视觉大模型 / VLM

2509.17664 2025-09-23 cs.CV cs.AI 88%

SD-VLM: Spatial Measuring and Understanding with Depth-Encoded Vision-Language Models

Pingyi Chen, Yujing Lou, Shen Cao, Jinhui Guo, Lubin Fan, Yue Wu, Lin Yang, Lizhuang Ma, Jieping Ye

机构 * Zhejiang University（浙江大学）； Westlake University（西湖大学）； Alibaba Cloud Computing（阿里云 computing）； Shanghai Jiao Tong University（上海交通大学）

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

Comments Accepted by NeurIPS 2025

2509.16680 2025-09-23 cs.CV cs.AI cs.LG 87%

ProtoVQA: An Adaptable Prototypical Framework for Explainable Fine-Grained Visual Question Answering

Xingjian Diao, Weiyi Wu, Keyi Kong, Peijun Qing, Xinwen Xu, Ming Cheng, Soroush Vosoughi, Jiang Gui

机构 * Dartmouth College（达特茅斯学院）； Shandong University（山东大学）； Harvard University（哈佛大学）

专题命中视觉问答：visual question answering(title,abstract)；visual reasoning(abstract)；grounding(abstract)；分类 cs.CV、cs.AI、cs.LG

Comments Accepted to EMNLP 2025 Main Conference

2509.17588 2025-09-23 cs.CV cs.AI cs.LG 85%

Interpreting Attention Heads for Image-to-Text Information Flow in Large Vision-Language Models

Jinyeong Kim, Seil Kang, Jiwoo Park, Junhyeok Kim, Seong Jae Hwang

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

2509.16633 2025-09-23 cs.CV cs.AI cs.CL 84%

When Big Models Train Small Ones: Label-Free Model Parity Alignment for Efficient Visual Question Answering using Small VLMs

Abhirama Subramanyam Penamakuri, Navlika Singh, Piyush Arora, Anand Mishra

机构 * Indian Institute of Technology Jodhpur（印度理工学院朱诺尔）

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

Comments Accepted to EMNLP (Main) 2025

2509.16628 2025-09-23 cs.CV 83%

Enhancing Scientific Visual Question Answering via Vision-Caption aware Supervised Fine-Tuning

Janak Kapuriya, Anwar Shaikh, Arnav Goel, Medha Hira, Apoorv Singh, Jay Saraf, Sanjana, Vaibhav Nauriyal, Avinash Anand, Zhengkui Wang, Rajiv Ratn Shah

机构 * Indraprastha Institute of Information Technology, Delhi（印度德里印度理工学院）； Singapore Institute of Technology（新加坡理工学院）

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

2503.18172 2025-09-23 cs.CL cs.AI 83%

Unmasking Deceptive Visuals: Benchmarking Multimodal Large Language Models on Misleading Chart Question Answering

Zixin Chen, Sicheng Song, Kashun Shum, Yanna Lin, Rui Sheng, Weiqi Wang, Huamin Qu

机构 * The Hong Kong University of Science and Technology（香港科学与技术大学）

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

Comments 34 pages in total, EMNLP 2025

2406.17974 2025-09-23 cs.CL cs.CV 79%

Evaluating Fairness in Large Vision-Language Models Across Diverse Demographic Attributes and Prompts

Xuyang Wu, Yuan Wang, Hsin-Tai Wu, Zhiqiang Tao, Yi Fang

机构 * Santa Clara University（圣克拉拉大学）； DOCOMO Innovations, Inc.（DOCOMO创新公司）； Rochester Institute of Technology（罗切斯特理工学院）

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

Comments EMNLP Findings

2509.16476 2025-09-23 cs.CV 77%

Eye Gaze Tells You Where to Compute: Gaze-Driven Efficient VLMs

Qinyu Chen, Jiawen Qi

机构 * Leiden Institute of Advanced Computer Science (LIACS)（莱顿先进计算机科学研究所）

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

Comments 11 pages

2509.16618 2025-09-23 cs.CV cs.AI 76%

Surgical-MambaLLM: Mamba2-enhanced Multimodal Large Language Model for VQLA in Robotic Surgery

Pengfei Hao, Hongqiu Wang, Shuaibo Li, Zhaohu Xing, Guang Yang, Kaishun Wu, Lei Zhu

机构 * Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州））； Imperial College London（帝国理工学院伦敦分校）； The Hong Kong University of Science and Technology（香港科学与技术大学）

