机器人 / 具身智能 - arXivDaily 专题

2507.21513 2025-07-30 cs.AI cs.CL 79%

What Does it Mean for a Neural Network to Learn a "World Model"?

Kenneth Li, Fernanda Viégas, Martin Wattenberg

机构 * Harvard University（哈佛大学）

专题命中具身推理：world model(title,abstract)；分类 cs.AI

2507.20832 2025-07-29 cs.RO 79%

Hanging Around: Cognitive Inspired Reasoning for Reactive Robotics

Mihai Pomarlan, Stefano De Giorgis, Rachel Ringe, Maria M. Hedblom, Nikolaos Tsiogkas

机构 * Applied Linguistics Department University of Bremen（应用语言学系比勒feld大学）； Digital Media Lab University of Bremen（数字媒体实验室比勒feld大学）； Department of Computer Science KU Leuven（计算机科学系卢森堡大学）

专题命中具身推理：robotics(title,abstract)；分类 cs.RO

Comments This article is published online with Open Access by IOS Press and distributed under the terms of the Creative Commons Attribution Non-Commercial License 4.0 (CC BY-NC 4.0)

Journal ref Frontiers in Artificial Intelligence and Applications; 2024; Vol. 394; pp. 2 - 15

2507.19468 2025-07-28 cs.CV 79%

Back to the Features: DINO as a Foundation for Video World Models

Federico Baldassarre, Marc Szafraniec, Basile Terver, Vasil Khalidov, Francisco Massa, Yann LeCun, Patrick Labatut, Maximilian Seitzer, Piotr Bojanowski

机构 * Meta FAIR

专题命中具身推理：world model(title,abstract)；分类 cs.CV

2507.15521 2025-07-22 cs.AI 79%

LLM world models are mental: Output layer evidence of brittle world model use in LLM mechanical reasoning

Cole Robertson, Philip Wolff

专题命中具身推理：world model(title,abstract)；分类 cs.AI

Comments Manuscript comprises 14 pages, 4 figures, 4 tables in the Technical Appendix and Supplementary Material, and is under review at NeurIPS 2025

2505.01729 2025-07-21 cs.CV 79%

PosePilot: Steering Camera Pose for Generative World Models with Self-supervised Depth

Bu Jin, Weize Li, Baihan Yang, Zhenxin Zhu, Junpeng Jiang, Huan-ang Gao, Haiyang Sun, Kun Zhan, Hengtong Hu, Xueyang Zhang, Peng Jia, Hao Zhao

机构 * The Hong Kong University of Science and Technology（香港科技大学）； Institute for AI Industry Research (AIR), Tsinghua University（清华大学人工智能产业研究院）； Li Auto ； BAAI（北京人工智能研究院）

专题命中具身推理：world model(title,abstract)；分类 cs.CV

Comments Accepted at IEEE/RSJ IROS 2025

2501.00226 2025-07-17 cs.AI cs.CL 79%

Generative Emergent Communication: Large Language Model is a Collective World Model

Tadahiro Taniguchi, Ryo Ueda, Tomoaki Nakamura, Masahiro Suzuki, Akira Taniguchi

机构 * Graduate School of Informatics, Kyoto University（京都大学信息科学研究生院）； Graduate School of Engineering, The University of Tokyo（东京大学工学研究生院）； Graduate School of Informatics and Engineering, The University of Electro-Communications（电通大学信息科学和工学研究生院）； College of Information Science and Engineering, Ritsumeikan University（立命馆大学信息科学和工学学院）

专题命中具身推理：world model(title,abstract)；分类 cs.AI

2507.10539 2025-07-15 cs.LG 79%

Graph World Model

Tao Feng, Yexin Wu, Guanyu Lin, Jiaxuan You

机构 * Department of Computer Science, University of Illinois Urbana Champaign Urbana, IL, USA（计算机科学系，伊利诺伊大学厄巴纳-香槟分校）

