视觉大模型 / VLM - arXivDaily 专题

2505.20241 2025-11-05 cs.LG cs.AI 62%

DreamPRM: Domain-Reweighted Process Reward Model for Multimodal Reasoning

Qi Cao, Ruiyi Wang, Ruiyi Zhang, Sai Ashish Somayajula, Pengtao Xie

机构 * University of California, San Diego（加州大学圣地亚哥分校）； Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)（穆罕默德·本·扎耶德人工智能大学）

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

Comments 28 pages, 10 figures, to appear in NeurIPS 2025 (Conference on Neural Information Processing Systems)

2511.00362 2025-11-04 cs.CV cs.AI cs.GR 62%

Oitijjo-3D: Generative AI Framework for Rapid 3D Heritage Reconstruction from Street View Imagery

Momen Khandoker Ope, Akif Islam, Mohd Ruhul Ameen, Abu Saleh Musa Miah, Md Rashedul Islam, Jungpil Shin

机构 * University of Rajshahi（拉贾沙希大学）； Marshall University（马歇尔大学）； University of Aizu（御所大学）； University of Asia Pacific（亚洲太平洋大学）

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

Comments 6 Pages, 4 figures, 2 Tables, Submitted to ICECTE 2026

2511.00110 2025-11-04 cs.CV cs.AI 62%

Chain of Time: In-Context Physical Simulation with Image Generation Models

YingQiao Wang, Eric Bigelow, Boyi Li, Tomer Ullman

机构 * Harvard University（哈佛大学）； Sakana AI ； NTT Research（NTT研究所）； UC Berkeley（伯克利大学）； Nvidia Research（NVIDIA研究）

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

2510.25933 2025-10-31 cs.AI cs.HC cs.LG cs.NE 62%

Humains-Junior: A 3.8B Language Model Achieving GPT-4o-Level Factual Accuracy by Directed Exoskeleton Reasoning

Nissan Yaron, Dan Bystritsky, Ben-Etzion Yaron

机构 * Humains AI Research（Humains人工智能研究）； Inpris Ltd（Inpris公司）

专题命中视觉推理：grounding(abstract)；分类 cs.AI、cs.LG

2510.25798 2025-10-31 cs.LG cs.AI cs.CL 62%

MemEIC: A Step Toward Continual and Compositional Knowledge Editing

Jin Seong, Jiyun Park, Wencke Liermann, Hongseok Choi, Yoonji Nam, Hyun Kim, Soojong Lim, Namhoon Lee

机构 * Electronics and Telecommunications Research Institute, Republic of Korea（韩国电子电信研究院）； POSTECH ； Sungkyunkwan University（全南大学）

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

Comments NeurIPS 2025, 38 pages, 8 figures

2509.17784 2025-10-31 cs.LG cs.AI 62%

Revealing Multimodal Causality with Large Language Models

Jin Li, Shoujin Wang, Qi Zhang, Feng Liu, Tongliang Liu, Longbing Cao, Shui Yu, Fang Chen

机构 * University of Technology Sydney（技术大学悉尼大学）； Tongji University（同济大学）； University of Melbourne（墨尔本大学）； University of Sydney（悉尼大学）； Macquarie University（麦考瑞大学）

专题命中视觉推理：MLLM(abstract)；分类 cs.AI、cs.LG

Comments Accepted at NeurIPS 2025

2503.04852 2025-10-31 cs.CV cs.LG 62%

CAUSAL3D: A Comprehensive Benchmark for Causal Learning from Visual Data

Disheng Liu, Yiran Qiao, Wuche Liu, Yiren Lu, Yunlai Zhou, Tuo Liang, Yu Yin, Jing Ma

机构 * Case Western Reserve University（凯斯西储大学）

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

Comments Datasets link: https://huggingface.co/datasets/LLDDSS/Causal3D_Dataset

2510.22118 2025-10-29 cs.CV cs.AI 62%

GRAID: Enhancing Spatial Reasoning of VLMs Through High-Fidelity Data Generation

Karim Elmaaroufi, Liheng Lai, Justin Svegliato, Yutong Bai, Sanjit A. Seshia, Matei Zaharia

机构 * University of California, Berkeley（加州大学伯克利分校）； Models for Embodied and Spatial Harmony（具身与空间和谐模型）

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

Comments 22 pages, 3 figures, 3 tables, project page: https://ke7.github.io/graid/

