视觉大模型 / VLM - arXivDaily 专题

2506.06856 2025-09-30 cs.CV 83%

Vision-EKIPL: External Knowledge-Infused Policy Learning for Visual Reasoning

Chaoyang Wang, Zeyu Zhang, Meng Meng, Xu Zhou, Haiyun Jiang

机构 * Sangfor Technologies ； The Australian National University（澳大利亚国立大学）； Shanghai Jiao Tong University（上海交通大学）

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

2509.21854 2025-09-29 cs.MM cs.CV 83%

Perception-Consistency Multimodal Large Language Models Reasoning via Caption-Regularized Policy Optimization

Songjun Tu, Qichao Zhang, Jingbo Sun, Yuqian Fu, Linjing Li, Xiangyuan Lan, Dongmei Jiang, Yaowei Wang, Dongbin Zhao

机构 * State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences（多模态人工智能系统国家重点实验室，自动化研究所，中国科学院）； Pengcheng Laboratory（鹏城实验室）； School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）； Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））

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

Comments 12pages, 11 figures

2507.20890 2025-09-29 cs.CV cs.CL 83%

$A^2R^2$: Advancing Img2LaTeX Conversion via Visual Reasoning with Attention-Guided Refinement

Zhecheng Li, Guoxian Song, Yiwei Wang, Zhen Xiong, Junsong Yuan, Yujun Cai

机构 * University of California, San Diego（加州大学圣地亚哥分校）； ByteDance（字节跳动）； University of California, Merced（加州大学默塞德分校）； University of Southern California（南加州大学）； University at Buffalo（布法罗大学）； The University of Queensland（昆士兰大学）

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

2509.19841 2025-09-25 cs.CV 83%

ThinkFake: Reasoning in Multimodal Large Language Models for AI-Generated Image Detection

Tai-Ming Huang, Wei-Tung Lin, Kai-Lung Hua, Wen-Huang Cheng, Junichi Yamagishi, Jun-Cheng Chen

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

2509.16149 2025-09-22 cs.CV 83%

Pointing to a Llama and Call it a Camel: On the Sycophancy of Multimodal Large Language Models

Renjie Pi, Kehao Miao, Li Peihang, Runtao Liu, Jiahui Gao, Jipeng Zhang, Xiaofang Zhou

机构 * HKUST（香港科技大学）； HKU（香港大学）

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

2509.15772 2025-09-22 cs.CV 83%

Vision-Language Models as Differentiable Semantic and Spatial Rewards for Text-to-3D Generation

Weimin Bai, Yubo Li, Weijian Luo, Wenzheng Chen, He Sun

机构 * Peking University（北京大学）； Xiaohongshu Inc（小红书公司）

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

2502.20587 2025-09-22 cs.LG 83%

Cache-of-Thought: Master-Apprentice Framework for Cost-Effective Vision Language Model Reasoning

Mingyuan Wu, Jize Jiang, Haozhen Zheng, Meitang Li, Zhaoheng Li, Beitong Tian, Bo Chen, Yongjoo Park, Minjia Zhang, Chengxiang Zhai, Klara Nahrstedt

机构 * University of Illinois Urbana Champaign（伊利诺伊大学厄巴纳-香槟分校）； University of Michigan Ann Arbor（密歇根大学安娜堡分校）

专题命中视觉推理：vision language model(title,abstract)；VLM(abstract)；分类 cs.LG

Comments EMNLP 2025 Main Conference. Mingyuan, Jize, and Haozhen contributed equally, while Minjia, Chengxiang, and Klara advised equally

2509.13773 2025-09-18 cs.AI cs.IR 83%

MIRA: Empowering One-Touch AI Services on Smartphones with MLLM-based Instruction Recommendation

Zhipeng Bian, Jieming Zhu, Xuyang Xie, Quanyu Dai, Zhou Zhao, Zhenhua Dong

机构 * Shenzhen University（深圳大学）； Huawei Noah’s Ark Lab（华为诺亚实验室）； Zhejiang University（浙江大学）

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

Comments Published in Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track), ACL 2025. Official version: https://doi.org/10.18653/v1/2025.acl-industry.103

Journal ref Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track) ACL 2025 1457-1465

2509.12060 2025-09-17 cs.AI 83%

When Safe Unimodal Inputs Collide: Optimizing Reasoning Chains for Cross-Modal Safety in Multimodal Large Language Models

Wei Cai, Shujuan Liu, Jian Zhao, Ziyan Shi, Yusheng Zhao, Yuchen Yuan, Tianle Zhang, Chi Zhang, Xuelong Li

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

2509.12132 2025-09-16 cs.CV cs.CL 83%

Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models

Pu Jian, Junhong Wu, Wei Sun, Chen Wang, Shuo Ren, Jiajun Zhang

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

Comments EMNLP2025 Main

2409.03521 2025-09-11 cs.CV 83%

Have Large Vision-Language Models Mastered Art History?