专题命中具身推理：world model(title,abstract)；分类 cs.LG

2503.20124 2025-07-15 cs.AI 79%

Synthesizing world models for bilevel planning

Zergham Ahmed, Joshua B. Tenenbaum, Christopher J. Bates, Samuel J. Gershman

专题命中具身推理：world model(title,abstract)；分类 cs.AI

Comments Accepted to TMLR

2507.00603 2025-07-02 cs.CV 79%

World4Drive: End-to-End Autonomous Driving via Intention-aware Physical Latent World Model

Yupeng Zheng, Pengxuan Yang, Zebin Xing, Qichao Zhang, Yuhang Zheng, Yinfeng Gao, Pengfei Li, Teng Zhang, Zhongpu Xia, Peng Jia, Dongbin Zhao

机构 * CASIA（中国科学院自动化研究所）； Li Auto（力汽车）； PCL（鹏城实验室）； NUS（新加坡国立大学）； Tsinghua（清华大学）

专题命中具身推理：world model(title,abstract)；分类 cs.CV

Comments ICCV 2025, first version

2506.24113 2025-07-01 cs.CV 79%

Epona: Autoregressive Diffusion World Model for Autonomous Driving

Kaiwen Zhang, Zhenyu Tang, Xiaotao Hu, Xingang Pan, Xiaoyang Guo, Yuan Liu, Jingwei Huang, Li Yuan, Qian Zhang, Xiao-Xiao Long, Xun Cao, Wei Yin

机构 * Horizon Robotics ； Tsinghua University（清华大学）； Peking University（北京大学）； Nanjing University（南京大学）； The Hong Kong University of Science and Technology（香港科学与技术大学）； Nanyang Technological University（南洋理工大学）； Tencent Hunyuan（腾讯文心）

专题命中具身推理：world model(title,abstract)；分类 cs.CV

Comments ICCV2025, Project Page: https://kevin-thu.github.io/Epona/

2506.19055 2025-06-25 eess.IV cs.CV 79%

Xray2Xray: World Model from Chest X-rays with Volumetric Context

Zefan Yang, Xinrui Song, Xuanang Xu, Yongyi Shi, Ge Wang, Mannudeep K. Kalra, Pingkun Yan

机构 * Department of Biomedical Engineering（生物医学工程系）； Center for Biotechnology（生物技术中心）； Interdisciplinary Studies（跨学科研究）； Rensselaer Polytechnic Institute（伦塞拉尔理工大学）； Department of Radiology（放射科）； Massachusetts General Hospital（麻省总医院）； Harvard Medical School（哈佛医学院）

专题命中具身推理：world model(title,abstract)；分类 cs.CV

2506.18537 2025-06-24 cs.LG cs.MA 79%

Transformer World Model for Sample Efficient Multi-Agent Reinforcement Learning

Azad Deihim, Eduardo Alonso, Dimitra Apostolopoulou

机构 * Artificial Intelligence Research Centre (CitAI), City St George’s, University of London（人工智能研究中心（CitAI）、圣乔治大学）； Oxford Institute for Energy Studies (OIES), University of Oxford（牛津能源研究所（OIES）、牛津大学）

专题命中具身推理：world model(title,abstract)；分类 cs.LG

2506.13260 2025-06-17 cs.CV 79%

COME: Adding Scene-Centric Forecasting Control to Occupancy World Model

Yining Shi, Kun Jiang, Qiang Meng, Ke Wang, Jiabao Wang, Wenchao Sun, Tuopu Wen, Mengmeng Yang, Diange Yang

机构 * School of Vehicle and Mobility, Tsinghua University（清华大学车辆与移动系统学院）； State Key Laboratory of Intelligent Green Vehicle and Mobility（智能绿色车辆与移动系统国家重点实验室）； Kargobot Inc（Kargobot公司）； Nankai University（南开大学）

专题命中具身推理：world model(title,abstract)；分类 cs.CV

2502.00466 2025-06-17 cs.LG 79%

EDELINE: Enhancing Memory in Diffusion-based World Models via Linear-Time Sequence Modeling