专题命中视觉问答：multimodal large language model(title)；分类 cs.CV、cs.AI

Comments Early accepted by MICCAI2025

2411.03823 2025-09-23 cs.CV cs.AI cs.CL cs.MM 73%

Both Text and Images Leaked! A Systematic Analysis of Data Contamination in Multimodal LLM

Dingjie Song, Sicheng Lai, Mingxuan Wang, Shunian Chen, Lichao Sun, Benyou Wang

机构 * Lehigh University（莱维大学）； The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））

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

Comments Accepted to EMNLP 2025 Findings

2509.17961 2025-09-23 cs.CL 50%

Bringing Pedagogy into Focus: Evaluating Virtual Teaching Assistants' Question-Answering in Asynchronous Learning Environments

Li Siyan, Zhen Xu, Vethavikashini Chithrra Raghuram, Xuanming Zhang, Renzhe Yu, Zhou Yu

机构 * Columbia University（哥伦比亚大学）

专题命中视觉问答：grounding(abstract)

Comments Accepted in EMNLP 2025 Findings

2509.16517 2025-09-23 cs.CV cs.AI cs.CL cs.MM 91%

Seeing Culture: A Benchmark for Visual Reasoning and Grounding

Burak Satar, Zhixin Ma, Patrick A. Irawan, Wilfried A. Mulyawan, Jing Jiang, Ee-Peng Lim, Chong-Wah Ngo

机构 * Singapore Management University（新加坡管理大学）； Bandung Institute of Technology（班达理工大学）

专题命中视觉推理：visual reasoning(title,abstract)；grounding(title,abstract)；vision-language model(abstract)；visual question answering(abstract)

Comments Accepted to EMNLP 2025 Main Conference, https://seeingculture-benchmark.github.io/

2509.17042 2025-09-23 cs.RO 82%

Orchestrate, Generate, Reflect: A VLM-Based Multi-Agent Collaboration Framework for Automated Driving Policy Learning

Zengqi Peng, Yusen Xie, Yubin Wang, Rui Yang, Qifeng Chen, Jun Ma

机构 * Robotics and Autonomous Systems Thrust, The Hong Kong University of Science and Technology (Guangzhou)（机器人与自主系统方向，香港科学与技术大学（广州））； Department of Computer Science and Engineering, The Hong Kong University of Science and Technology（计算机科学与工程系，香港科学与技术大学）； Cheng Kar-Shun Robotics Institute, The Hong Kong University of Science and Technology（陈家骏机器人研究所，香港科学与技术大学）

专题命中视觉推理：VLM(title,abstract)；vision-language model(abstract)

2507.05255 2025-09-23 cs.CV cs.CL 79%

Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning

Yana Wei, Liang Zhao, Jianjian Sun, Kangheng Lin, Jisheng Yin, Jingcheng Hu, Yinmin Zhang, En Yu, Haoran Lv, Zejia Weng, Jia Wang, Chunrui Han, Yuang Peng, Qi Han, Zheng Ge, Xiangyu Zhang, Daxin Jiang, Vishal M. Patel

机构 * Johns Hopkins University（约翰霍普金斯大学）； StepFun ； BUPT（北京邮电大学）； UCAS（中国科学院大学）； THU（清华大学）； HUST（华中科技大学）

专题命中视觉推理：visual reasoning(title,abstract)；分类 cs.CV

Comments NeurIPS 2025

2505.20024 2025-09-23 cs.CV cs.AI cs.RO 73%

ReasonPlan: Unified Scene Prediction and Decision Reasoning for Closed-loop Autonomous Driving

Xueyi Liu, Zuodong Zhong, Yuxin Guo, Yun-Fu Liu, Zhiguo Su, Qichao Zhang, Junli Wang, Yinfeng Gao, Yupeng Zheng, Qiao Lin, Huiyong Chen, Dongbin Zhao

机构 * SKL-MAIS, Institute of Automation, Chinese Academy of Sciences, Beijing, China（中国科学院自动化研究所SKL-MAIS部门，北京）； School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China（中国科学院大学人工智能学院，北京）； EACON, Fujian, China（福建EACON机构，中国）； School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, China（北京科技大学自动化与电气工程学院）