Ombretta Strafforello, Derya Soydaner, Michiel Willems, Anne-Sofie Maerten, Stefanie De Winter

机构 * KU Leuven（库勒韦恩大学）； Leiden University（莱顿大学）

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

2509.06312 2025-09-09 eess.SY cs.LG cs.SY 83%

Enhancing Low-Altitude Airspace Security: MLLM-Enabled UAV Intent Recognition

Guangyu Lei, Tianhao Liang, Yuqi Ping, Xinglin Chen, Longyu Zhou, Junwei Wu, Xiyuan Zhang, Huahao Ding, Xingjian Zhang, Weijie Yuan, Tingting Zhang, Qinyu Zhang

机构 * School of Information Science and Technology, Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳）信息科学与技术学院）； Guangdong Provincial Key Laboratory of Space-Aerial Networking and Intelligent Sensing（广东省空间-航空网络与智能感知重点实验室）； Information Systems Technology and Design, Singapore University of Technology and Design（新加坡科技设计大学信息系统技术与设计）； School of System Design and Intelligent Manufacturing, Southern University of Science and Technology（南方科技大学系统设计与智能制造学院）

专题命中视觉推理：MLLM(title,abstract)；multimodal large language model(abstract)；分类 cs.LG

Comments The paper has been submitted to IEEE Internet of Things Magazine

2508.15802 2025-08-25 cs.CL cs.AI 83%

MAC: A Live Benchmark for Multimodal Large Language Models in Scientific Understanding

Mohan Jiang, Jin Gao, Jiahao Zhan, Dequan Wang

机构 * Shanghai Jiao Tong University（上海交通大学）； Shanghai Innovation Institute（上海创新研究院）； Fudan University（复旦大学）

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

2508.10287 2025-08-21 cs.CV 83%

JRDB-Reasoning: A Difficulty-Graded Benchmark for Visual Reasoning in Robotics

Simindokht Jahangard, Mehrzad Mohammadi, Yi Shen, Zhixi Cai, Hamid Rezatofighi

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

2508.01057 2025-08-13 cs.AI cs.RO 83%

Edge-Based Multimodal Sensor Data Fusion with Vision Language Models (VLMs) for Real-time Autonomous Vehicle Accident Avoidance

Fengze Yang, Bo Yu, Yang Zhou, Xuewen Luo, Zhengzhong Tu, Chenxi Liu

机构 * Department of Civil & Environmental Engineering University of Utah（土木与环境工程系犹他大学）； Zachry Department of Civil and Environmental Engineering Texas A&M University（扎克里系土木与环境工程系德克萨斯农工大学）； Department of Computer Science & Engineering Texas A&M University（计算机科学与工程系德克萨斯农工大学）

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

Comments 24 pages, 6 tables, 7 figures

2508.07260 2025-08-12 cs.CV 83%

Small-Large Collaboration: Training-efficient Concept Personalization for Large VLM using a Meta Personalized Small VLM

Sihan Yang, Huitong Ji, Shaolin Lu, Jiayi Chen, Binxiao Xu, Ming Lu, Yuanxing Zhang, Wenhui Dong, Wentao Zhang

机构 * Peking University（北京大学）

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

2505.19015 2025-08-11 cs.CV cs.MM 83%

Can Multimodal Large Language Models Understand Spatial Relations?

Jingping Liu, Ziyan Liu, Zhedong Cen, Yan Zhou, Yinan Zou, Weiyan Zhang, Haiyun Jiang, Tong Ruan

机构 * School of Information Science and Engineering, East China University of Science and Technology, Shanghai, China（信息科学与工程学院，东华大学，上海，中国）； School of Computer Science, Fudan University, Shanghai, China（计算机科学学院，复旦大学，上海，中国）

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

Comments 13 pages, 7 figures, published to ACL 2025

Journal ref In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 620-632, 2025, Vienna, Austria

2508.00323 2025-08-04 cs.AI 83%

Oedipus and the Sphinx: Benchmarking and Improving Visual Language Models for Complex Graphic Reasoning

Jianyi Zhang, Xu Ji, Ziyin Zhou, Yuchen Zhou, Shubo Shi, Haoyu Wu, Zhen Li, Shizhao Liu