Jia-Hua Lee, Bor-Jiun Lin, Wei-Fang Sun, Chun-Yi Lee

机构 * Department of Computer Science, National Tsing Hua University（国立清华大学计算机科学系）； Department of Computer Science, National Taiwan University（国立台湾大学计算机科学系）； NVIDIA AI Technology Center (NVAITC), NVIDIA Corporation（NVIDIA人工智能技术中心）

专题命中具身推理：world model(title,abstract)；分类 cs.LG

Comments 31 pages

2506.07450 2025-06-10 cs.AI 79%

Efficient Generation of Diverse Cooperative Agents with World Models

Yi Loo, Akshunn Trivedi, Malika Meghjani

机构 * Singapore University of Technology and Design（新加坡科技设计大学）

专题命中具身推理：world model(title,abstract)；分类 cs.AI

2502.01366 2025-06-10 cs.LG 79%

Trajectory World Models for Heterogeneous Environments

Shaofeng Yin, Jialong Wu, Siqiao Huang, Xingjian Su, Xu He, Jianye Hao, Mingsheng Long

专题命中具身推理：world model(title,abstract)；分类 cs.LG

Comments ICML 2025. Code is available at https://github.com/thuml/TrajWorld

2506.06355 2025-06-10 cs.CY cs.CE cs.CL cs.CV 79%

LLMs as World Models: Data-Driven and Human-Centered Pre-Event Simulation for Disaster Impact Assessment

Lingyao Li, Dawei Li, Zhenhui Ou, Xiaoran Xu, Jingxiao Liu, Zihui Ma, Runlong Yu, Min Deng

机构 * University of South Florida（佛罗里达州立大学）； Arizona State University（亚利桑那州立大学）； Massachusetts Institute of Technology（麻省理工学院）； New York University（纽约大学）； University of Alabama（阿拉巴马大学）； Texas Tech University（德克萨斯科技大学）

专题命中具身推理：world model(title,abstract)；分类 cs.CV

2506.05284 2025-06-06 cs.CV 79%

Video World Models with Long-term Spatial Memory

Tong Wu, Shuai Yang, Ryan Po, Yinghao Xu, Ziwei Liu, Dahua Lin, Gordon Wetzstein

机构 * Stanford University（斯坦福大学）； Shanghai Jiao Tong University（上海交通大学）； The Chinese University of Hong Kong（香港中文大学）； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）； S-Lab, Nanyang Technological University（南洋理工大学S实验室）

专题命中具身推理：world model(title,abstract)；分类 cs.CV

Comments Project page: https://spmem.github.io/

2506.02996 2025-06-04 cs.AI 79%

Linear Spatial World Models Emerge in Large Language Models

Matthieu Tehenan, Christian Bolivar Moya, Tenghai Long, Guang Lin

专题命中具身推理：world model(title,abstract)；分类 cs.AI

2506.02327 2025-06-04 cs.CV 79%

Medical World Model: Generative Simulation of Tumor Evolution for Treatment Planning

Yijun Yang, Zhao-Yang Wang, Qiuping Liu, Shuwen Sun, Kang Wang, Rama Chellappa, Zongwei Zhou, Alan Yuille, Lei Zhu, Yu-Dong Zhang, Jieneng Chen

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））； Johns Hopkins University（约翰霍普金斯大学）； The First Affiliated Hospital of Nanjing Medical University（南京医科大学第一附属医院）； University of California, San Francisco（加州大学旧金山分校）

专题命中具身推理：world model(title,abstract)；分类 cs.CV

2506.01546 2025-06-03 cs.CV 79%

LongDWM: Cross-Granularity Distillation for Building a Long-Term Driving World Model

