Explore learned models of environments and their dynamics. Follow research on prediction, simulation, physical reasoning, and planning.
41 papers · Latest edition October 6, 2026
Three of the latest briefs in this collection. Read the evidence and the original papers alongside them.
4Director makes video world models controllable by moving explicit 3D meshes through time while preserving realistic, consistent appearances.
EMPIRIC lets robots discover missing physics through targeted experiments and use the resulting interpretable world models to plan better.
RoboCoach uses imagined robot failures to decide what demonstrations to request next, making long-horizon manipulation skills improve more efficiently.
Newest editions first.
Wei Cao, Hao Zhang, Vikram Voleti, Yuqun Wu, Mallikarjun B R, Shimon Vainer, Mark Boss, Yaoyao Liu
4Director makes video world models controllable by moving explicit 3D meshes through time while preserving realistic, consistent appearances.
Yichao Liang, Amber Li, Dat Nguyen, Emily Bunnapradist, Michelangelo Naim, Sreela Kodali, Matteo Merler, Bowen Li, Kiran Gopinathan, Yiyun Liu, Nikhil Pimpalkhare, Joshua B. Tenenbaum, Adrian Weller, Zenna Tavares, Tom Silver, Kevin Ellis
EMPIRIC lets robots discover missing physics through targeted experiments and use the resulting interpretable world models to plan better.
Jiajun Liu, Yifan Chen, Yichao Liu, Jiayi Zhang, Ruoqu Chen, Shaoxuan Xie, Guocai Yao, Mengdi Xu, Sen Cui, Changshui Zhang
RoboCoach uses imagined robot failures to decide what demonstrations to request next, making long-horizon manipulation skills improve more efficiently.
Zhiqi Bai, Junai Cai, Yixin Chen, Jingrun Du, Tao Feng, Wei Gong, Siyuan Huang, Xiao Lin, Jiaheng Liu, Jun Luo, Yongzhe Lyu, Liya Ma, Zenan Meng, Lin Qu, Wenbo Su, Jiaming Wang, Qinghe Wang, Shaofei Wang, Yanghai Wang, Zequn Wang, Ziming Wang, Hu Wei, Jiangtao Wu, Ruiqi Wu, Jiaxin Xie, Yuchi Xu, Ze Xu, Chengting Yu, Liangyu Yuan, Gang Zeng, Yawen Zeng, Xingyao Zhang, Zizheng Zhang, Bo Zheng, Jiancheng Zhu, Song-Chun Zhu
HappyWorld-Bench tests whether AI-generated worlds remain coherent, editable, and responsive when agents explore and act within them.
Taoyong Cui, Zhongyao Wang, Xinyue Xu, Weiyang Liu, Zhaochen Yu, Yuying Zhang, Qiang Gao, Mengyue Yang, Wanli Ouyang, Pheng Ann Heng, Yingcheng Wu, Zhenfei Yin, Ling Yang
JEPA-Anything aims to provide one factorized recipe for learning predictive world models spanning vision, biology, medicine, physics, control, and weather.
Bardienus P. Duisterhof, Kaifeng Zhang, Adam Hung, Bowen Wen, Stan Birchfield, Yunzhu Li, Deva Ramanan, Jeffrey Ichnowski
PointZero learns general 3D motion dynamics from sparse point tracks rather than robot actions, then transfers that knowledge to manipulation and imitation tasks.
AgiBot Research Team, Renhang Liu, Wenzhi Zhao, Zhuo Yang, Liliang Chen, Pengfei Zhou, Shengcong Chen, Guanghui Ren, Youlun Peng, Rongjun Jin, Nan Wang, Sukai Wang, Xindong He, Jinyuan Feng, Ziyu Xiong, Linqing Zhong, Yifei Wei, Feng Han, Long Zhang, Da Huang, Nanshu Zhao, Chenghao Yin, Mo Wu, Zhaodong Yan, Kongtao Hu, Yuxiang Yan, Aogelijiang Niyazi, Yu Fang, Jia Zeng, Lizhu Meng, Daizhen Lv, Haoyu Cao, Zhiwen Hou, Lianjin Ye, Yuehan Niu, Zhikai Cai, Xuan Hu, Hui Min, Xiongfeng Cai, Yue Liao, Jing Wu, Soujanya Poria, Ye Li, Sanping Zhou, Maoqing Yao
GE-Act 2.0 trains a scalable robot world-action model from scratch and shows that more diverse manipulation data can substantially improve zero-shot control across tasks, embodiments, and environments.
Zheng-Hui Huang, Guixu Lin, Jiacheng Lin, Yi-Chuan Huang, Ruihan Yu, Muyao Niu, Siqi Yang, Yu-Lun Liu, Yung-Yu Chuang, Kaipeng Zhang, Zhixiang Wang
A programmable world model combines an explicit game-state engine with generative video to create persistent, controllable interactive worlds.
Xiyuan Yang, Sheikh Sarwar, Jingru Cheng, Zhan Shi, Duanshun Li, Huiyuan Chen, Haiyang Zhang, Xing Fan, Chenlei Guo, Jingrui He, Zhenyu Liao
This work speeds up the training of autonomous research agents by letting them practice in a learned simulated world instead of repeatedly running costly real experiments.
