视觉大模型 / VLM

Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas

Shiqi Chen, Tongyao Zhu, Ruochen Zhou, Jinghan Zhang, Siyang Gao, Juan Carlos Niebles, Mor Geva, Junxian He, Jiajun Wu, Manling Li

机构 * City University of Hong Kong（香港城市大学） ； National University of Singapore（新加坡国立大学） ； Hong Kong University of Science（香港科学大学） ； Stanford University（斯坦福大学） ； Salesforce Research（Salesforce研究） ； Tel Aviv University（特拉维夫大学） ； Northwestern University（西北大学） 纠错

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

Comments ICML 2025

Scaling Code-Assisted Chain-of-Thoughts and Instructions for Model Reasoning

Honglin Lin, Qizhi Pei, Xin Gao, Zhuoshi Pan, Yu Li, Juntao Li, Conghui He, Lijun Wu

机构 * OpenDataLab, Shanghai Artificial Intelligence Laboratory（OpenDataLab，上海人工智能实验室） ； Shanghai Jiao Tong University（上海交通大学） ； Soochow University（苏州大学） 纠错

专题命中 视觉推理 ：grounding(abstract)

Comments Accepted by NeurIPS2025

Training-free Task-oriented Grasp Generation

Jiaming Wang, Diwen Liu, Jizhuo Chen, Harold Soh

专题命中 视觉推理 ：vision-language model(abstract)

Comments Jiaming Wang, Diwen Liu, and Jizhuo Chen contributed equally

Voice Evaluation of Reasoning Ability: Diagnosing the Modality-Induced Performance Gap

Yueqian Lin, Zhengmian Hu, Qinsi Wang, Yudong Liu, Hengfan Zhang, Jayakumar Subramanian, Nikos Vlassis, Hai Helen Li, Yiran Chen

机构 * Duke University（杜克大学） ； Adobe 纠错

专题命中 视觉推理 ：grounding(abstract)

Comments Code and data available at https://github.com/linyueqian/VERA

SONAR: Semantic-Object Navigation with Aggregated Reasoning through a Cross-Modal Inference Paradigm

Yao Wang, Zhirui Sun, Wenzheng Chi, Baozhi Jia, Wenjun Xu, Jiankun Wang

机构 * Shenzhen Key Laboratory of Robotics Perception and Intelligence（机器人感知与智能深圳重点实验室） ； Department of Electronic and Electrical Engineering（电子与电气工程系） ； Southern University of Science and Technology（南方科技大学） ； Research Institute of Multiple Agents and Embodied Intelligence（多智能体与具身智能研究院） ； Peng Cheng Laboratory（鹏城实验室） ； Robotics and Microsystems Center（机器人与微系统中心） ； School of Mechanical and Electric Engineering（机械与电子工程学院） ； Soochow University（苏州大学） ； Xiamen Key Laboratory of Visual Perception Technology and Application（视觉感知技术与应用厦门重点实验室） ； Reconova Information Technology Co., Ltd.（Reconova信息技术有限公司） 纠错

专题命中 视觉推理 ：vision-language model(abstract)

Ko-PIQA: A Korean Physical Commonsense Reasoning Dataset with Cultural Context

Dasol Choi, Jungwhan Kim, Guijin Son

专题命中 视觉推理 ：grounding(abstract)

Beyond Classification: Towards Speech Emotion Reasoning with Multitask AudioLLMs

Wenyu Zhang, Yingxu He, Geyu Lin, Zhuohan Liu, Shuo Sun, Bin Wang, Xunlong Zou, Jeremy H. M. Wong, Qiongqiong Wang, Hardik B. Sailor, Nancy F. Chen, Ai Ti Aw

机构 * Institute for Infocomm Research (I 2 {}^{\text{2}} R), Agency for Science, Technology and Research (A*STAR)（信息与通信研究机构（I2R），科技研究局（A*STAR）） ； Centre for Frontier AI Research (CFAR), Agency for Science, Technology and Research (A*STAR)（前沿人工智能研究中心（CFAR），科技研究局（A*STAR）） 纠错

专题命中 视觉推理 ：grounding(abstract)

InSpire: Vision-Language-Action Models with Intrinsic Spatial Reasoning

Ji Zhang, Shihan Wu, Xu Luo, Hao Wu, Lianli Gao, Heng Tao Shen, Jingkuan Song

机构 * Southwest Jiaotong University（西南交通大学） ； University of Electronic Science and Technology of China（电子科技大学） ； Tongji University（同济大学） 纠错

专题命中 视觉推理 ：vision-language model(abstract)

VIVA+: Human-Centered Situational Decision-Making

Zhe Hu, Yixiao Ren, Guanzhong Liu, Jing Li, Yu Yin

机构 * Department of Computing, The Hong Kong Polytechnic University（香港理工大学计算机系） ； Research Centre for Data Science & Artificial Intelligence（数据科学与人工智能研究中心） ； Department of Computer and Data Sciences, Case Western Reserve University（凯斯西储大学计算机与数据科学系） 纠错