机构 * Beijing Electronic Science & Technology Institute（北京电子科学技术研究所）

专题命中视觉推理：visual language model(title,abstract)；VLM(abstract)；分类 cs.AI

2507.20342 2025-07-29 cs.AI cs.RO 83%

VLMPlanner: Integrating Visual Language Models with Motion Planning

Zhipeng Tang, Sha Zhang, Jiajun Deng, Chenjie Wang, Guoliang You, Yuting Huang, Xinrui Lin, Yanyong Zhang

机构 * University of Science and Technology of China（科学技术大学）； University of Adelaide（阿德莱德大学）； Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（合肥综合性国家科学中心人工智能研究院）

专题命中视觉推理：visual language model(title)；vision-language model(abstract)；VLM(abstract)；分类 cs.AI

Comments 8 pages, 3 figures, this paper has been accepted by ACM MM 2025

2411.12789 2025-07-29 cs.CV 83%

Efficient Physics Simulation for 3D Scenes via MLLM-Guided Gaussian Splatting

Haoyu Zhao, Hao Wang, Xingyue Zhao, Hao Fei, Hongqiu Wang, Chengjiang Long, Hua Zou

机构 * School of Computer Science, Wuhan University（武汉大学计算机学院）； Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology（华中科技大学光电研究院）； Meta Reality Lab（Meta现实实验室）； Xi’an Jiao Tong University（西安交通大学）； National University of Singapore（新加坡国立大学）； The Department of Systems Hub, Hong Kong University of Science and Technology (Guangzhou)（香港科技大学系统枢纽部门（广州））

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

Comments ICCV 2025

2507.17204 2025-07-24 cs.LG 83%

Filter-And-Refine: A MLLM Based Cascade System for Industrial-Scale Video Content Moderation

Zixuan Wang, Jinghao Shi, Hanzhong Liang, Xiang Shen, Vera Wen, Zhiqian Chen, Yifan Wu, Zhixin Zhang, Hongyu Xiong

机构 * TikTok（字节跳动）

专题命中视觉推理：MLLM(title,abstract)；multimodal large language model(abstract)；分类 cs.LG

Comments Camera Ready for ACL 2025

2507.11079 2025-07-16 cs.AI 83%

Tactical Decision for Multi-UGV Confrontation with a Vision-Language Model-Based Commander

Li Wang, Qizhen Wu, Lei Chen

机构 * Yangtze Delta Region Academy（扬子江地区学院）； Beijing Institute of Technology（北京理工大学）； School of Automation（自动化学院）； Beihang University（北航大学）； Advanced Research Institute of Multidisciplinary Sciences（多学科科学高级研究机构）

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

2507.07424 2025-07-11 cs.CV 83%

Corvid: Improving Multimodal Large Language Models Towards Chain-of-Thought Reasoning

Jingjing Jiang, Chao Ma, Xurui Song, Hanwang Zhang, Jun Luo

机构 * Shanghai Jiao Tong University（上海交通大学）； Nanyang Technological University（南洋理工大学）

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

Comments ICCV 2025

2506.14727 2025-07-08 cs.RO cs.AI 83%

Casper: Inferring Diverse Intents for Assistive Teleoperation with Vision Language Models

Huihan Liu, Rutav Shah, Shuijing Liu, Jack Pittenger, Mingyo Seo, Yuchen Cui, Yonatan Bisk, Roberto Martín-Martín, Yuke Zhu

专题命中视觉推理：vision language model(title)；VLM(abstract)；visual language model(abstract)；分类 cs.AI

2410.11564 2025-07-08 cs.RO cs.CV 83%

PAVLM: Advancing Point Cloud based Affordance Understanding Via Vision-Language Model

Shang-Ching Liu, Van Nhiem Tran, Wenkai Chen, Wei-Lun Cheng, Yen-Lin Huang, I-Bin Liao, Yung-Hui Li, Jianwei Zhang

机构 * Technical Aspects of Multimodal Systems (TAMS), Department of Informatics, University of Hamburg（汉堡大学信息学院多模态系统技术部门）； Hon Hai Research Institute (HHRI)（鸿海研究机构）； Department of Electrical Engineering, National Taiwan University（台湾大学电子工程系）； Department of Computer Science and Technology, National Tsinghua University（清华大学计算机科学与技术系）

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

2507.00886 2025-07-02 cs.CV cs.RO 83%

GaussianVLM: Scene-centric 3D Vision-Language Models using Language-aligned Gaussian Splats for Embodied Reasoning and Beyond

Anna-Maria Halacheva, Jan-Nico Zaech, Xi Wang, Danda Pani Paudel, Luc Van Gool

机构 * ETH Zurich（苏黎世联邦理工学院）； TU Munich（慕尼黑技术大学）

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

2506.23352 2025-07-01 cs.CV 83%

GeoProg3D: Compositional Visual Reasoning for City-Scale 3D Language Fields

Shunsuke Yasuki, Taiki Miyanishi, Nakamasa Inoue, Shuhei Kurita, Koya Sakamoto, Daichi Azuma, Masato Taki, Yutaka Matsuo

