机器人 / 具身智能

Cross-View World Models

跨视角世界模型

Rishabh Sharma, Gijs Hogervorst, Wayne E. Mackey, David J. Heeger, Stefano Martiniani

机构 * Simons Center for Computational Physical Chemistry（Simon计算物理化学中心） ； Center for Soft Matter Research, Department of Physics（软物质研究中心，物理系） ； Statespace Labs, Inc.（Statespace公司） ； Center for Neural Science, New York University（神经科学中心，纽约大学） ； Department of Psychology, New York University（心理学系，纽约大学） ； Courant Institute of Mathematical Sciences, New York University（Courant数学科学研究所，纽约大学） 纠错

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

AI总结 本文提出跨视角世界模型，通过多视角预测训练智能体在不同视角下进行规划，提升空间感知与多智能体协作能力。

Comments 12 pages, 7 figures

MosaicThinker: On-Device Visual Spatial Reasoning for Embodied AI via Iterative Construction of Space Representation

MosaicThinker: 通过迭代构建空间表示实现设备端具身AI的视觉空间推理

Haoming Wang, Qiyao Xue, Weichen Liu, Wei Gao

机构 * Department of Electrical and Computer Engineering（电气与计算机工程系） ； University of Pittsburgh（匹兹堡大学） 纠错

专题命中 具身推理 ：embodied AI(title,abstract)；manipulation(abstract)；分类 cs.AI、cs.CV

AI总结 MosaicThinker通过迭代构建空间表示，提升设备端具身AI在复杂跨帧空间推理任务中的准确性。

BridgeV2W: Bridging Video Generation Models to Embodied World Models via Embodiment Masks

BridgeV2W: 通过具身遮罩将视频生成模型与具身世界模型 bridging

Yixiang Chen, Peiyan Li, Jiabing Yang, Keji He, Xiangnan Wu, Yuan Xu, Kai Wang, Jing Liu, Nianfeng Liu, Yan Huang, Liang Wang

机构 * New Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences（模式识别新实验室（NLPR），自动化研究所，中国科学院） ； School of Artificial Intelligence, University of Chinese Academy of Sciences（人工智能学院，中国科学院大学） ； Shandong University（山东大学） 纠错

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

AI总结 BridgeV2W 通过具身遮罩将视频生成模型与具身世界模型结合，解决坐标空间动作与像素空间视频的不匹配问题，并提升视频生成质量与跨具身统一性。

Active Inference-Driven World Modeling for Adaptive UAV Swarm Trajectory Design

基于主动推断的世界建模用于自适应无人机蜂群轨迹设计

Kaleem Arshid, Ali Krayani, Lucio Marcenaro, David Martin Gomez, Carlo Regazzoni

机构 * University of Genoa（热那亚大学） ； Carlos III University Madrid（马德里卡洛斯三世大学） 纠错

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

AI总结 本文提出基于主动推断的世界建模框架，用于自适应无人机蜂群轨迹设计，通过整合概率推理和自我学习实现动态环境下的适应性响应。

Comments This paper has been accepted for presentation at the 2026 IEEE International Conference on Acoustics, Speech, and Signal Processing (IEEE ICASSP 2026) Workshop: 'Multi-Modal Signal Processing and AI for Communications and Sensing in 6G and Beyond (MuSiC-6GB)'

Understanding World or Predicting Future? A Comprehensive Survey of World Models

理解世界还是预测未来？世界模型的全面综述

Jingtao Ding, Yunke Zhang, Yu Shang, Jie Feng, Yuheng Zhang, Zefang Zong, Yuan Yuan, Hongyuan Su, Nian Li, Jinghua Piao, Yucheng Deng, Nicholas Sukiennik, Chen Gao, Fengli Xu, Yong Li

机构 * Department of Electronic Engineering, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University（电子工程系，信息科学与技术国家研究中心（BNRist），清华大学） 纠错

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

AI总结 本文综述了世界模型在理解与预测方面的功能，探讨了其在多个领域的应用及未来研究方向。

Comments Extended version of the original ACM CSUR paper, 49 pages, 6 figures, 8 tables

GigaBrain-0: A World Model-Powered Vision-Language-Action Model

GigaBrain-0：一种由世界模型驱动的视觉-语言-动作模型

GigaBrain Team, Angen Ye, Boyuan Wang, Chaojun Ni, Guan Huang, Guosheng Zhao, Haoyun Li, Jie Li, Jiagang Zhu, Lv Feng, Peng Li, Qiuping Deng, Runqi Ouyang, Wenkang Qin, Xinze Chen, Xiaofeng Wang, Yang Wang, Yifan Li, Yilong Li, Yiran Ding, Yuan Xu, Yun Ye, Yukun Zhou, Zhehao Dong, Zhenan Wang, Zhichao Liu, Zheng Zhu

