semantic Communication in Large Multimodal Models-based Vehicle Networks

Baoxia Du, Hongyang Du, Dusit Niyato, Ruidong Li

机构 * Institute of Science and Engineering, Kanazawa University（金泽大学科学与工程研究所）； Department of Electrical and Electronic Engineering, University of Hong Kong（香港大学电子与电气工程系）； College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）

专题命中视觉问答：LLaVA(abstract)；visual question answering(abstract)；分类 cs.AI

2504.09809 2025-04-23 cs.HC cs.AI 70%

See or Recall: A Sanity Check for the Role of Vision in Solving Visualization Question Answer Tasks with Multimodal LLMs

Zhimin Li, Haichao Miao, Xinyuan Yan, Valerio Pascucci, Matthew Berger, Shusen Liu

机构 * Vanderbilt University（范德比大学）； Lawrence Livermore National Laboratory（劳伦斯利弗莫尔国家实验室）； University of Utah（犹他大学）

专题命中视觉问答：multimodal large language model(abstract)；MLLM(abstract)；分类 cs.AI

2504.07556 2025-04-11 cs.CV 70%

TokenFocus-VQA: Enhancing Text-to-Image Alignment with Position-Aware Focus and Multi-Perspective Aggregations on LVLMs

Zijian Zhang, Xuhui Zheng, Xuecheng Wu, Chong Peng, Xuezhi Cao

专题命中视觉问答：vision-language model(abstract)；visual question answering(abstract)；分类 cs.CV

Comments 10 pages, 3 figures

1. 视觉问答 3148 篇

A Simple Data Augmentation Strategy for Text-in-Image Scientific VQA

Towards Better Dental AI: A Multimodal Benchmark and Instruction Dataset for Panoramic X-ray Analysis

Omnidirectional Spatial Modeling from Correlated Panoramas

Do VLMs Have Bad Eyes? Diagnosing Compositional Failures via Mechanistic Interpretability

Architecting Clinical Collaboration: Multi-Agent Reasoning Systems for Multimodal Medical VQA

Benchmarking GPT-5 for Zero-Shot Multimodal Medical Reasoning in Radiology and Radiation Oncology

Checkmate: interpretable and explainable RSVQA is the endgame

Chart-CoCa: Self-Improving Chart Understanding of Vision LMs via Code-Driven Synthesis and Candidate-Conditioned Answering

Med-GRIM: Enhanced Zero-Shot Medical VQA using prompt-embedded Multimodal Graph RAG

How Can Objects Help Video-Language Understanding?

E-VRAG: Enhancing Long Video Understanding with Resource-Efficient Retrieval Augmented Generation

Multi-TW: Benchmarking Multimodal Models on Traditional Chinese Question Answering in Taiwan

SplatTalk: 3D VQA with Gaussian Splatting

Aligning Knowledge Graphs and Language Models for Factual Accuracy

ClinKD: Cross-Modal Clinical Knowledge Distiller For Multi-Task Medical Images

MIRA: A Novel Framework for Fusing Modalities in Medical RAG

Evaluating Attribute Confusion in Fashion Text-to-Image Generation

Toward Robust Hyper-Detailed Image Captioning: A Multiagent Approach and Dual Evaluation Metrics for Factuality and Coverage

Temporal Chain of Thought: Long-Video Understanding by Thinking in Frames

MDSAM:Memory-Driven Sparse Attention Matrix for LVLMs Hallucination Mitigation

HAIBU-ReMUD: Reasoning Multimodal Ultrasound Dataset and Model Bridging to General Specific Domains

CoMemo: LVLMs Need Image Context with Image Memory

Expanding the Boundaries of Vision Prior Knowledge in Multi-modal Large Language Models

Building Trustworthy Multimodal AI: A Review of Fairness, Transparency, and Ethics in Vision-Language Tasks

Clapper: Compact Learning and Video Representation in VLMs

MediConfusion: Can you trust your AI radiologist? Probing the reliability of multimodal medical foundation models

Debating for Better Reasoning: An Unsupervised Multimodal Approach

Task-Oriented Semantic Communication in Large Multimodal Models-based Vehicle Networks

See or Recall: A Sanity Check for the Role of Vision in Solving Visualization Question Answer Tasks with Multimodal LLMs

TokenFocus-VQA: Enhancing Text-to-Image Alignment with Position-Aware Focus and Multi-Perspective Aggregations on LVLMs