2510.23482 2025-10-28 cs.CV cs.AI 62%

On the Faithfulness of Visual Thinking: Measurement and Enhancement

Zujing Liu, Junwen Pan, Qi She, Yuan Gao, Guisong Xia

机构 * Wuhan University（武汉大学）； ByteDance（字节跳动）

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

2510.22849 2025-10-28 cs.CL cs.AI cs.LG 62%

Once Upon an Input: Reasoning via Per-Instance Program Synthesis

Adam Stein, Neelay Velingker, Mayur Naik, Eric Wong

机构 * University of Pennsylvania（宾夕法尼亚大学）

专题命中视觉推理：visual question answering(abstract)；分类 cs.AI、cs.LG

Comments Accepted at NeurIPS 2025. 34 pages, 7 figures

2508.06937 2025-10-28 cs.CV cs.AI 62%

CannyEdit: Selective Canny Control and Dual-Prompt Guidance for Training-Free Image Editing

Weiyan Xie, Han Gao, Didan Deng, Kaican Li, April Hua Liu, Yongxiang Huang, Nevin L. Zhang

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

Comments Project Page: vaynexie.github.io/CannyEdit/; MindSpore Code: github.com/mindspore-lab/mindone/tree/master/examples/canny_edit; PyTorch Code: github.com/vaynexie/CannyEdit

2510.21839 2025-10-28 cs.CV cs.AI 62%

Evaluating ChatGPT's Performance in Classifying Pneumonia from Chest X-Ray Images

Pragna Prahallad, Pranathi Prahallad

机构 * Emerald High School（埃默尔德高中）

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

2510.12712 2025-10-28 cs.CV cs.AI 62%

Beyond Seeing: Evaluating Multimodal LLMs on Tool-Enabled Image Perception, Transformation, and Reasoning

Xingang Guo, Utkarsh Tyagi, Advait Gosai, Paula Vergara, Jayeon Park, Ernesto Gabriel Hernández Montoya, Chen Bo Calvin Zhang, Bin Hu, Yunzhong He, Bing Liu, Rakshith Sharma Srinivasa

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

2510.19808 2025-10-23 cs.CV cs.CL cs.LG 62%

Pico-Banana-400K: A Large-Scale Dataset for Text-Guided Image Editing

Yusu Qian, Eli Bocek-Rivele, Liangchen Song, Jialing Tong, Yinfei Yang, Jiasen Lu, Wenze Hu, Zhe Gan

机构 * Apple（苹果公司）

专题命中视觉推理：MLLM(abstract)；分类 cs.CV、cs.LG

2507.16814 2025-10-23 cs.LG cs.CV 62%

Semi-off-Policy Reinforcement Learning for Vision-Language Slow-Thinking Reasoning

Junhao Shen, Haiteng Zhao, Yuzhe Gu, Songyang Gao, Kuikun Liu, Haian Huang, Jianfei Gao, Dahua Lin, Wenwei Zhang, Kai Chen

机构 * Shanghai Jiao Tong University（上海交通大学）； Shanghai AI Laboratory（上海人工智能实验室）； MMLab, The Chinese University of Hong Kong（香港中文大学MMLab）

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

2510.17354 2025-10-21 cs.CL cs.AI cs.IR cs.LG 62%

Towards Mixed-Modal Retrieval for Universal Retrieval-Augmented Generation

Chenghao Zhang, Guanting Dong, Xinyu Yang, Zhicheng Dou

机构 * Renmin University of China（中国人民大学）

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

Comments This work is in progress

2510.17157 2025-10-21 cs.CV cs.AI 62%

GACO-CAD: Geometry-Augmented and Conciseness-Optimized CAD Model Generation from Single Image

Yinghui Wang, Xinyu Zhang, Peng Du

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

2510.16772 2025-10-21 cs.CV cs.AI 62%

Region in Context: Text-condition Image editing with Human-like semantic reasoning

Thuy Phuong Vu, Dinh-Cuong Hoang, Minhhuy Le, Phan Xuan Tan

机构 * Greenwich Vietnam FPT University（越南格林威治FPT大学）

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

2510.16643 2025-10-21 cs.CV cs.AI cs.RO 62%

Structured Interfaces for Automated Reasoning with 3D Scene Graphs

Aaron Ray, Jacob Arkin, Harel Biggie, Chuchu Fan, Luca Carlone, Nicholas Roy

机构 * Massachusetts Institute of Technology（麻省理工学院）

专题命中视觉推理：grounding(abstract)；分类 cs.CV、cs.AI

Comments 25 pages, 3 figures

2510.16540 2025-10-21 cs.CV cs.AI 62%

Enhancing Compositional Reasoning in CLIP via Reconstruction and Alignment of Text Descriptions