专题命中视觉推理：multimodal large language model(abstract)；MLLM(abstract)；分类 cs.CV、cs.AI

Comments 18 pages; 9 figures; https://github.com/Liuxueyi/ReasonPlan

2509.16597 2025-09-23 cs.CL 71%

MCP: A Control-Theoretic Orchestration Framework for Synergistic Efficiency and Interpretability in Multimodal Large Language Models

Luyan Zhang

机构 * Northeastern University（东北大学）

专题命中视觉推理：multimodal large language model(title)

Comments 13 pages, 6 figures, 2 tables

2509.17437 2025-09-23 cs.CL 67%

GeoPQA: Bridging the Visual Perception Gap in MLLMs for Geometric Reasoning

Guizhen Chen, Weiwen Xu, Hao Zhang, Hou Pong Chan, Deli Zhao, Anh Tuan Luu, Yu Rong

机构 * Nanyang Technological University（南洋理工大学）； DAMO Academy, Alibaba Group（阿里达摩院）； Hupan Lab（华普实验室）

专题命中视觉推理：grounding(abstract)；MLLM(abstract)

Comments Accepted to EMNLP2025 Findings

2502.16989 2025-09-23 cs.CL 67%

All-in-one: Understanding and Generation in Multimodal Reasoning with the MAIA Benchmark

Davide Testa, Giovanni Bonetta, Raffaella Bernardi, Alessandro Bondielli, Alessandro Lenci, Alessio Miaschi, Lucia Passaro, Bernardo Magnini

机构 * Università di Roma La Sapienza（罗马La Sapienza大学）； Fondazione Bruno Kessler (FBK)（布鲁诺·凯斯勒基金会）； Free University of Bozen-Bolzano（博兹纳-博尔扎诺自由大学）； Dept. of Computer Science, University of Pisa（比萨大学计算机科学系）； CoLing Lab, Dept. of Philology, Literature and Linguistics, University of Pisa（比萨大学语言学、文学与语言学系CoLing实验室）； Istituto di Linguistica Computazionale "A. Zampolli" (CNR-ILC), ItaliaNLP Lab, Pisa（A. Zampolli计算语言学研究所（CNR-ILC），意大利NLP实验室，比萨）

专题命中视觉推理：vision language model(abstract)；visual language model(abstract)

Comments Accepted at Findings of EMNLP 2025

2509.16721 2025-09-23 cs.CV cs.AI cs.RO 62%

Text-Scene: A Scene-to-Language Parsing Framework for 3D Scene Understanding

Haoyuan Li, Rui Liu, Hehe Fan, Yi Yang

机构 * College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）

专题命中视觉推理：multimodal large language model(abstract)；分类 cs.CV、cs.AI

Comments 19 pages, 12 figures, 6 tables

2509.15293 2025-09-23 cs.CV cs.RO 57%

How Good are Foundation Models in Step-by-Step Embodied Reasoning?

Dinura Dissanayake, Ahmed Heakl, Omkar Thawakar, Noor Ahsan, Ritesh Thawkar, Ketan More, Jean Lahoud, Rao Anwer, Hisham Cholakkal, Ivan Laptev, Fahad Shahbaz Khan, Salman Khan

机构 * Mohamed bin Zayed University of AI（穆罕默德·本·扎耶德人工智能大学）； Linköping University（林雪平大学）； Australian National University（澳大利亚国立大学）

专题命中视觉推理：grounding(abstract)；分类 cs.CV

Comments Project page: https://mbzuai-oryx.github.io/FoMER-Bench/

2509.17740 2025-09-23 cs.CV cs.CL 57%

WISE: Weak-Supervision-Guided Step-by-Step Explanations for Multimodal LLMs in Image Classification

Yiwen Jiang, Deval Mehta, Siyuan Yan, Yaling Shen, Zimu Wang, Zongyuan Ge

机构 * Faculty of Engineering, Monash University（墨尔本大学工程学院）； AIM for Health Lab, Faculty of IT, Monash University（墨尔本大学信息技术学院健康人工智能实验室）

专题命中视觉推理：multimodal large language model(abstract)；分类 cs.CV

Comments Accepted at EMNLP 2025 (Main)

2509.17044 2025-09-23 cs.CV 57%

AgriDoctor: A Multimodal Intelligent Assistant for Agriculture

Mingqing Zhang, Zhuoning Xu, Peijie Wang, Rongji Li, Liang Wang, Qiang Liu, Jian Xu, Xuyao Zhang, Shu Wu, Liang Wang

机构 * State Key Laboratory of Multimodal Artificial Intelligence Systems（多模态人工智能系统国家重点实验室）； Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）； School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）