Xiaodong Wang, Zhirong Wu, Peixi Peng

机构 * Peking University（北京大学）； Peng Cheng Laboratory（鹏城实验室）

专题命中具身推理：world model(title,abstract)；分类 cs.CV

Comments project homepage: https://wang-xiaodong1899.github.io/longdwm/

2506.01103 2025-06-03 cs.CV 79%

DeepVerse: 4D Autoregressive Video Generation as a World Model

Junyi Chen, Haoyi Zhu, Xianglong He, Yifan Wang, Jianjun Zhou, Wenzheng Chang, Yang Zhou, Zizun Li, Zhoujie Fu, Jiangmiao Pang, Tong He

机构 * SJTU（上海交通大学）； Shanghai AI Lab（上海人工智能实验室）； USTC（中国科学技术大学）； THU（清华大学）； ZJU（浙江大学）； FDU（福建师范大学）； NTU（国立台湾大学）

专题命中具身推理：world model(title,abstract)；分类 cs.CV

2506.00417 2025-06-03 cs.AI 79%

World Models for Cognitive Agents: Transforming Edge Intelligence in Future Networks

Changyuan Zhao, Ruichen Zhang, Jiacheng Wang, Gaosheng Zhao, Dusit Niyato, Geng Sun, Shiwen Mao, Dong In Kim

机构 * College of Computing and Data Science, Nanyang Technological University（计算与数据科学学院，南洋理工大学）； College of Computer Science and Technology, Jilin University（计算机科学与技术学院，吉林大学）； Department of Electrical and Computer Engineering, Auburn University（电气与计算机工程系，阿伯茨罕大学）； Department of Electrical and Computer Engineering, Sungkyunkwan University（电气与计算机工程系，成均馆大学）

专题命中具身推理：world model(title,abstract)；分类 cs.AI

Comments 7 pages, 4 figures

2505.20171 2025-05-27 cs.CV 79%

Long-Context State-Space Video World Models

Ryan Po, Yotam Nitzan, Richard Zhang, Berlin Chen, Tri Dao, Eli Shechtman, Gordon Wetzstein, Xun Huang

机构 * Stanford University（斯坦福大学）； Princeton University（普林斯顿大学）； Adobe Research（Adobe研究）

专题命中具身推理：world model(title,abstract)；分类 cs.CV

Comments Project website: https://ryanpo.com/ssm_wm

2505.18650 2025-05-27 cs.CV 79%

ProphetDWM: A Driving World Model for Rolling Out Future Actions and Videos

Xiaodong Wang, Peixi Peng

机构 * Peking University（北京大学）； Peng Cheng Laboratory（鹏城实验室）

专题命中具身推理：world model(title,abstract)；分类 cs.CV

Comments 9 pages, 7 figures

2504.13936 2025-05-21 cs.HC cs.LG cs.SY eess.SY 79%

ViMo: A Generative Visual GUI World Model for App Agents

Dezhao Luo, Bohan Tang, Kang Li, Georgios Papoudakis, Jifei Song, Shaogang Gong, Jianye Hao, Jun Wang, Kun Shao

机构 * Queen Mary University of London（伦敦女王学院）； University of Oxford（牛津大学）； Huawei Noah’s Ark Lab（华为诺亚实验室）； University College London（伦敦大学学院）

专题命中具身推理：world model(title,abstract)；分类 cs.LG

Comments https://ai-agents-2030.github.io/ViMo/

2502.04728 2025-05-09 cs.AI 79%

Generating Symbolic World Models via Test-time Scaling of Large Language Models

Zhouliang Yu, Yuhuan Yuan, Tim Z. Xiao, Fuxiang Frank Xia, Jie Fu, Ge Zhang, Ge Lin, Weiyang Liu

机构 * Westlake University（西湖大学）； The Chinese University of Hong Kong（香港中文大学）； The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））； Max Planck Institute for Intelligent Systems, Tübingen（智能系统马克斯·普朗克研究所（图宾根））； Environmental Systems Research Institute, Inc.（环境系统研究所）； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）； SEED, Bytedance（字节跳动SEED团队）； The Hong Kong University of Science and Technology（香港科技大学）

