arXivDaily arXiv每日学术速递 周一至周五更新

视觉与机器人

世界模型

面向环境建模、时序预测、仿真规划、具身智能和自动驾驶的世界模型方法与应用。

共收录 6483 信号源:cs.AI, cs.LG, cs.CV, cs.RO, cs.MA

1. 通用世界模型 4335 篇

2509.19080 2026-03-23 cs.RO cs.AI 94%

World4RL: Diffusion World Models for Policy Refinement with Reinforcement Learning for Robotic Manipulation

World4RL: 基于扩散世界模型的强化学习政策精修框架用于机器人操作

Zhennan Jiang, Kai Liu, Yuxin Qin, Shuai Tian, Yupeng Zheng, Mingcai Zhou, Chao Yu, Haoran Li, Dongbin Zhao

机构 * The State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences(多模态人工智能系统国家重点实验室,自动化研究所,中国科学院) School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院) Zhongguancun Academy(中关村学院) Beijing Zhongke Huiling Robot Technology Co(北京中科创联机器人技术有限公司) Department of Electronic Engineering, Tsinghua University(清华大学电子工程系)

专题命中 通用世界模型 :world model(title,abstract);world models(title,abstract);world model(title,abstract);world models(title,abstract)

AI总结 World4RL通过扩散世界模型提升机器人操作政策的精修效果,采用高保真模拟环境进行端到端政策优化,优于模仿学习及其他基线方法。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.17117 2026-03-19 cs.CV 94%

MosaicMem: Hybrid Spatial Memory for Controllable Video World Models

MosaicMem: 用于可控视频世界模型的混合空间记忆

Wei Yu, Runjia Qian, Yumeng Li, Liquan Wang, Songheng Yin, Sri Siddarth Chakaravarthy P, Dennis Anthony, Yang Ye, Yidi Li, Weiwei Wan, Animesh Garg

机构 * University of Toronto(多伦多大学) Vector Institute(向量研究所) The University of Osaka(大阪大学) Georgia Institute of Technology(佐治亚理工学院) Mujin Inc.(Mujin公司) University of Texas at Austin(德克萨斯大学奥斯汀分校) Taiyuan University of Technology(太原本科技大学)

专题命中 通用世界模型 :world model(title);world models(title);video world model(title);world model(title)

AI总结 MosaicMem提出一种混合空间记忆方法,通过提升片段至3D实现可靠定位与检索,结合模型原生条件化保留提示生成,提升姿态一致性与动态建模能力,支持细粒度导航与场景编辑。

Comments Project Page: https://mosaicmem.github.io/mosaicmem/

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.00844 2026-01-06 cs.LG cs.AI cs.RO 94%

Value-guided action planning with JEPA world models

基于JEPA世界模型的价值引导动作规划

Matthieu Destrade, Oumayma Bounou, Quentin Le Lidec, Jean Ponce, Yann LeCun

机构 * École Polytechnique(巴黎高等理工学院) ENS Paris(巴黎高等师范学院) New York University(纽约大学)

专题命中 通用世界模型 :world model(title,abstract);world models(title,abstract);world model(title,abstract);world models(title,abstract)

AI总结 本文提出了一种基于JEPA世界模型的价值引导动作规划方法,通过塑造表示空间提升规划性能。

Comments Presented as a poster at the World Modeling Workshop 2026, Mila

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.12548 2025-12-30 cs.AI cs.LG 94%

World Models Unlock Optimal Foraging Strategies in Reinforcement Learning Agents

世界模型解锁强化学习智能体的最优觅食策略

Yesid Fonseca, Manuel S. Ríos, Nicanor Quijano, Luis F. Giraldo

机构 * Center of Excellence in Analytics, Artificial Intelligence, and Information Governance, Bancolombia, Colombia(分析、人工智能和信息治理卓越中心,Bancolombia,哥伦比亚) Department of Biomedical Engineering, Universidad de los Andes, Bogotá, Colombia(生物医学工程系, Universidad de los Andes,波哥大,哥伦比亚) Department of Electrical and Electronics Engineering, Universidad de los Andes, Bogotá, Colombia(电气与电子工程系, Universidad de los Andes,波哥大,哥伦比亚)