Jihoon Kwon, Kyle Min, Jy-yong Sohn

机构 * Seoul National University（首尔国立大学）； Oracle（Oracle公司）； Yonsei University（延世大学）； Intel Labs（英特尔实验室）

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

Comments Accepted at NeurIPS 2025 (poster). This is the camera-ready version

2510.10248 2025-10-20 cs.LG cs.AI 62%

Reasoning-Enhanced Large Language Models for Molecular Property Prediction

Jiaxi Zhuang, Yaorui Shi, Jue Hou, Yunong He, Mingwei Ye, Mingjun Xu, Yuming Su, Linfeng Zhang, Ying Qian, Linfeng Zhang, Guolin Ke, Hengxing Cai

机构 * DP Technology（DP技术公司）； Shanghai Jiao Tong University（上海交通大学）； East China Normal University（华东师范大学）

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

2509.01055 2025-10-20 cs.AI cs.CL cs.CV 62%

VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use

Dongfu Jiang, Yi Lu, Zhuofeng Li, Zhiheng Lyu, Ping Nie, Haozhe Wang, Alex Su, Hui Chen, Kai Zou, Chao Du, Tianyu Pang, Wenhu Chen

机构 * University of Waterloo（滑铁卢大学）； Sea AI Lab（Sea AI 实验室）； University of Toronto（多伦多大学）； Shanghai University（上海大学）； HKUST（香港科技大学）； M-A-P ； National University of Singapore（新加坡国立大学）

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

Comments 32 pages, 5 figures, 13 tables

2506.17462 2025-10-20 cs.RO cs.AI cs.CV 62%

General-Purpose Robotic Navigation via LVLM-Orchestrated Perception, Reasoning, and Acting

Bernard Lange, Anil Yildiz, Mansur Arief, Shehryar Khattak, Mykel Kochenderfer, Georgios Georgakis

机构 * Stanford University（斯坦福大学）； Jet Propulsion Laboratory（喷气推进实验室）； California Institute of Technology（加州理工学院）

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

2506.23584 2025-10-17 eess.IV cs.AI cs.CV 62%

A Clinically-Grounded Two-Stage Framework for Renal CT Report Generation

Renjie Liang, Zhengkang Fan, Jinqian Pan, Chenkun Sun, Bruce Daniel Steinberg, Russell Terry, Jie Xu

机构 * Department of Health Outcomes and Biomedical Informatics, University of Florida（健康结果与生物医学信息学系，佛罗里达大学）； Department of Urology, University of Florida（泌尿外科系，佛罗里达大学）

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

2510.13804 2025-10-16 cs.CV cs.AI cs.CL 62%

Generative Universal Verifier as Multimodal Meta-Reasoner

Xinchen Zhang, Xiaoying Zhang, Youbin Wu, Yanbin Cao, Renrui Zhang, Ruihang Chu, Ling Yang, Yujiu Yang

机构 * Tsinghua University（清华大学）； ByteDance Seed（字节跳动种子）； Princeton University（普林斯顿大学）

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

2406.12736 2025-10-16 cs.CV cs.AI 62%

Beyond Visual Appearances: Privacy-sensitive Objects Identification via Hybrid Graph Reasoning

Zhuohang Jiang, Bingkui Tong, Xia Du, Ahmed Alhammadi, Jizhe Zhou

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

Comments I would like to formally request the withdrawal of my manuscript from arXiv. After a further internal review, I realized that the dataset used in this study contains personal or sensitive information that may inadvertently compromise individuals' privacy

2508.01181 2025-10-14 cs.AI cs.CV cs.MM cs.SD eess.AS 62%

Benchmarking and Bridging Emotion Conflicts for Multimodal Emotion Reasoning

Zhiyuan Han, Beier Zhu, Yanlong Xu, Peipei Song, Xun Yang

机构 * University of Science and Technology of China（科学技术大学）； Nanyang Technological University（南洋理工大学）