专题命中视觉推理：vision-language model(abstract)；分类 cs.CV

2509.16226 2025-09-23 cs.CL cs.AI 57%

On LLM-Based Scientific Inductive Reasoning Beyond Equations

Brian S. Lin, Jiaxin Yuan, Zihan Zhou, Shouli Wang, Shuo Wang, Cunliang Kong, Qi Shi, Yuxuan Li, Liner Yang, Zhiyuan Liu, Maosong Sun

机构 * Dept. of Comp. Sci. & Tech., Institute for AI, BNRist Center, Tsinghua University（计算机科学与技术系，人工智能研究院，BNRist中心，清华大学）； Jiangsu Collaborative Innovation Center for Language Ability, Jiangsu Normal University（江苏语言能力协同创新中心，江苏师范大学）； Beijing Language and Culture University（北京语言文化大学）； Xiamen University（厦门大学）； Harbin Institute of Technology（哈尔滨工业大学）

专题命中视觉推理：grounding(abstract)；分类 cs.AI

Comments 24 pages

2506.21188 2025-09-23 cs.CV 79%

GroundFlow: A Plug-in Module for Temporal Reasoning on 3D Point Cloud Sequential Grounding

Zijun Lin, Shuting He, Cheston Tan, Bihan Wen

机构 * Nanyang Technological University（南洋理工大学）； Centre for Frontier AI Research, A*STAR（前沿人工智能研究中心，A*STAR）； MoE Key Laboratory of Interdisciplinary Research of Computation and Economics, Shanghai University of Finance and Economics（计算与经济学交叉研究关键实验室，上海财经大学）

专题命中视觉定位与Grounding ：grounding(title,abstract)；分类 cs.CV

2506.16806 2025-09-23 cs.CV 79%

FOCUS: Unified Vision-Language Modeling for Interactive Editing Driven by Referential Segmentation

Fan Yang, Yousong Zhu, Xin Li, Yufei Zhan, Hongyin Zhao, Shurong Zheng, Yaowei Wang, Ming Tang, Jinqiao Wang

机构 * Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所基础模型研究中心）； School of Artificial Intelligence, University of Chinese Academy of Science（中国科学院大学人工智能学院）； Peng Cheng Laboratory, Shenzhen, China（鹏城实验室）； Wuhan AI Research, Wuhan, China（武汉人工智能研究所）

专题命中视觉定位与Grounding ：vision-language model(title)；vision language model(abstract)；分类 cs.CV

2509.16534 2025-09-23 cs.CL cs.AI 79%

InteGround: On the Evaluation of Verification and Retrieval Planning in Integrative Grounding

Cheng Jiayang, Qianqian Zhuang, Haoran Li, Chunkit Chan, Xin Liu, Lin Qiu, Yangqiu Song

机构 * The Hong Kong University of Science and Technology（香港科学与技术大学）； Shanghai Jiaotong University（上海交通大学）

专题命中视觉定位与Grounding ：grounding(title,abstract)；分类 cs.AI

Comments Accepted to EMNLP 2025 Findings

2506.21535 2025-09-23 eess.IV cs.CV cs.LG 62%

Exploring the Design Space of 3D MLLMs for CT Report Generation

Mohammed Baharoon, Jun Ma, Congyu Fang, Augustin Toma, Bo Wang

机构 * Vector Institute for Artificial Intelligence（向量人工智能研究所）； Department of Biomedical Informatics, Harvard Medical School（生物医学信息学系，哈佛医学院）； Peter Munk Cardiac Centre, University Health Network（皮特·蒙克心脏中心，大学健康网络）； Medical Biophysics, University of Toronto（医学生物物理系，多伦多大学）； Department of Computer Science, University of Toronto（计算机科学系，多伦多大学）； Department of Laboratory Medicine and Pathobiology, University of Toronto（实验室医学与病理学系，多伦多大学）； AI Hub, University Health Network（人工智能中心，大学健康网络）

专题命中视觉定位与Grounding ：multimodal large language model(abstract)；分类 cs.CV、cs.LG

2509.18096 2025-09-23 cs.CV 57%

Seg4Diff: Unveiling Open-Vocabulary Segmentation in Text-to-Image Diffusion Transformers

Chaehyun Kim, Heeseong Shin, Eunbeen Hong, Heeji Yoon, Anurag Arnab, Paul Hongsuck Seo, Sunghwan Hong, Seungryong Kim