专题命中具身推理：world model(title,abstract)；分类 cs.AI

Comments Accepted by TMLR2025 (32 pages, 6 figures)

Journal ref Transactions on Machine Learning Research, 2025

2505.02074 2025-05-06 cs.LG stat.ML 79%

Learning Local Causal World Models with State Space Models and Attention

Francesco Petri, Luigi Asprino, Aldo Gangemi

机构 * Institute for Cognitive Sciences and Technologies, National Research Council（认知科学与技术研究所，国家科研理事会）； Sapienza University of Rome（罗马大学）； University of Bologna（博洛尼亚大学）

专题命中具身推理：world model(title,abstract)；分类 cs.LG

2504.15785 2025-04-23 cs.AI 79%

WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents

Siyu Zhou, Tianyi Zhou, Yijun Yang, Guodong Long, Deheng Ye, Jing Jiang, Chengqi Zhang

机构 * Australian AI Institute, Faculty of Engineering and IT, University of Technology Sydney（澳大利亚人工智能研究所，工程与信息学院，悉尼大学）； Department of Computer Science, University of Maryland, College Park（计算机科学系，马里兰大学，College Park）； Tencent, China（腾讯，中国）

专题命中具身推理：world model(title,abstract)；分类 cs.AI

Comments Code is available at https://github.com/elated-sawyer/WALL-E

2504.13820 2025-04-21 cs.CV 79%

CheXWorld: Exploring Image World Modeling for Radiograph Representation Learning

Yang Yue, Yulin Wang, Chenxin Tao, Pan Liu, Shiji Song, Gao Huang

机构 * Tsinghua University（清华大学）； PLA General Hospital（中国人民解放军总医院）

专题命中具身推理：world model(title,abstract)；分类 cs.CV

Comments Accepted by CVPR 2025

1. 具身推理 3091 篇

What Does it Mean for a Neural Network to Learn a "World Model"?

Hanging Around: Cognitive Inspired Reasoning for Reactive Robotics

Back to the Features: DINO as a Foundation for Video World Models

LLM world models are mental: Output layer evidence of brittle world model use in LLM mechanical reasoning

PosePilot: Steering Camera Pose for Generative World Models with Self-supervised Depth

Generative Emergent Communication: Large Language Model is a Collective World Model

Graph World Model

Synthesizing world models for bilevel planning

World4Drive: End-to-End Autonomous Driving via Intention-aware Physical Latent World Model

Epona: Autoregressive Diffusion World Model for Autonomous Driving

Xray2Xray: World Model from Chest X-rays with Volumetric Context

Transformer World Model for Sample Efficient Multi-Agent Reinforcement Learning

COME: Adding Scene-Centric Forecasting Control to Occupancy World Model

EDELINE: Enhancing Memory in Diffusion-based World Models via Linear-Time Sequence Modeling

Efficient Generation of Diverse Cooperative Agents with World Models

Trajectory World Models for Heterogeneous Environments

LLMs as World Models: Data-Driven and Human-Centered Pre-Event Simulation for Disaster Impact Assessment

Video World Models with Long-term Spatial Memory

Linear Spatial World Models Emerge in Large Language Models

Medical World Model: Generative Simulation of Tumor Evolution for Treatment Planning

LongDWM: Cross-Granularity Distillation for Building a Long-Term Driving World Model

DeepVerse: 4D Autoregressive Video Generation as a World Model

World Models for Cognitive Agents: Transforming Edge Intelligence in Future Networks

Long-Context State-Space Video World Models

ProphetDWM: A Driving World Model for Rolling Out Future Actions and Videos

ViMo: A Generative Visual GUI World Model for App Agents

Generating Symbolic World Models via Test-time Scaling of Large Language Models

Learning Local Causal World Models with State Space Models and Attention

WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents

CheXWorld: Exploring Image World Modeling for Radiograph Representation Learning