专题命中 通用世界模型 :world model(title,abstract);world models(title,abstract);world model(title,abstract);world models(title,abstract)

AI总结 世界模型帮助强化学习智能体实现最优觅食策略,通过预见能力而非单纯奖励最大化驱动高效决策。

Comments 14 pages, 6 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.03429 2025-12-04 cs.RO cs.AI 94%

World Models for Autonomous Navigation of Terrestrial Robots from LIDAR Observations

基于LIDAR观测的地面机器人自主导航的World Models

Raul Steinmetz, Fabio Demo Rosa, Victor Augusto Kich, Jair Augusto Bottega, Ricardo Bedin Grando, Daniel Fernando Tello Gamarra

机构 * Universidade Federal de Santa Maria, Brazil(巴西联邦大学圣玛利亚分校) University of Tsukuba, Japan(日本筑波大学) Universidade Federal de Rio Grande(巴西联邦大学里约格兰德分校) Universidad Tecnológica del Uruguay, Uruguay(乌拉圭技术大学)

专题命中 通用世界模型 :world model(title,abstract);world models(title,abstract);world model(title,abstract);world models(title,abstract)

AI总结 本文提出基于DreamerV3算法的模型驱动强化学习框架,通过整合MLP-VAE实现高维LIDAR数据的高效编码与潜在表示学习,提升地面机器人自主导航的效率与鲁棒性。

Comments Accepted for publication in the Journal of Intelligent and Fuzzy Systems

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.09297 2025-09-10 cs.LG 94%

When Do Neural Networks Learn World Models?

Tianren Zhang, Guanyu Chen, Feng Chen

机构 * Department of Automation, Tsinghua University, Beijing, China(自动化系,清华大学,北京,中国)

专题命中 通用世界模型 :world model(title,abstract);world models(title,abstract);world model(title,abstract);world models(title,abstract)

Comments ICML 2025; ICLR 2025 World Models Workshop (oral, outstanding paper award)

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.14081 2025-05-13 cs.LG 94%

Reward-free World Models for Online Imitation Learning

Shangzhe Li, Zhiao Huang, Hao Su

专题命中 通用世界模型 :world model(title,abstract);world models(title,abstract);world model(title,abstract);world models(title,abstract)

Comments ICML 2025; Code available at: https://github.com/TobyLeelsz/iqmpc

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.07095 2025-04-10 cs.LG cs.RO 94%

Neural Motion Simulator: Pushing the Limit of World Models in Reinforcement Learning

Chenjie Hao, Weyl Lu, Yifan Xu, Yubei Chen

专题命中 通用世界模型 :world model(title,abstract);world models(title,abstract);world model(title,abstract);world models(title,abstract)

Comments 8 pages (main), 2-page appendix, 8 figures, accepted by CVPR 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.10171 2025-03-11 cs.RO cs.AI 94%

Imagine-2-Drive: Leveraging High-Fidelity World Models via Multi-Modal Diffusion Policies

Anant Garg, K Madhava Krishna

专题命中 通用世界模型 :world model(title,abstract);world models(title,abstract);world model(title,abstract);world models(title,abstract)

Comments Submitted to IROS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2401.16650 2024-07-17 cs.LG cs.AI 94%

Augmenting Replay in World Models for Continual Reinforcement Learning

Luke Yang, Levin Kuhlmann, Gideon Kowadlo

专题命中 通用世界模型 :world model(title,abstract);world models(title,abstract);world model(title,abstract);world models(title,abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2405.06263 2024-05-31 cs.LG cs.AI 94%

Learning Latent Dynamic Robust Representations for World Models

Ruixiang Sun, Hongyu Zang, Xin Li, Riashat Islam

专题命中 通用世界模型 :world model(title,abstract);world models(title,abstract);world model(title,abstract);world models(title,abstract)

