视觉大模型 / VLM

MMRPT: MultiModal Reinforcement Pre-Training via Masked Vision-Dependent Reasoning

MMRPT：通过遮蔽视觉依赖推理的多模态强化预训练

Xuhui Zheng, Kang An, Ziliang Wang, Yuhang Wang, Faqiang Qian, Yichao Wu

机构 * SenseTime（秒速科技） 纠错

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

AI总结 MMRPT通过强化学习提升多模态预训练效果，利用视觉基础推理增强模型对视觉内容的理解能力。

Comments 7 pages, 1 figures

Seeing through Imagination: Learning Scene Geometry via Implicit Spatial World Modeling

通过想象看见：通过隐式空间世界建模学习场景几何

Meng Cao, Haokun Lin, Haoyuan Li, Haoran Tang, Rongtao Xu, Dong An, Xue Liu, Ian Reid, Xiaodan Liang

机构 * MBZUAI ； SYSU（南方科技大学） ； PKU（北京大学） ； Spatialtemporal AI（时空人工智能） 纠错

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

AI总结 本文提出MILO和RePE，通过隐式空间世界建模提升多模态大语言模型的空间推理能力。

Synthesizing Visual Concepts as Vision-Language Programs

合成视觉概念作为视觉-语言程序

Antonia Wüst, Wolfgang Stammer, Hikaru Shindo, Lukas Helff, Devendra Singh Dhami, Kristian Kersting

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

AI总结 本研究提出视觉-语言程序（VLP），结合视觉模型的感知灵活性与程序合成的系统推理能力，通过生成结构化视觉描述并编译成神经符号程序，提升复杂逻辑推理任务的性能。

SpatialGeo:Boosting Spatial Reasoning in Multimodal LLMs via Geometry-Semantics Fusion

SpatialGeo:通过几何-语义融合提升多模态大语言模型的空间推理能力

Jiajie Guo, Qingpeng Zhu, Jin Zeng, Xiaolong Wu, Changyong He, Weida Wang

机构 * School of Computer Science and Technology, Tongji University, Shanghai, China（计算机科学与技术学院，同济大学，上海，中国） 纠错

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

AI总结 SpatialGeo通过几何-语义融合提升多模态大语言模型的空间推理能力，实验表明在空间推理任务中准确率提升8.0%且内存消耗减少50%。

OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles

Yihe Deng, Hritik Bansal, Fan Yin, Nanyun Peng, Wei Wang, Kai-Wei Chang

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

Comments 23 pages, 11 figures, 8 tables

Struct2D: A Perception-Guided Framework for Spatial Reasoning in MLLMs

Fangrui Zhu, Hanhui Wang, Yiming Xie, Jing Gu, Tianye Ding, Jianwei Yang, Huaizu Jiang

机构 * Northeastern University（东北大学） ； Microsoft Research（微软研究院） ； University of Southern California（南加州大学） ； University of California, Santa Cruz（加州大学圣克鲁兹分校） 纠错

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

Comments NeurIPS 2025, code link: https://github.com/neu-vi/struct2d

Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks

Xu Zheng, Zihao Dongfang, Lutao Jiang, Boyuan Zheng, Yulong Guo, Zhenquan Zhang, Giuliano Albanese, Runyi Yang, Mengjiao Ma, Zixin Zhang, Chenfei Liao, Dingcheng Zhen, Yuanhuiyi Lyu, Yuqian Fu, Bin Ren, Linfeng Zhang, Danda Pani Paudel, Nicu Sebe, Luc Van Gool, Xuming Hu

专题命中 视觉推理 ：visual question answering(abstract)；grounding(abstract)；multimodal large language model(abstract)；分类 cs.CV

CIR-CoT: Towards Interpretable Composed Image Retrieval via End-to-End Chain-of-Thought Reasoning

Weihuang Lin, Yiwei Ma, Jiayi Ji, Xiaoshuai Sun, Rongrong Ji

机构 * Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University（教育部多媒体可信感知与高效计算重点实验室，厦门大学） 纠错