机构 * Rikkyo University（立命馆大学）； University of Tokyo（东京大学）； ATR（ATR研究所）； Institute of Science Tokyo（东京科学研究院）； National Institute of Informatics（国家信息研究所）； NII LLMC（日本信息处理学会LLMC）； Sony Semiconductor Solutions（索尼半导体解决方案）

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

Comments Accepted by ICCV 2025

2505.24164 2025-06-18 cs.CL cs.CV 83%

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models

Shilin Xu, Yanwei Li, Rui Yang, Tao Zhang, Yueyi Sun, Wei Chow, Linfeng Li, Hang Song, Qi Xu, Yunhai Tong, Xiangtai Li, Hao Fei

机构 * ByteDance（字节跳动）； Peking University（北京大学）； National University of Singapore（新加坡国立大学）

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

2506.06600 2025-06-17 cs.CV 83%

RARL: Improving Medical VLM Reasoning and Generalization with Reinforcement Learning and LoRA under Data and Hardware Constraints

Tan-Hanh Pham, Chris Ngo

机构 * Harvard Medical School（哈佛医学院）； Knovel Engineering Lab（Knovel工程实验室）

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

Comments Under review

2505.13031 2025-06-12 cs.AI 83%

MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO

Yicheng Xiao, Lin Song, Yukang Chen, Yingmin Luo, Yuxin Chen, Yukang Gan, Wei Huang, Xiu Li, Xiaojuan Qi, Ying Shan

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）； ARC Lab, Tencent PCG（腾讯PCG ARC实验室）； The Chinese University of Hong Kong（香港中文大学）； The University of Hong Kong（香港大学）

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

Comments Code: https://github.com/TencentARC/MindOmni

1. 视觉推理 4478 篇

Vision-EKIPL: External Knowledge-Infused Policy Learning for Visual Reasoning

Perception-Consistency Multimodal Large Language Models Reasoning via Caption-Regularized Policy Optimization

$A^2R^2$: Advancing Img2LaTeX Conversion via Visual Reasoning with Attention-Guided Refinement

ThinkFake: Reasoning in Multimodal Large Language Models for AI-Generated Image Detection

Pointing to a Llama and Call it a Camel: On the Sycophancy of Multimodal Large Language Models

Vision-Language Models as Differentiable Semantic and Spatial Rewards for Text-to-3D Generation

Cache-of-Thought: Master-Apprentice Framework for Cost-Effective Vision Language Model Reasoning

MIRA: Empowering One-Touch AI Services on Smartphones with MLLM-based Instruction Recommendation

When Safe Unimodal Inputs Collide: Optimizing Reasoning Chains for Cross-Modal Safety in Multimodal Large Language Models

Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models

Have Large Vision-Language Models Mastered Art History?

Enhancing Low-Altitude Airspace Security: MLLM-Enabled UAV Intent Recognition

MAC: A Live Benchmark for Multimodal Large Language Models in Scientific Understanding

JRDB-Reasoning: A Difficulty-Graded Benchmark for Visual Reasoning in Robotics

Edge-Based Multimodal Sensor Data Fusion with Vision Language Models (VLMs) for Real-time Autonomous Vehicle Accident Avoidance

Small-Large Collaboration: Training-efficient Concept Personalization for Large VLM using a Meta Personalized Small VLM

Can Multimodal Large Language Models Understand Spatial Relations?

Oedipus and the Sphinx: Benchmarking and Improving Visual Language Models for Complex Graphic Reasoning

VLMPlanner: Integrating Visual Language Models with Motion Planning

Efficient Physics Simulation for 3D Scenes via MLLM-Guided Gaussian Splatting

Filter-And-Refine: A MLLM Based Cascade System for Industrial-Scale Video Content Moderation

Tactical Decision for Multi-UGV Confrontation with a Vision-Language Model-Based Commander

Corvid: Improving Multimodal Large Language Models Towards Chain-of-Thought Reasoning

Casper: Inferring Diverse Intents for Assistive Teleoperation with Vision Language Models

PAVLM: Advancing Point Cloud based Affordance Understanding Via Vision-Language Model

GaussianVLM: Scene-centric 3D Vision-Language Models using Language-aligned Gaussian Splats for Embodied Reasoning and Beyond

GeoProg3D: Compositional Visual Reasoning for City-Scale 3D Language Fields

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models

RARL: Improving Medical VLM Reasoning and Generalization with Reinforcement Learning and LoRA under Data and Hardware Constraints

MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO