大模型推理能力

Beyond Perception: Evaluating Abstract Visual Reasoning through Multi-Stage Task

Yanbei Jiang, Yihao Ding, Chao Lei, Jiayang Ao, Jey Han Lau, Krista A. Ehinger

专题命中 视觉空间推理 ：reasoning(title,abstract)；分类 cs.AI

Comments Accepted at ACL Findings

EPO: Explicit Policy Optimization for Strategic Reasoning in LLMs via Reinforcement Learning

Xiaoqian Liu, Ke Wang, Yongbin Li, Yuchuan Wu, Wentao Ma, Aobo Kong, Fei Huang, Jianbin Jiao, Junge Zhang

机构 * University of Chinese Academy of Sciences（中国科学院大学） ； Tongyi Lab（通义实验室） ； The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences（复杂系统认知与决策智能重点实验室，中国科学院自动化研究所） 纠错

专题命中 视觉空间推理 ：reasoning(title,abstract)；分类 cs.CL

Comments ACL2025 main

Plane Geometry Problem Solving with Multi-modal Reasoning: A Survey

Seunghyuk Cho, Zhenyue Qin, Yang Liu, Youngbin Choi, Seungbeom Lee, Dongwoo Kim

机构 * Graduate School of Artificial Intelligence, POSTECH（POSTECH人工智能研究生院） ； Department of Computer Science and Engineering, POSTECH（POSTECH计算机科学与工程系） ； Australian National University（澳大利亚国立大学） 纠错

专题命中 视觉空间推理 ：reasoning(title,abstract)；分类 cs.LG

Comments 18 pages

Real-Time Verification of Embodied Reasoning for Generative Skill Acquisition

Bo Yue, Shuqi Guo, Kaiyu Hu, Chujiao Wang, Benyou Wang, Kui Jia, Guiliang Liu

机构 * School of Data Science, The Chinese University of Hong Kong, Shenzhen（数据科学学院，香港中文大学（深圳）） 纠错

专题命中 视觉空间推理 ：reasoning(title,abstract)；分类 cs.AI

SceneLLM: Implicit Language Reasoning in LLM for Dynamic Scene Graph Generation

Hang Zhang, Zhuoling Li, Jun Liu

专题命中 视觉空间推理 ：reasoning(title,abstract)；分类 cs.AI

Comments 29 pages, 7 figures

SpaRE: Enhancing Spatial Reasoning in Vision-Language Models with Synthetic Data

Michael Ogezi, Freda Shi

机构 * University of Waterloo（滑铁卢大学） ； Vector Institute（向量研究所） 纠错

专题命中 视觉空间推理 ：reasoning(title,abstract)；分类 cs.AI

Think Hierarchically, Act Dynamically: Hierarchical Multi-modal Fusion and Reasoning for Vision-and-Language Navigation

Junrong Yue, Yifan Zhang, Chuan Qin, Bo Li, Xiaomin Lie, Xinlei Yu, Wenxin Zhang, Zhendong Zhao

机构 * City University of Hong Kong, Dongguan Campus（香港城市大学东莞校区） ； The University of Melbourne（墨尔本大学） ； Tsinghua University（清华大学） ； Baidu Inc.（百度公司） ； University of Chinese Academy of Science（中国科学院大学） ； National University of Singapore（新加坡国立大学） 纠错

专题命中 视觉空间推理 ：reasoning(title,abstract)；分类 cs.AI

Comments 11 pages, 4 figures, Submitted to ACM MM 2025

Embodied-R: Collaborative Framework for Activating Embodied Spatial Reasoning in Foundation Models via Reinforcement Learning

Baining Zhao, Ziyou Wang, Jianjie Fang, Chen Gao, Fanhang Man, Jinqiang Cui, Xin Wang, Xinlei Chen, Yong Li, Wenwu Zhu

专题命中 视觉空间推理 ：reasoning(title,abstract)；分类 cs.AI

Comments 12 pages, 5 figures

CameraBench: Benchmarking Visual Reasoning in MLLMs via Photography

I-Sheng Fang, Jun-Cheng Chen

专题命中 视觉空间推理 ：reasoning(title,abstract)；分类 cs.CL

SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models

Hardy Chen, Haoqin Tu, Fali Wang, Hui Liu, Xianfeng Tang, Xinya Du, Yuyin Zhou, Cihang Xie

专题命中 视觉空间推理 ：reasoning(title,abstract)；分类 cs.CL

TopV-Nav: Unlocking the Top-View Spatial Reasoning Potential of MLLM for Zero-shot Object Navigation

Linqing Zhong, Chen Gao, Zihan Ding, Yue Liao, Huimin Ma, Shifeng Zhang, Xu Zhou, Si Liu

专题命中 视觉空间推理 ：reasoning(title,abstract)；分类 cs.AI

Comments 10 pages

Mind the Gap: Benchmarking Spatial Reasoning in Vision-Language Models

Ilias Stogiannidis, Steven McDonagh, Sotirios A. Tsaftaris

专题命中 视觉空间推理 ：reasoning(title,abstract)；分类 cs.CL

Comments 8 main pages, 4 pages Appendix, 5 figures

Towards Understanding Distilled Reasoning Models: A Representational Approach

David D. Baek, Max Tegmark

专题命中 视觉空间推理 ：reasoning(title,abstract)；分类 cs.LG

Comments 13 pages, 9 figures

Journal ref ICLR 2025 Workshop on Building Trust in Language Models and Applications

SeqAfford: Sequential 3D Affordance Reasoning via Multimodal Large Language Model

Chunlin Yu, Hanqing Wang, Ye Shi, Haoyang Luo, Sibei Yang, Jingyi Yu, Jingya Wang