Journal ref ICML 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2402.05643 2024-05-30 cs.LG cs.AI 94%

Improving Token-Based World Models with Parallel Observation Prediction

Lior Cohen, Kaixin Wang, Bingyi Kang, Shie Mannor

专题命中 通用世界模型 :world model(title,abstract);world models(title,abstract);world model(title,abstract);world models(title,abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2401.13034 2024-04-18 cs.LG cs.AI 94%

Locality Sensitive Sparse Encoding for Learning World Models Online

Zichen Liu, Chao Du, Wee Sun Lee, Min Lin

专题命中 通用世界模型 :world model(title,abstract);world models(title,abstract);world model(title,abstract);world models(title,abstract)

Comments ICLR 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2308.05701 2024-01-10 cs.AI cs.RO 94%

Exploring the Potential of World Models for Anomaly Detection in Autonomous Driving

Daniel Bogdoll, Lukas Bosch, Tim Joseph, Helen Gremmelmaier, Yitian Yang, J. Marius Zöllner

专题命中 通用世界模型 :world model(title,abstract);world models(title,abstract);world model(title,abstract);world models(title,abstract)

Comments Accepted for publication at SSCI 2023

详情

展开后加载摘要…

URL PDF HTML 收藏
2303.04116 2023-09-29 cs.RO cs.CV 94%

TrafficBots: Towards World Models for Autonomous Driving Simulation and Motion Prediction

Zhejun Zhang, Alexander Liniger, Dengxin Dai, Fisher Yu, Luc Van Gool

专题命中 通用世界模型 :world model(title,abstract);world models(title,abstract);world model(title,abstract);world models(title,abstract)

Comments Published at ICRA 2023. The repository is available at https://github.com/zhejz/TrafficBots

详情

展开后加载摘要…

URL PDF HTML 收藏
2308.15852 2023-09-19 cs.RO 94%

Learning to Navigate from Scratch using World Models and Curiosity: the Good, the Bad, and the Ugly

Daria de Tinguy, Sven Remmery, Pietro Mazzaglia, Tim Verbelen, Bart Dhoedt

专题命中 通用世界模型 :world model(title,abstract);world models(title,abstract);world model(title,abstract);world models(title,abstract)

Comments IROS 2023 workshop World Models and Predictive Coding in Cognitive Robotics and IROS 2023 workshop Learning Robot Super Autonomy

详情

展开后加载摘要…

URL PDF HTML 收藏
2203.00494 2022-03-02 cs.LG cs.AI cs.SY eess.SY 94%

DreamingV2: Reinforcement Learning with Discrete World Models without Reconstruction

Masashi Okada, Tadahiro Taniguchi

专题命中 通用世界模型 :world model(title,abstract);world models(title,abstract);world model(title,abstract);world models(title,abstract)

Comments The code will be available soon

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.10012 2025-11-14 cs.AI cs.RO 94%

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 通用世界模型 :world model(title,abstract);world models(title,abstract);world model(title,abstract);world models(title,abstract)

Comments Accepted at AAAI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.04020 2025-10-13 cs.LG cs.AI 94%

Spatiotemporal Forecasting as Planning: A Model-Based Reinforcement Learning Approach with Generative World Models

Hao Wu, Yuan Gao, Xingjian Shi, Shuaipeng Li, Fan Xu, Fan Zhang, Zhihong Zhu, Weiyan Wang, Xiao Luo, Kun Wang, Xian Wu, Xiaomeng Huang

专题命中 通用世界模型 :world model(title,abstract);world models(title);world model(title,abstract);model-based reinforcement learning(title,abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.03198 2026-07-13 cs.LG math-ph math.MP 新提交 94%

Reduced-Order Models: The Mother of World Models

降阶模型:世界模型之母

Rajat Ghosh

机构 * Independent Researcher(独立研究员)

专题命中 通用世界模型 :world model(title,abstract);world models(title,abstract);world model(title,abstract);world models(title,abstract)