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

CaRDiff: Video Salient Object Ranking Chain of Thought Reasoning for Saliency Prediction with Diffusion

Yolo Yunlong Tang, Gen Zhan, Li Yang, Yiting Liao, Chenliang Xu

机构 * ByteDance（字节跳动） 纠错

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

Comments Accepted to AAAI 2025

Spatial Reasoning in Foundation Models: Benchmarking Object-Centric Spatial Understanding

Vahid Mirjalili, Ramin Giahi, Sriram Kollipara, Akshay Kekuda, Kehui Yao, Kai Zhao, Jianpeng Xu, Kaushiki Nag, Sinduja Subramaniam, Topojoy Biswas, Evren Korpeoglu, Kannan Achan

机构 * Walmart Global Tech（沃尔玛全球科技） 纠错

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

Comments 4 pages, NeurIPS Workshop SpaVLE

MARS2 2025 Challenge on Multimodal Reasoning: Datasets, Methods, Results, Discussion, and Outlook

Peng Xu, Shengwu Xiong, Jiajun Zhang, Yaxiong Chen, Bowen Zhou, Chen Change Loy, David A. Clifton, Kyoung Mu Lee, Luc Van Gool, Ruiming He, Ruilin Yao, Xinwei Long, Jirui Huang, Kai Tian, Sa Yang, Yihua Shao, Jin Feng, Yue Zhong, Jiakai Zhou, Cheng Tang, Tianyu Zou, Yifang Zhang, Junming Liang, Guoyou Li, Zhaoxiang Wang, Qiang Zhou, Yichen Zhao, Shili Xiong, Hyeongjin Nam, Jaerin Lee, Jaeyoung Chung, JoonKyu Park, Junghun Oh, Kanggeon Lee, Wooseok Lee, Juneyoung Ro, Turghun Osman, Can Hu, Chaoyang Liao, Cheng Chen, Chengcheng Han, Chenhao Qiu, Chong Peng, Cong Xu, Dailin Li, Feiyu Wang, Feng Gao, Guibo Zhu, Guopeng Tang, Haibo Lu, Han Fang, Han Qi, Hanxiao Wu, Haobo Cheng, Hongbo Sun, Hongyao Chen, Huayong Hu, Hui Li, Jiaheng Ma, Jiang Yu, Jianing Wang, Jie Yang, Jing He, Jinglin Zhou, Jingxuan Li, Josef Kittler, Lihao Zheng, Linnan Zhao, Mengxi Jia, Muyang Yan, Nguyen Thanh Thien, Pu Luo, Qi Li, Shien Song, Shijie Dong, Shuai Shao, Shutao Li, Taofeng Xue, Tianyang Xu, Tianyi Gao, Tingting Li, Wei Zhang, Weiyang Su, Xiaodong Dong, Xiao-Jun Wu, Xiaopeng Zhou, Xin Chen, Xin Wei, Xinyi You, Xudong Kang, Xujie Zhou, Xusheng Liu, Yanan Wang, Yanbin Huang, Yang Liu, Yang Yang, Yanglin Deng, Yashu Kang, Ye Yuan, Yi Wen, Yicen Tian, Yilin Tao, Yin Tang, Yipeng Lin, Yiqing Wang, Yiting Xi, Yongkang Yu, Yumei Li, Yuxin Qin, Yuying Chen, Yuzhe Cen, Zhaofan Zou, Zhaohong Liu, Zhehao Shen, Zhenglin Du, Zhengyang Li, Zhenni Huang, Zhenwei Shao, Zhilong Song, Zhiyong Feng, Zhiyu Wang, Zhou Yu, Ziang Li, Zihan Zhai, Zijian Zhang, Ziyang Peng, Ziyun Xiao, Zongshu Li

专题命中 视觉推理 ：visual reasoning(abstract)；visual question answering(abstract)；grounding(abstract)；分类 cs.CV