专题命中 视觉空间推理 ：reasoning(title,abstract)；分类 cs.AI

Long-Term Planning Around Humans in Domestic Environments with 3D Scene Graphs

Ermanno Bartoli, Dennis Rotondi, Kai O. Arras, Iolanda Leite

专题命中 视觉空间推理 ：planning(title,abstract)；分类 cs.AI

Comments 5 pages, 2 figures, 1 table

Visual Reasoning at Urban Intersections: FineTuning GPT-4o for Traffic Conflict Detection

Sari Masri, Huthaifa I. Ashqar, Mohammed Elhenawy

专题命中 视觉空间推理 ：reasoning(title,abstract)；分类 cs.CL

A Stepwise Distillation Learning Strategy for Non-differentiable Visual Programming Frameworks on Visual Reasoning Tasks

Wentao Wan, Nan Kang, Zeqing Wang, Zhuojie Yang, Liang Lin, Keze Wang

专题命中 视觉空间推理 ：reasoning(title,abstract)；分类 cs.AI

The Geometry of Numerical Reasoning: Language Models Compare Numeric Properties in Linear Subspaces

Ahmed Oumar El-Shangiti, Tatsuya Hiraoka, Hilal AlQuabeh, Benjamin Heinzerling, Kentaro Inui

专题命中 视觉空间推理 ：reasoning(title,abstract)；分类 cs.CL

What Is Missing in Multilingual Visual Reasoning and How to Fix It

Yueqi Song, Simran Khanuja, Graham Neubig

专题命中 视觉空间推理 ：reasoning(title,abstract)；分类 cs.CL

What Makes for Good Visual Instructions? Synthesizing Complex Visual Reasoning Instructions for Visual Instruction Tuning

Yifan Du, Hangyu Guo, Kun Zhou, Wayne Xin Zhao, Jinpeng Wang, Chuyuan Wang, Mingchen Cai, Ruihua Song, Ji-Rong Wen

专题命中 视觉空间推理 ：reasoning(title,abstract)；分类 cs.CL

Comments Accepted by COLING2025

RLS3: RL-Based Synthetic Sample Selection to Enhance Spatial Reasoning in Vision-Language Models for Indoor Autonomous Perception

Joshua R. Waite, Md. Zahid Hasan, Qisai Liu, Zhanhong Jiang, Chinmay Hegde, Soumik Sarkar

专题命中 视觉空间推理 ：reasoning(title,abstract)；分类 cs.LG

Comments ICCPS 2025 accepted paper, 10 pages, 9 figures

Improving Multimodal LLMs Ability In Geometry Problem Solving, Reasoning, And Multistep Scoring

Avinash Anand, Raj Jaiswal, Abhishek Dharmadhikari, Atharva Marathe, Harsh Parimal Popat, Harshil Mital, Kritarth Prasad, Rajiv Ratn Shah, Roger Zimmermann

专题命中 视觉空间推理 ：reasoning(title,abstract)；分类 cs.AI

Comments 15 pages

Coarse Correspondences Boost Spatial-Temporal Reasoning in Multimodal Language Model

Benlin Liu, Yuhao Dong, Yiqin Wang, Zixian Ma, Yansong Tang, Luming Tang, Yongming Rao, Wei-Chiu Ma, Ranjay Krishna

专题命中 视觉空间推理 ：reasoning(title,abstract)；分类 cs.LG

Comments project page: https://coarse-correspondence.github.io

XMask3D: Cross-modal Mask Reasoning for Open Vocabulary 3D Semantic Segmentation

Ziyi Wang, Yanbo Wang, Xumin Yu, Jie Zhou, Jiwen Lu

专题命中 视觉空间推理 ：reasoning(title,abstract)；分类 cs.AI

Comments Accepted to NeurIPS 2024

Multi-modal Situated Reasoning in 3D Scenes

Xiongkun Linghu, Jiangyong Huang, Xuesong Niu, Xiaojian Ma, Baoxiong Jia, Siyuan Huang

专题命中 视觉空间推理 ：reasoning(title,abstract)；分类 cs.AI

Comments Accepted by NeurIPS 2024 Datasets and Benchmarks Track. Project page: https://msr3d.github.io/

End-to-End Navigation with Vision Language Models: Transforming Spatial Reasoning into Question-Answering

Dylan Goetting, Himanshu Gaurav Singh, Antonio Loquercio

专题命中 视觉空间推理 ：reasoning(title)；planning(abstract)；分类 cs.CL

Untrained neural networks can demonstrate memorization-independent abstract reasoning

Tomer Barak, Yonatan Loewenstein

专题命中 视觉空间推理 ：reasoning(title,abstract)；分类 cs.AI

Journal ref Sci Rep 14, 27249 (2024)

Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models

Jiayu Wang, Yifei Ming, Zhenmei Shi, Vibhav Vineet, Xin Wang, Yixuan Li, Neel Joshi

专题命中 视觉空间推理 ：reasoning(title,abstract)；分类 cs.AI

Comments Accepted to NeurIPS 2024

Replace-then-Perturb: Targeted Adversarial Attacks With Visual Reasoning for Vision-Language Models

Jonggyu Jang, Hyeonsu Lyu, Jungyeon Koh, Hyun Jong Yang

专题命中 视觉空间推理 ：reasoning(title,abstract)；分类 cs.AI

Comments 13 pages, 5 figure

Zero-shot Object Navigation with Vision-Language Models Reasoning

Congcong Wen, Yisiyuan Huang, Hao Huang, Yanjia Huang, Shuaihang Yuan, Yu Hao, Hui Lin, Yu-Shen Liu, Yi Fang

专题命中 视觉空间推理 ：reasoning(title,abstract)；分类 cs.AI

Comments Accepted by the International Conference on Pattern Recognition (ICPR) for Oral presentation