AI总结 探讨世界模型的功能结构早于现代自监督学习,在模型降阶和控制文献中就已独立发展。追溯其在三个领域的发展,对比传统降阶模型与学习型世界模型的优缺点,指出在关键系统中部署世界模型的障碍及统一两者的研究议程。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.06401 2026-07-08 cs.AI 新提交 94%

A Definition and Roadmap for World Models

世界模型的定义与路线图

Xinyuan Chen, Haoyu Guo, Shi Guo, Bingqi Jiang, Chunhua Shen, Xing Shen, Tianfan Xue, Yufei Xue, Mulin Yu, Weinan Zhang, Bin Zhao, Bowen Zhou, Ming Zhou

机构 * Shanghai AI Laboratory(上海人工智能实验室)

专题命中 通用世界模型 :world model(title,abstract);world models(title,abstract);world model(title,abstract);world models(title,abstract)

AI总结 本文针对人工智能领域对世界模型定义、预测内容及构建方式缺乏共识的问题,给出科学定义,讨论关键技术,提供分阶段路线图,以助力有效世界模型的开发。

Comments Technical report, 58 pages, 10 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.12471 2026-07-07 stat.ML cs.CL cs.ET cs.LG 新提交 94%

Identifiability Without Gaussianity: Symbolic World Models and Near-Infinite Temporal Consistency

无高斯假设的可识别性:符号世界模型与近无限时间一致性

Seth Dobrin, Łukasz Chmiel

机构 * Department of Computer Science, Stanford University(1 计算机科学系,斯坦福大学)

专题命中 通用世界模型 :world model(title,abstract);world models(title,abstract);world model(title,abstract);world models(title,abstract)

AI总结 本文提出物理基础符号架构(PGSA),证明其在非高斯动态系统中实现精确线性可识别性和近无限时间一致性,克服了统计世界模型的高斯边界限制。

Comments Pre-print

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.02403 2026-07-03 cs.RO cs.AI cs.CV 新提交 94%

ACID: Action Consistency via Inverse Dynamics for Planning with World Models

ACID: 通过逆动力学实现行动一致性以用于世界模型规划

Gawon Seo, Dongwon Kim, Suha Kwak

机构 * POSTECH KAIST(韩国科学技术院)

专题命中 通用世界模型 :world model(title,abstract);world models(title,abstract);world model(title,abstract);world models(title,abstract)

AI总结 提出ACID框架,通过逆动力学模型引入循环行动一致性约束,改进基于世界模型的决策时规划,在多种任务中提升规划效果并降低计算成本。

Comments Project Page: [this https URL](https://gawon1224.github.io/ACID/)

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.31232 2026-07-01 cs.AI 新提交 94%

Delta-JEPA: Learning Action-Sensitive World Models via Latent Difference Decoding

Delta-JEPA: 通过潜在差异解码学习动作敏感的世界模型

Zhenghao Zhang, Yuanxiang Wang, Zhenyu Guan, Yujia Yang, Bingkang Shi, Tianyu Zong, Hongzhu Yi, Guoqing Chao, Xingchen Chen, Tiankun Yang, Chenxi Bao, Tao Yu, Jingjing Zhou, Jungang Xu

机构 * School of Computer Science and Technology, University of Chinese Academy of Sciences(中国科学院大学计算机科学与技术学院) Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所) School of Computer Science and Technology, Harbin Institute of Technology, Weihai(哈尔滨工业大学(威海)计算机科学与技术学院) Faculty of Computing, Harbin Institute of Technology, Harbin(哈尔滨工业大学计算学部) Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所)

专题命中 通用世界模型 :world model(title,abstract);world models(title,abstract);world model(title,abstract);world models(title,abstract)

AI总结 提出Delta-JEPA,一种无重建的世界模型,通过潜在差异动作解码器(LDAD)从连续观测的潜在位移中重建动作,防止表示坍塌,提升基于规划的性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.28751 2026-06-30 cs.LG cond-mat.stat-mech 94%