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

Comments EMNLP 2025 Findings

Towards an AI Musician: Synthesizing Sheet Music Problems for Musical Reasoning

Zhilin Wang, Zhe Yang, Yun Luo, Yafu Li, Xiaoye Qu, Ziqian Qiao, Haoran Zhang, Runzhe Zhan, Derek F. Wong, Jizhe Zhou, Yu Cheng

机构 * University of Science and Technology of China（中国科学技术大学） ； Shanghai AI Laboratory（上海人工智能实验室） ； Sichuan University（四川大学） ； Shanghai Jiao Tong University（上海交通大学） ； University of Macau（澳门大学） ； Tsinghua University（清华大学） ； The Chinese University of Hong Kong（香港中文大学） 纠错

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

Comments 34 pages

DRISHTIKON: A Multimodal Multilingual Benchmark for Testing Language Models' Understanding on Indian Culture

Arijit Maji, Raghvendra Kumar, Akash Ghosh, Anushka, Nemil Shah, Abhilekh Borah, Vanshika Shah, Nishant Mishra, Sriparna Saha

机构 * Indian Institute of Technology Patna（印度理工学院帕纳巴分校） ； Banasthali Vidyapeeth University（班纳萨利大学） ； Pandit Deendayal Energy University（德英德能源大学） ； Manipal University Jaipur（马哈拉施特拉邦大学贾伊普尔分校） ； Dwarkadas J. Sanghvi College of Engineering（德瓦尔卡斯J.桑格维工程学院） 纠错

专题命中 视觉推理 ：vision-language model(abstract)

Comments EMNLP MAINS 2025

Imagination at Inference: Synthesizing In-Hand Views for Robust Visuomotor Policy Inference

Haoran Ding, Anqing Duan, Zezhou Sun, Dezhen Song, Yoshihiko Nakamura

机构 * Department of Robotics, Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)（机器人系，Mohamed bin Zayed人工智能大学） 纠错

专题命中 视觉推理 ：visual reasoning(abstract)

Comments Submitted to IEEE for possible publication, under review

MolmoAct: Action Reasoning Models that can Reason in Space

Jason Lee, Jiafei Duan, Haoquan Fang, Yuquan Deng, Shuo Liu, Boyang Li, Bohan Fang, Jieyu Zhang, Yi Ru Wang, Sangho Lee, Winson Han, Wilbert Pumacay, Angelica Wu, Rose Hendrix, Karen Farley, Eli VanderBilt, Ali Farhadi, Dieter Fox, Ranjay Krishna

机构 * Allen Institute for AI（艾伦人工智能研究所） ； University of Washington（华盛顿大学） 纠错

专题命中 视觉推理 ：grounding(abstract)

Comments Updated GR00T result to N1.5

Memory-Anchored Multimodal Reasoning for Explainable Video Forensics

Chen Chen, Runze Li, Zejun Zhang, Pukun Zhao, Fanqing Zhou, Longxiang Wang, Haojian Huang

专题命中 视觉推理 ：grounding(abstract)

Domain-Conditioned Scene Graphs for State-Grounded Task Planning

Jonas Herzog, Jiangpin Liu, Yue Wang

机构 * Zhejiang University（浙江大学） 纠错

专题命中 视觉推理 ：grounding(abstract)

Comments Accepted for IROS 2025

Rethinking Denial-of-Service: A Conditional Taxonomy Unifying Availability and Sustainability Threats

Mark Dorsett, Scott Man, Tim Koussas

专题命中 视觉推理 ：grounding(abstract)

Comments 7 pages, 3 figures, 3 tables,

QU-NLP at QIAS 2025 Shared Task: A Two-Phase LLM Fine-Tuning and Retrieval-Augmented Generation Approach for Islamic Inheritance Reasoning

Mohammad AL-Smadi

机构 * Qatar University（卡塔尔大学） 纠错

专题命中 视觉推理 ：grounding(abstract)

ContextualLVLM-Agent: A Holistic Framework for Multi-Turn Visually-Grounded Dialogue and Complex Instruction Following

Seungmin Han, Haeun Kwon, Ji-jun Park, Taeyang Yoon

机构 * Dongguk University（东国大学） 纠错

专题命中 视觉推理 ：vision-language model(abstract)

Robust Symbolic Reasoning for Visual Narratives via Hierarchical and Semantically Normalized Knowledge Graphs

Yi-Chun Chen

机构 * Yale University（耶鲁大学） 纠错

专题命中 视觉推理 ：grounding(abstract)

Comments 12 pages, 4 figures, 2 tables. Extends our earlier framework on hierarchical narrative graphs with a semantic normalization module

From Templates to Natural Language: Generalization Challenges in Instruction-Tuned LLMs for Spatial Reasoning

Chalamalasetti Kranti, Sherzod Hakimov, David Schlangen

机构 * Computational Linguistics, Department of Linguistics University of Potsdam（乌特雷赫特大学语言学系计算语言学部） ； German Research Center for Artificial Intelligence (DFKI), Berlin（德国人工智能研究中心（DFKI）柏林） 纠错

专题命中 视觉推理 ：grounding(abstract)

Comments 17 pages

BigCharts-R1: Enhanced Chart Reasoning with Visual Reinforcement Finetuning

Ahmed Masry, Abhay Puri, Masoud Hashemi, Juan A. Rodriguez, Megh Thakkar, Khyati Mahajan, Vikas Yadav, Sathwik Tejaswi Madhusudhan, Alexandre Piché, Dzmitry Bahdanau, Christopher Pal, David Vazquez, Enamul Hoque, Perouz Taslakian, Sai Rajeswar, Spandana Gella

专题命中 视觉推理 ：vision-language model(abstract)

VisFinEval: A Scenario-Driven Chinese Multimodal Benchmark for Holistic Financial Understanding

Zhaowei Liu, Xin Guo, Haotian Xia, Lingfeng Zeng, Fangqi Lou, Jinyi Niu, Mengping Li, Qi Qi, Jiahuan Li, Wei Zhang, Yinglong Wang, Weige Cai, Weining Shen, Liwen Zhang

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

GM-PRM: A Generative Multimodal Process Reward Model for Multimodal Mathematical Reasoning

Jianghangfan Zhang, Yibo Yan, Kening Zheng, Xin Zou, Song Dai, Xuming Hu

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

Towards Zero-Shot Terrain Traversability Estimation: Challenges and Opportunities

Ida Germann, Mark O. Mints, Peer Neubert

机构 * Intelligent Autonomous Systems Group, Institute of Computational Visualisitics, University of Koblenz（智能自主系统组，计算可视化研究所，科隆大学） 纠错

专题命中 视觉推理 ：vision-language model(abstract)

Comments Accepted and presented at the 1st German Robotics Conference (GRC); March 13-15, 2025, Nuremberg, Germany https://ras.papercept.net/conferences/conferences/GRC25/program/GRC25_ContentListWeb_3.html#sada_48

ISO-Bench: Benchmarking Multimodal Causal Reasoning in Visual-Language Models through Procedural Plans

Ananya Sadana, Yash Kumar Lal, Jiawei Zhou

机构 * Stony Brook University（石溪大学） 纠错

专题命中 视觉推理 ：vision-language model(abstract)

Zero-shot Performance of Generative AI in Brazilian Portuguese Medical Exam

Cesar Augusto Madid Truyts, Amanda Gomes Rabelo, Gabriel Mesquita de Souza, Daniel Scaldaferri Lages, Adriano Jose Pereira, Uri Adrian Prync Flato, Eduardo Pontes dos Reis, Joaquim Edson Vieira, Paulo Sergio Panse Silveira, Edson Amaro Junior

机构 * Einstein Global Advanced Technologies for Equity（埃因斯坦全球先进科技以公平为宗旨） ； Hospital Israelita Albert Einstein（埃因斯坦医院） ； Departamento de Pacientes Graves（重症患者部门） ； Stanford Center for Artificial Intelligence in Medicine and Imaging（斯坦福大学医学与成像人工智能中心） ； Departmento de Cirurgia（外科部门） ； Faculdade de Medicina, Universidade de São Paulo（圣保罗大学医学院） ； Faculdade Israelita de Ciências da Saúde Albert Einstein（埃因斯坦以色列健康科学学院） 纠错

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

From Answers to Rationales: Self-Aligning Multimodal Reasoning with Answer-Oriented Chain-of-Thought

Wentao Tan, Qiong Cao, Yibing Zhan, Chao Xue, Changxing Ding

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

Making VLMs More Robot-Friendly: Self-Critical Distillation of Low-Level Procedural Reasoning

Chan Young Park, Jillian Fisher, Marius Memmel, Dipika Khullar, Seoho Yun, Abhishek Gupta, Yejin Choi

专题命中 视觉推理 ：vision-language model(abstract)

Comments Code Available: https://github.com/chan0park/SelfReVision

DyG-RAG: Dynamic Graph Retrieval-Augmented Generation with Event-Centric Reasoning

Qingyun Sun, Jiaqi Yuan, Shan He, Xiao Guan, Haonan Yuan, Xingcheng Fu, Jianxin Li, Philip S. Yu

机构 * Beihang University（北航大学） ； Guangxi Normal University（广西师范大学） ； University of Illinois Chicago（伊利诺伊大学芝加哥分校） 纠错

专题命中 视觉推理 ：grounding(abstract)

The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs

Jierun Chen, Tiezheng Yu, Haoli Bai, Lewei Yao, Jiannan Wu, Kaican Li, Fei Mi, Chaofan Tao, Lei Zhu, Manyi Zhang, Xiaohui Li, Lu Hou, Lifeng Shang, Qun Liu

机构 * Huawei Technologies（华为技术有限公司） ； HKUST（香港科技大学） 纠错

专题命中 视觉推理 ：vision-language model(abstract)