机构 * KAIST AI（韩国科学技术院人工智能研究所）； Korea University（韩国大学）； ETH Zürich（苏黎世联邦理工学院）

专题命中视觉定位与Grounding ：grounding(abstract)；分类 cs.CV

Comments NeurIPS 2025. Project page: https://cvlab-kaist.github.io/Seg4Diff/

2509.17671 2025-09-23 cs.CL cs.AI 57%

Turk-LettuceDetect: A Hallucination Detection Models for Turkish RAG Applications

Selva Taş, Mahmut El Huseyni, Özay Ezerceli, Reyhan Bayraktar, Fatma Betül Terzioğlu

机构 * Hidden for Review（保密）

专题命中视觉定位与Grounding ：grounding(abstract)；分类 cs.AI

2509.17615 2025-09-23 cs.CV 57%

From Benchmarks to Reality: Advancing Visual Anomaly Detection by the VAND 3.0 Challenge

Lars Heckler-Kram, Ashwin Vaidya, Jan-Hendrik Neudeck, Ulla Scheler, Dick Ameln, Samet Akcay, Paula Ramos

机构 * MVTec Software GmbH（MVTec软件公司）； Technical University of Munich（慕尼黑技术大学）； Intel（英特尔）； Voxel51

专题命中视觉定位与Grounding ：vision language model(abstract)；分类 cs.CV

1. 视觉问答 11 篇

SD-VLM: Spatial Measuring and Understanding with Depth-Encoded Vision-Language Models

ProtoVQA: An Adaptable Prototypical Framework for Explainable Fine-Grained Visual Question Answering

Interpreting Attention Heads for Image-to-Text Information Flow in Large Vision-Language Models

When Big Models Train Small Ones: Label-Free Model Parity Alignment for Efficient Visual Question Answering using Small VLMs

Enhancing Scientific Visual Question Answering via Vision-Caption aware Supervised Fine-Tuning

Unmasking Deceptive Visuals: Benchmarking Multimodal Large Language Models on Misleading Chart Question Answering

Evaluating Fairness in Large Vision-Language Models Across Diverse Demographic Attributes and Prompts

Eye Gaze Tells You Where to Compute: Gaze-Driven Efficient VLMs

Surgical-MambaLLM: Mamba2-enhanced Multimodal Large Language Model for VQLA in Robotic Surgery

Both Text and Images Leaked! A Systematic Analysis of Data Contamination in Multimodal LLM

Bringing Pedagogy into Focus: Evaluating Virtual Teaching Assistants' Question-Answering in Asynchronous Learning Environments

2. 视觉推理 12 篇

Seeing Culture: A Benchmark for Visual Reasoning and Grounding

Orchestrate, Generate, Reflect: A VLM-Based Multi-Agent Collaboration Framework for Automated Driving Policy Learning

Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning

ReasonPlan: Unified Scene Prediction and Decision Reasoning for Closed-loop Autonomous Driving

MCP: A Control-Theoretic Orchestration Framework for Synergistic Efficiency and Interpretability in Multimodal Large Language Models

GeoPQA: Bridging the Visual Perception Gap in MLLMs for Geometric Reasoning

All-in-one: Understanding and Generation in Multimodal Reasoning with the MAIA Benchmark

Text-Scene: A Scene-to-Language Parsing Framework for 3D Scene Understanding

How Good are Foundation Models in Step-by-Step Embodied Reasoning?

WISE: Weak-Supervision-Guided Step-by-Step Explanations for Multimodal LLMs in Image Classification

AgriDoctor: A Multimodal Intelligent Assistant for Agriculture

On LLM-Based Scientific Inductive Reasoning Beyond Equations

3. 视觉定位与Grounding 17 篇

GroundFlow: A Plug-in Module for Temporal Reasoning on 3D Point Cloud Sequential Grounding

FOCUS: Unified Vision-Language Modeling for Interactive Editing Driven by Referential Segmentation

InteGround: On the Evaluation of Verification and Retrieval Planning in Integrative Grounding

Exploring the Design Space of 3D MLLMs for CT Report Generation

Seg4Diff: Unveiling Open-Vocabulary Segmentation in Text-to-Image Diffusion Transformers

Turk-LettuceDetect: A Hallucination Detection Models for Turkish RAG Applications

From Benchmarks to Reality: Advancing Visual Anomaly Detection by the VAND 3.0 Challenge