A Path-Space Formulation of Prediction in World Models: From a Single Action to Prediction, Planning, and Irreversibility

世界模型中预测的路径空间表述:从单一动作到预测、规划和不可逆性

Gunn Kim

机构 * Department of Physics, Sejong University, Seoul 05006, Republic of Korea(首尔大学物理系,首尔05006,韩国)

专题命中 通用世界模型 :world model(title,abstract);world models(title,abstract);world model(title,abstract);world models(title,abstract)

AI总结 提出世界模型中预测的路径空间表述,将预测、规划和不确定性统一为作用泛函上的操作,并发现注意力不对称性编码了数据的不可逆性。

Comments 13 pages, 3 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.09457 2026-06-25 cs.RO 新提交 94%

$ω$-EVA: Envision, Verify, and Act with Latent Interactive World Models

$ω$-EVA:基于潜在交互世界模型的构想、验证与行动

Zhenguo Sun, Yu Sun, Hande Huang, Alois Knoll

机构 * Technical University of Munich(慕尼黑工业大学)

专题命中 通用世界模型 :world model(title,abstract);world models(title,abstract);world model(title,abstract);world models(title,abstract)

AI总结 提出$ω$-EVA框架,通过潜在交互世界模型实现“构想-验证-行动”循环,利用动作条件潜在动力学和语言条件流策略生成动作,无需生成未来视频,在多种机器人操作任务中提升策略性能。

Comments Add some ablation experiments

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.02800 2026-06-24 cs.CV cs.AI cs.LG cs.MM cs.RO 版本更新 94%

Cosmos 3: Omnimodal World Models for Physical AI

Cosmos 3:面向物理AI的全模态世界模型

NVIDIA, :, Aditi, Niket Agarwal, Arslan Ali, Jon Allen, Martin Antolini, Adeline Aubame, Alisson Azzolini, Junjie Bai, Maciej Bala, Yogesh Balaji, Josh Bapst, Aarti Basant, Mukesh Beladiya, Mohammad Qazim Bhat, Zaid Pervaiz Bhat, Dan Blick, Vanni Brighella, Han Cai, Tiffany Cai, Eric Cameracci, Jiaxin Cao, Yulong Cao, Mark Carlson, Carlos Casanova, Ting-Yun Chang, Yan Chang, Yu-Wei Chao, Prithvijit Chattopadhyay, Roshan Chaudhari, Chieh-Yun Chen, Junyu Chen, Ke Chen, Qizhi Chen, Wenkai Chen, Xiaotong Chen, Yu Chen, An-Chieh Cheng, Click Cheng, Xiu Chia, Jeana Choi, Chaeyeon Chung, Wenyan Cong, Yin Cui, Magdalena Dadela, Nalin Dadhich, Wenliang Dai, Joyjit Daw, Alperen Degirmenci, Rodrigo Vieira Del Monte, Robert Denomme, Sameer Dharur, Marco Di Lucca, Ke Ding, Wenhao Ding, Yifan Ding, Yuzhu Dong, Nicole Drumheller, Yilun Du, Aigul Dzhumamuratova, Aleksandr Efitorov, Hamid Eghbalzadeh, Naomi Eigbe, Imad El Hanafi, Hassan Eslami, Benedikt Falk, Jiaojiao Fan, Jim Fan, Amol Fasale, Sergiy Fefilatyev, Liang Feng, Francesco Ferroni, Sanja Fidler, Xiao Fu, Vikram Fugro, Prashant Gaikwad, TJ Galda, Katelyn Gao, Yihuai Gao, Wenhang Ge, Sreyan Ghosh, Arushi Goel, Vivek Goel, Akash Gokul, Rama Govindaraju, Jinwei Gu, Miguel Guerrero, Elfie Guo, Aryaman Gupta, Siddharth Gururani, Hugo Hadfield, Song Han, Ankur Handa, Zekun Hao, Mohammad Harrim, Ali Hassani, Nathan Hayes-Roth, Yufan He, Chris Helvig, Cyrus Hogg, Madison Huang, Michael Huang, Sophia Huang, Yufan Huang, Jacob Huffman, DeLesley Hutchins, Suneel Indupuru, Boris Ivanovic, Arihant Jain, Joel Jang, Ryan Ji, Yanan Jian, Dongfu Jiang, Jingyi Jin, Atharva Joshi, Nikhilesh Joshi, Pranjali Joshi, Andy Ju, Jaehun Jung, Weiwei Kang, Scott Kassekert, Jan Kautz, Ashna Khetan, Julia Kiczka, Slawek Kierat, Gwanghyun Kim, Kuno Kim, Sunny Kim, Kezhi Kong, Xin Kong, Zhifeng Kong, Tomasz Kornuta, Egor Krivov, Hui Kuang, Saurav Kumar, Chia-Wen Kuo, George Kurian, Wojciech Kutak, JF Lafleche, Himangshu Lahkar, Omar Laymoun, Jayjun Lee, Sanggil Lee, Gabriele Leone, Boyi Li, Freya Li, Jiajun Li, Jinfeng Li, Ling Li, Pengcheng Li, Shangru Li, Tingle Li, Xiaolong Li, Xuan Li, Zhaoshuo Li, Zhiqi Li, Hao Liang, Maosheng Liao, Chen-Hsuan Lin, Tsung-Yi Lin, Ming-Yu Liu, Sifei Liu, Zihan Liu, Hai Loc Lu, Xiangyu Lu, Alice Luo, Ruipu Luo, Wenjie Luo, Jiangran Lyu, Martin Ding Ma, Nic Ma, Qianli Ma, Dawid Majchrowski, Louis Marcoux, Miguel Martin, Qing Miao, Ashkan Mirzaei, Shreyas Misra, Kaichun Mo, Durra Mohsin, Hyejin Moon, Pawel Morkisz, Saeid Motiian, Kirill Motkov, Seungjun Nah, Yashraj Narang, Deepak Narayanan, Thabang Ngazimbi, Julian Ouyang, Shubham Pachori, David Page, Yatian Pang, Sehwi Park, Mahesh Patekar, Mostofa Patwary, Marco Pavone, Trung Pham, Wei Ping, Soha Pouya, Shrimai Prabhumoye, Varun Praveen, Delin Qu, Hesam Rabeti, Morteza Ramezanali, Marilyn Reeb, Xuanchi Ren, Kristen Rumley, Wojciech Rymer, Jun Saito, Yeongho Seol, John Shao, Piyush Shekdar, Tianwei Shen, Humphrey Shi, Min Shi, Stella Shi, Kevin Shih, Mohammad Shoeybi, Mateusz Sieniawski, Shuran Song, Alexander Sotelo, Amir Sotoodeh, Sunil Srinivasa, Vignesh Srinivasakumar, Bartosz Stefaniak, Rahul Heinrich Steiger, Shangkun Sun, Jiaxiang Tang, Shitao Tang, Yangyang Tang, Yue Tang, Tolou Tavakkoli, Kayley Ting, Krzysztof Tomala, Wei-Cheng Tseng, Jibin Varghese, Sergei Vasilev, Thomas Volk, Raju Wagwani, Roger Waleffe, Andrew Z. Wang, Boxiang Wang, Haoxiang Wang, Qiao Wang, Shihao Wang, Shijie Wang, Ting-Chun Wang, Yan Wang, Yu Wang, Rohit Watve, David Wehr, Fangyin Wei, Xinshuo Weng, Jay Zhangjie Wu, Kedi Wu, Hongchi Xia, Summer Xiao, Tianjun Xiao, Kevin Xie, Daguang Xu, Jiashu Xu, Mengyao Xu, Ruqing Xu, Xingqian Xu, Yao Xu, Dinghao Yang, Dong Yang, Hans Yang, Xiaodong Yang, Xuning Yang, Yichu Yang, Yurong You, Zhiding Yu, Hao Yuan, Simon Yuen, Xiaohui Zeng, Pengcuo Zeren, Cindy Zha, Haotian Zhang, Jenny Zhang, Jing Zhang, Liangkai Zhang, Paris Zhang, Shun Zhang, Xuanmeng Zhang, Zhizheng Zhang, Ann Zhao, Yilin Zhao, Yuliya Zhautouskaya, Charles Zhou, Fengzhe Zhou, Shilin Zhu, Yuke Zhu, Dima Zhylko, Artur Zolkowski