Comments ICCV 2025 MARS2 Workshop and Challenge "Multimodal Reasoning and Slow Thinking in the Large Model Era: Towards System 2 and Beyond''

ByDeWay: Boost Your multimodal LLM with DEpth prompting in a Training-Free Way

Rajarshi Roy, Devleena Das, Ankesh Banerjee, Arjya Bhattacharjee, Kousik Dasgupta, Subarna Tripathi

机构 * Kalyani Government Engineering College（卡利尼政府工程学院） ； Intel Labs（英特尔实验室） 纠错

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

Understanding Museum Exhibits using Vision-Language Reasoning

Ada-Astrid Balauca, Sanjana Garai, Stefan Balauca, Rasesh Udayakumar Shetty, Naitik Agrawal, Dhwanil Subhashbhai Shah, Yuqian Fu, Xi Wang, Kristina Toutanova, Danda Pani Paudel, Luc Van Gool

机构 * ETH Zürich, Switzerland（苏黎世联邦理工学院，瑞士） ； Indian Institute of Technology, Varanasi (IIT BHU)（印度瓦拉纳西理工学院（IIT BHU）） ； Google DeepMind（谷歌DeepMind） 纠错

专题命中 视觉推理 ：vision-language model(abstract)；LLaVA(abstract)；visual question answering(abstract)；分类 cs.CV

Comments Accepted at ICCV 2025

Teaching AI Stepwise Diagnostic Reasoning with Report-Guided Chain-of-Thought Learning

Yihong Luo, Wenwu He, Zhuo-Xu Cui, Dong Liang

机构 * Fujian University of Technology（福建工程学院） ； Fujian Provincial Key Laboratory of Big Data Mining and Applications（福建省大数据挖掘与应用重点实验室） ； Key Laboratory of Biomedical Imaging Science and System, Chinese Academy of Sciences（生物医学成像科学与系统重点实验室，中国科学院） 纠错

专题命中 视觉推理 ：vision-language model(abstract)；LLaVA(abstract)；grounding(abstract)；分类 cs.AI

REVEAL -- Reasoning and Evaluation of Visual Evidence through Aligned Language

Ipsita Praharaj, Yukta Butala, Badrikanath Praharaj, Yash Butala

机构 * Carnegie Mellon University（卡内基梅隆大学） ； VIT Bhopal（维捷商学院） 纠错

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

Comments 4 pages, 6 figures, International Conference on Computer Vision, ICCV 2025

Learning Only with Images: Visual Reinforcement Learning with Reasoning, Rendering, and Visual Feedback

Yang Chen, Yufan Shen, Wenxuan Huang, Sheng Zhou, Qunshu Lin, Xinyu Cai, Zhi Yu, Jiajun Bu, Botian Shi, Yu Qiao

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

Eyes Will Shut: A Vision-Based Next GPS Location Prediction Model by Reinforcement Learning from Visual Map Feed Back

Ruixing Zhang, Yang Zhang, Tongyu Zhu, Leilei Sun, Weifeng Lv

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

Unsupervised Visual Chain-of-Thought Reasoning via Preference Optimization

Kesen Zhao, Beier Zhu, Qianru Sun, Hanwang Zhang

机构 * Nanyang Technological University（南洋理工大学） ； Singapore Management University（新加坡管理大学） 纠错

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

Skywork-R1V3 Technical Report

Wei Shen, Jiangbo Pei, Yi Peng, Xuchen Song, Yang Liu, Jian Peng, Haofeng Sun, Yunzhuo Hao, Peiyu Wang, Jianhao Zhang, Yahui Zhou

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

MAPS: Advancing Multi-Modal Reasoning in Expert-Level Physical Science

Erle Zhu, Yadi Liu, Zhe Zhang, Xujun Li, Jin Zhou, Xinjie Yu, Minlie Huang, Hongning Wang

机构 * The Conversational AI (CoAI) Group（对话人工智能小组） ； Department of Computer Science & Technology（计算机科学与技术系） ； Department of Electrical Engineering（电子工程系） 纠错