机构 * GigaBrain Team（GigaBrain团队） 纠错

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

AI总结 GigaBrain-0通过世界模型生成数据，减少对真实机器人数据的依赖，提升视觉-语言-动作模型的泛化能力和现实世界性能。

Comments https://gigabrain0.github.io/

NORA-1.5: A Vision-Language-Action Model Trained using World Model- and Action-based Preference Rewards

Chia-Yu Hung, Navonil Majumder, Haoyuan Deng, Liu Renhang, Yankang Ang, Amir Zadeh, Chuan Li, Dorien Herremans, Ziwei Wang, Soujanya Poria

机构 * Nanyang Technological University（南洋理工大学） ； Lambda Labs（Lambda实验室） ； Singapore University of Technology and Design（新加坡科技设计大学） 纠错

专题命中 具身推理 ：world model(title,abstract)；embodied agent(abstract)；分类 cs.RO、cs.AI

Comments https://declare-lab.github.io/nora-1.5

Unlocking Efficient Vehicle Dynamics Modeling via Analytic World Models

Asen Nachkov, Danda Pani Paudel, Jan-Nico Zaech, Davide Scaramuzza, Luc Van Gool

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

Comments Accepted at AAAI 2026

Jasmine: A Simple, Performant and Scalable JAX-based World Modeling Codebase

Mihir Mahajan, Alfred Nguyen, Franz Srambical, Stefan Bauer

机构 * p(doom) 纠错

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

Comments Blog post: https://pdoom.org/jasmine.html

WoW: Towards a World omniscient World model Through Embodied Interaction

Xiaowei Chi, Peidong Jia, Chun-Kai Fan, Xiaozhu Ju, Weishi Mi, Kevin Zhang, Zhiyuan Qin, Wanxin Tian, Kuangzhi Ge, Hao Li, Zezhong Qian, Anthony Chen, Qiang Zhou, Yueru Jia, Jiaming Liu, Yong Dai, Qingpo Wuwu, Chengyu Bai, Yu-Kai Wang, Ying Li, Lizhang Chen, Yong Bao, Zhiyuan Jiang, Jiacheng Zhu, Kai Tang, Ruichuan An, Yulin Luo, Qiuxuan Feng, Siyuan Zhou, Chi-min Chan, Chengkai Hou, Wei Xue, Sirui Han, Yike Guo, Shanghang Zhang, Jian Tang

机构 * Beijing Innovation Center of Humanoid Robotics（北京人形机器人创新中心） ； State Key Laboratory of Multimedia Information Processing（国家多媒体信息处理重点实验室） ； School of Computer Science, Peking University（北京大学计算机学院） ； Hong Kong University of Science and Technology（香港科技大学） 纠错

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

KG-MAS: Knowledge Graph-Enhanced Multi-Agent Infrastructure for coupling physical and digital robotic environments

Walid Abdela

机构 * Walid Abdela（独立研究者） 纠错

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

PhysiAgent: An Embodied Agent Framework in Physical World

Zhihao Wang, Jianxiong Li, Jinliang Zheng, Wencong Zhang, Dongxiu Liu, Yinan Zheng, Haoyi Niu, Junzhi Yu, Xianyuan Zhan

机构 * AIR, Tsinghua University（清华大学） ； Peking University（北京大学） ； University of California, Berkeley（加州大学伯克利分校） 纠错

专题命中 具身推理 ：embodied agent(title,abstract)；robotic(abstract)；分类 cs.RO、cs.AI

KeyWorld: Key Frame Reasoning Enables Effective and Efficient World Models

Sibo Li, Qianyue Hao, Yu Shang, Yong Li

机构 * Department of Electronic Engineering, BNRist, Tsinghua University（电子工程系、北京理工大学、清华大学） 纠错

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

RoboScape: Physics-informed Embodied World Model

Yu Shang, Xin Zhang, Yinzhou Tang, Lei Jin, Chen Gao, Wei Wu, Yong Li

机构 * Tsinghua University（清华大学） ； Manifold AI 纠错

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

Comments 17 pages

Closed-Loop Long-Horizon Robotic Planning via Equilibrium Sequence Modeling

Jinghan Li, Zhicheng Sun, Yadong Mu

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

Comments ICML 2025

A Survey on World Models Grounded in Acoustic Physical Information

Xiaoliang Chen, Le Chang, Xin Yu, Yunhe Huang, Xianling Tu

机构 * SoundAI Technology Co., Ltd.（声AI技术有限公司） 纠错

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

Comments 28 pages,11 equations

EVA: An Embodied World Model for Future Video Anticipation

Xiaowei Chi, Chun-Kai Fan, Hengyuan Zhang, Xingqun Qi, Rongyu Zhang, Anthony Chen, Chi-min Chan, Wei Xue, Qifeng Liu, Shanghang Zhang, Yike Guo

机构 * Hong Kong University of Science（香港科学与技术大学） ； State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University（多媒体信息处理国家重点实验室，计算机科学学院，北京大学） 纠错

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

GeoDrive: 3D Geometry-Informed Driving World Model with Precise Action Control

Anthony Chen, Wenzhao Zheng, Yida Wang, Xueyang Zhang, Kun Zhan, Peng Jia, Kurt Keutzer, Shanghang Zhang

机构 * State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University（多媒体信息处理国家重点实验室，计算机学院，北京大学） ； Li Auto Inc.（利亚德公司） ； UC Berkeley（加州大学伯克利分校） 纠错

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

Comments code will be released at https://github.com/antonioo-c/GeoDrive

Learning 3D Persistent Embodied World Models

Siyuan Zhou, Yilun Du, Yuncong Yang, Lei Han, Peihao Chen, Dit-Yan Yeung, Chuang Gan

机构 * Institution1（机构1） ； Institution2（机构2） 纠错

专题命中 具身推理 ：world model(title,abstract)；embodied agent(abstract)；分类 cs.RO、cs.CV

COMBO: Compositional World Models for Embodied Multi-Agent Cooperation

Hongxin Zhang, Zeyuan Wang, Qiushi Lyu, Zheyuan Zhang, Sunli Chen, Tianmin Shu, Behzad Dariush, Kwonjoon Lee, Yilun Du, Chuang Gan

专题命中 具身推理 ：world model(title,abstract)；embodied agent(abstract)；分类 cs.AI、cs.CV

Comments Published at ICLR 2025. 24 pages. The first three authors contributed equally

Dream to Manipulate: Compositional World Models Empowering Robot Imitation Learning with Imagination

Leonardo Barcellona, Andrii Zadaianchuk, Davide Allegro, Samuele Papa, Stefano Ghidoni, Efstratios Gavves

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

WorldModelBench: Judging Video Generation Models As World Models

Dacheng Li, Yunhao Fang, Yukang Chen, Shuo Yang, Shiyi Cao, Justin Wong, Michael Luo, Xiaolong Wang, Hongxu Yin, Joseph E. Gonzalez, Ion Stoica, Song Han, Yao Lu

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

DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning

Gaoyue Zhou, Hengkai Pan, Yann LeCun, Lerrel Pinto

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

Grounding Large Language Models In Embodied Environment With Imperfect World Models

Haolan Liu, Jishen Zhao

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

Multi-Task Interactive Robot Fleet Learning with Visual World Models

Huihan Liu, Yu Zhang, Vaarij Betala, Evan Zhang, James Liu, Crystal Ding, Yuke Zhu

专题命中 具身推理 ：world model(title,abstract)；robot learning(abstract)；分类 cs.RO、cs.AI

Comments In Proceedings of CoRL 2024

InCoRo: In-Context Learning for Robotics Control with Feedback Loops

Jiaqiang Ye Zhu, Carla Gomez Cano, David Vazquez Bermudez, Michal Drozdzal

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

Language Models Meet World Models: Embodied Experiences Enhance Language Models

Jiannan Xiang, Tianhua Tao, Yi Gu, Tianmin Shu, Zirui Wang, Zichao Yang, Zhiting Hu

专题命中 具身推理 ：world model(title,abstract)；embodied agent(abstract)；分类 cs.AI、cs.LG

Unifying (Machine) Vision via Counterfactual World Modeling

Daniel M. Bear, Kevin Feigelis, Honglin Chen, Wanhee Lee, Rahul Venkatesh, Klemen Kotar, Alex Durango, Daniel L. K. Yamins

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

Predictive World Models from Real-World Partial Observations

Robin Karlsson, Alexander Carballo, Keisuke Fujii, Kento Ohtani, Kazuya Takeda

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

Comments Best Paper Award at IEEE MOST 2023

DreamingV2: Reinforcement Learning with Discrete World Models without Reconstruction

Masashi Okada, Tadahiro Taniguchi

专题命中 具身推理 ：world model(title,abstract)；robot learning(abstract)；分类 cs.AI、cs.LG

Comments The code will be available soon