机构 * NVIDIA

专题命中 通用世界模型 :world model(title,abstract);world models(title,abstract);world model(title,abstract);world models(title,abstract)

AI总结 提出基于统一混合Transformer架构的全模态世界模型Cosmos 3,联合处理语言、图像、视频、音频和动作序列,在理解和生成任务上达到新最优,为具身智能体提供可扩展的通用骨干。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.21775 2026-06-23 cs.LG cs.AI 新提交 94%

Beyond the Next Step: Variable-Length Latent World Models for Long-Horizon Planning

超越下一步:用于长时程规划的变长潜世界模型

Tianqi Du, Qi Zhang, Yifei Wang, Yisen Wang

机构 * State Key Lab of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University(北京大学智能科学与技术学院通用人工智能国家重点实验室) Amazon AGI SF Lab(亚马逊AGI旧金山实验室) Institute for Artificial Intelligence, Peking University(北京大学人工智能研究院)

专题命中 通用世界模型 :world model(title,abstract);world models(title,abstract);world model(title,abstract);world models(title,abstract)

AI总结 提出变长潜世界模型(VLWM),通过学习变长动作序列的条件潜状态预测,解决递归一步预测在长时程规划中的累积误差问题,结合课程训练策略,在长时程控制任务上平均提升13%。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.15032 2026-06-16 cs.LG 新提交 94%

How Should World Models Be Evaluated for Embodied Decision-Making? A Decision-Making-Centric Position

世界模型应如何评估?一个以决策为中心的立场

Yang Yu, Shiyuan Zhang, Yifei Sheng, Haoxiang Ren, Haoxin Lin

机构 * National Key Laboratory for Novel Software Technology, Nanjing University(南京大学计算机软件新技术国家重点实验室) School of Artificial Intelligence, Nanjing University(南京大学人工智能学院) Cirquar Technologies

专题命中 通用世界模型 :world model(title,abstract);world models(title,abstract);world model(title,abstract);world models(title,abstract)

AI总结 本文指出世界模型评估中声明与证据不匹配的问题,提出以决策为中心的评估框架,强调反事实推理、策略优化等能力,并定义L0-L7评估阶梯。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.04534 2026-06-04 cs.RO 94%

MAD: Mapping-Aware World Models for Agile Quadrotor Flight

MAD: 面向敏捷四旋翼飞行的地图感知世界模型

Xinhong Zhang, Runqing Wang, Yunfan Ren, Ding Yu, Boyu Zhou, Jian Sun, Fang Deng, Jie Chen, Gang Wang

机构 * State Key Lab of Autonomous Intelligent Unmanned Systems, Beijing Institute of Technology, Beijing 100081, China(自主智能无人系统国家重点实验室,北京理工大学,北京100081,中国) Zhongguancun Academy, Beijing 100094, China(中关村学院,北京100094,中国) School of Computer Science and Technology, Tongji University(同济大学计算机科学与技术学院) Department of Mechanical and Energy Engineering, Southern University of Science and Technology(南方科技大学机械与能源工程系) Harbin Institute of Technology(哈尔滨工业大学)

专题命中 通用世界模型 :world model(title,abstract);world models(title,abstract);world model(title,abstract);world models(title,abstract)

AI总结 提出地图感知世界模型MAD,通过重构机器人中心占用和可见性网格地图学习几何感知的潜在动力学,在视觉导航和竞速任务中实现更高成功率、更快飞行速度和更好跨任务迁移。

Comments 12 pages, 14 figures

详情

展开后加载摘要…

URL PDF HTML 收藏