专题命中 视觉推理 ：visual language model(abstract)；visual reasoning(abstract)；MLLM(abstract)；分类 cs.AI

Journal ref Proceedings of the 13th International Conference on Learning Representations (ICLR), 2025

Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model

Tianle Li, Jihai Zhang, Yongming Rao, Yu Cheng

机构 * The Chinese University of Hong Kong（香港中文大学） ； Tencent Hunyuan Research（腾讯文言研究院） 纠错

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

SAMJAM: Zero-Shot Video Scene Graph Generation for Egocentric Kitchen Videos

Joshua Li, Fernando Jose Pena Cantu, Emily Yu, Alexander Wong, Yuchen Cui, Yuhao Chen

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

Chain of Functions: A Programmatic Pipeline for Fine-Grained Chart Reasoning Data

Zijian Li, Jingjing Fu, Lei Song, Jiang Bian, Jun Zhang, Rui Wang

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

Comments Under review

ClawMachine: Learning to Fetch Visual Tokens for Referential Comprehension

Tianren Ma, Lingxi Xie, Yunjie Tian, Boyu Yang, Qixiang Ye

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

Comments ICLR 2025. Code is available at github.com/martian422/ClawMachine

Revisiting MLLMs: An In-Depth Analysis of Image Classification Abilities

Huan Liu, Lingyu Xiao, Jiangjiang Liu, Xiaofan Li, Ze Feng, Sen Yang, Jingdong Wang

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

Visual Transformation Telling

Wanqing Cui, Xin Hong, Yanyan Lan, Liang Pang, Jiafeng Guo, Xueqi Cheng

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

Toward Grounded Commonsense Reasoning

Minae Kwon, Hengyuan Hu, Vivek Myers, Siddharth Karamcheti, Anca Dragan, Dorsa Sadigh

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

Comments IEEE International Conference on Robotics and Automation 2024

Stabilizing On-Policy Distillation for MLLM Reasoning with Global Normalization

稳定基于策略的蒸馏用于多模态大语言模型推理的全局归一化

Dongze Hao, Zhiwei Jin, Chen Chen, Haonan Lu

机构 * OPPO AI Center（OPPO AI中心） 纠错

专题命中 视觉推理 ：MLLM(title)；分类 cs.CV、cs.LG

AI总结 针对策略蒸馏中异常状态导致梯度不稳定的问题，提出全局归一化蒸馏策略优化（GNDPO），通过将KL分数转化为批次级相对优势来稳定优化，提升多模态推理任务的训练鲁棒性和性能。

MM-Telco: Benchmarks and Multimodal Large Language Models for Telecom Applications

MM-Telco: 电信应用的多模态大语言模型基准与工具

Anshul Kumar, Gagan Raj Gupta, Manish Rai, Apu Chakraborty, Ashutosh Modi, Abdelaali Chaoub, Soumajit Pramanik, Moyank Giri, Yashwanth Holla, Sunny Kumar, M. V. Kiran Sooraj

机构 * IIT Bhilai（比哈尔理工学院） ； IIT Kanpur（坎pur理工学院） ； INPT（伊斯兰北方技术大学） 纠错

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

AI总结 本文提出MM-Telco，为电信领域设计的多模态基准和模型，旨在解决领域特定挑战，通过基准任务和实验验证提升大语言模型在电信中的性能。

Fake-HR1: Rethinking Reasoning of Vision Language Model for Synthetic Image Detection

Fake-HR1: 重新思考视觉语言模型在合成图像检测中的推理方式

Changjiang Jiang, Xinkuan Sha, Fengchang Yu, Jingjing Liu, Jian Liu, Mingqi Fang, Chenfeng Zhang, Wei Lu

机构 * Wuhan University（武汉大学） ； AntGroup（蚂蚁集团） ； Zhejiang University（浙江大学） 纠错

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

AI总结 Fake-HR1通过两阶段训练框架实现自适应推理，提升合成图像检测性能与效率，优于现有LLMs。

Comments Accepted by ICASSP 2026