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

Comments ACM Multimedia 2025 Oral Code: https://github.com/ZhiyuanHan-Aaron/MoSEAR Project Page: https://zhiyuanhan-aaron.github.io/MoSEAR-page/

2510.09302 2025-10-13 cs.CV cs.AI cs.CL 62%

CapGeo: A Caption-Assisted Approach to Geometric Reasoning

Yuying Li, Siyi Qian, Hao Liang, Leqi Zheng, Ruichuan An, Yongzhen Guo, Wentao Zhang

机构 * THU（清华大学）； PKU（北京大学）； Ant Group（蚂蚁集团）

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

Comments preprint, under review

2510.08559 2025-10-10 cs.CV cs.AI 62%

SciVideoBench: Benchmarking Scientific Video Reasoning in Large Multimodal Models

Andong Deng, Taojiannan Yang, Shoubin Yu, Lincoln Spencer, Mohit Bansal, Chen Chen, Serena Yeung-Levy, Xiaohan Wang

机构 * University of Central Florida（中央佛罗里达大学）； University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）； Stanford University（斯坦福大学）

专题命中视觉推理：grounding(abstract)；分类 cs.CV、cs.AI

2510.05593 2025-10-08 cs.CV cs.AI cs.CL 62%

Improving Chain-of-Thought Efficiency for Autoregressive Image Generation

Zeqi Gu, Markos Georgopoulos, Xiaoliang Dai, Marjan Ghazvininejad, Chu Wang, Felix Juefei-Xu, Kunpeng Li, Yujun Shi, Zecheng He, Zijian He, Jiawei Zhou, Abe Davis, Jialiang Wang

机构 * Meta Superintelligence Labs（Meta超智能实验室）； Meta FAIR ； Cornell University（康奈尔大学）； Stony Brook University（石溪大学）

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

1. 视觉推理 4484 篇

DreamPRM: Domain-Reweighted Process Reward Model for Multimodal Reasoning

Oitijjo-3D: Generative AI Framework for Rapid 3D Heritage Reconstruction from Street View Imagery

Chain of Time: In-Context Physical Simulation with Image Generation Models

Humains-Junior: A 3.8B Language Model Achieving GPT-4o-Level Factual Accuracy by Directed Exoskeleton Reasoning

MemEIC: A Step Toward Continual and Compositional Knowledge Editing

Revealing Multimodal Causality with Large Language Models

CAUSAL3D: A Comprehensive Benchmark for Causal Learning from Visual Data

GRAID: Enhancing Spatial Reasoning of VLMs Through High-Fidelity Data Generation

On the Faithfulness of Visual Thinking: Measurement and Enhancement

Once Upon an Input: Reasoning via Per-Instance Program Synthesis

CannyEdit: Selective Canny Control and Dual-Prompt Guidance for Training-Free Image Editing

Evaluating ChatGPT's Performance in Classifying Pneumonia from Chest X-Ray Images

Beyond Seeing: Evaluating Multimodal LLMs on Tool-Enabled Image Perception, Transformation, and Reasoning

Pico-Banana-400K: A Large-Scale Dataset for Text-Guided Image Editing

Semi-off-Policy Reinforcement Learning for Vision-Language Slow-Thinking Reasoning

Towards Mixed-Modal Retrieval for Universal Retrieval-Augmented Generation

GACO-CAD: Geometry-Augmented and Conciseness-Optimized CAD Model Generation from Single Image

Region in Context: Text-condition Image editing with Human-like semantic reasoning

Structured Interfaces for Automated Reasoning with 3D Scene Graphs

Enhancing Compositional Reasoning in CLIP via Reconstruction and Alignment of Text Descriptions

Reasoning-Enhanced Large Language Models for Molecular Property Prediction

VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use

General-Purpose Robotic Navigation via LVLM-Orchestrated Perception, Reasoning, and Acting

A Clinically-Grounded Two-Stage Framework for Renal CT Report Generation

Generative Universal Verifier as Multimodal Meta-Reasoner

Beyond Visual Appearances: Privacy-sensitive Objects Identification via Hybrid Graph Reasoning

Benchmarking and Bridging Emotion Conflicts for Multimodal Emotion Reasoning

CapGeo: A Caption-Assisted Approach to Geometric Reasoning

SciVideoBench: Benchmarking Scientific Video Reasoning in Large Multimodal Models

Improving Chain-of-Thought Efficiency for Autoregressive Image Generation