Junchao Huang, Guian Fang, Shengju Qian, Xianghao Kong, Zhuoran Zhao, Wei Huang, Yihua Du, Zixin Zhang, Justin Cui, Yuchao Gu, Yukang Chen, Xinting Hu, Tianyu He, Shaoshuai Shi, Zhuotao Tian, Xin Wang, Mike Zheng Shou, Li Jiang
SolarWM is an open, scalable toolkit for training video world models that can simulate interactive environments over minutes or even hours.
Muyao Niu, Jixuan He, Ruihan Yu, Lian Fu, Yonghao Yu, Zheng-Hui Huang, Yifan Zhan, Fengbo Lan, Yongtao Ge, Yinqiang Zheng, Kaipeng Zhang, Zhixiang Wang
WorldSculpt turns partial multi-view videos into large, editable 3D worlds made of individually generated object meshes, even in heavily cluttered scenes.
Xionghao Wu, Yijun Yang, Shiyang Zhou, Haoze Sun, Jianhui Liu, Songsong Yu, Jiyao Zhang, Wenbo Li, Bo Wang, Guoqing Ma, Lin Song, Renjie Liao, Shenghe Zheng, Wei Tang, Xiaojuan Qi, Yanwei Li, Yuan Zhang, Zhuotao Tian, Haoyang Huang, Nan Duan
ZimaBlue turns massive amounts of human and robot video into real-time, generalizable robot manipulation skills.
Kechen Liu, Ola Shorinwa
CLAP aims to turn diverse human and robot videos into a shared physical simulator that can predict and control unfamiliar robot embodiments.
Tong Wang, Huan Deng, Mucheng Yang, Yang He, Xiaohui Kuang, Gang Zhao
This study asks whether today’s generative world models can truly replace simulators and finds that they still lack reliable physics, state feedback, and stable long-horizon behavior.
Yuandong Pu, Le Zhuo, Sayak Paul, Gabriel Jorge Menezes, Avram Đorđević, Shiyang Li, Yifan Zhou, Bin Fu, Wenlong Zhang, Junjun He, Yu Qiao, Yihao Liu, Jingbo Xing, Xi Chen
PAWBench asks whether video generators merely make plausible futures or actually reproduce the full range and probabilities of how the world can unfold.
Yuanyang Yin, Gongxuan Wang, Yifan Zhan, Chuanhao Li, Kaipeng Zhang, Feng Zhao
Evoke builds an interactive world model that remembers evolving scenes indefinitely while generating responsive video in just three steps.
Ge Yan, Jinghao Liu, Yuzhi Fan, Lei Cai, Minwen Liao, Jesse Zhang, Dieter Fox
Flex-π gives robots a flexible world model that combines video, 3D structure, semantics, and actions to improve precise bimanual manipulation while adapting compute at inference time.
Alexy Skoutnev, Kirill Acharya, Gaston Longhitano, Madeleine Udell, Kevin Ellis, Iddo Drori
An AI agent learns the rules and goals of unfamiliar games by building and debugging its own executable digital twin.
Kang He, Wenshuo Peng, Zihui Gao, Jiaming Tan, Kaipeng Zhang, Yongtao Ge
Sekai2 is a large-scale video dataset designed to teach AI systems how worlds evolve across time, viewpoints, and camera trajectories.
Yuxue Yang, Shuyao Shang, Jiahe Wang, Zitong Zhou, Liang Tan, Junhan Zeng, Ruizhi Li, Junyan Li, Yu Liu, Xiao Yang, Yong Li, Jun Zhu, Hongsheng Li, Tieniu Tan, Lue Fan, Zhaoxiang Zhang
WorldExam tests whether video models merely look convincing or can actually understand scenes well enough to react plausibly to what happens in them.
Peterson Co, Sicheng Hu, Chunxuan Jiao, Hongyang Cheng, Yulin Luo, Yijie Xu, Sixiang Chen, Zhongxia Zhao, Zihao Wang, DaFeng Chi, Peidong Liu, YuTong Chen, Henghua Liu, Zhihao Yuan, Huizhu Jia, Yuzheng Zhuang, Tianle Zhang, Liang Lin, Huajie Tan, Shanghang Zhang
WorldSimProbe checks whether embodied world models truly respond to actions like physical simulators, rather than merely generating plausible-looking videos.
Hao Fei, Yiran Zhao
This paper argues that truly useful world models must simulate not only what happens in a scene, but also what the people in it believe, want, and intend.
Senyu Fei, Xiaopeng Yu, Siyin Wang, Xianzhong Zhao, Jingjing Gong, Xipeng Qiu
WCM improves robot-learning critics by predicting how the world evolves over time instead of relying only on single-frame value estimates.
Kaizhen Tan, Xin Xu, Siru Tao, Hanzhe Hong, Yang Feng, Heqing Du
The study shows that latent world models learn only the physical properties that both the sensors reveal and the prediction objective actively pressures them to retain.
Quanfu Yu, Xian Wu, Hao Xu, Liulong Ma
HyWorldVLA combines pixel-grounded and latent world modeling to make autonomous-driving vision-language-action systems more robust to noisy future predictions.
Xiangteng Zhang, Yang Guan, Bo Zhang, Ya-Qin Zhang, Shengbo Eben Li
This paper explains when learned world models can truly recover both the hidden state and the effects of actions, especially when training data lacks sufficient action diversity.
Jiacong Xu, Hanwen Jiang, Zhixin Shu, Kalyan Sunkavalli, Vishal M. Patel, Yiqun Mei
Wonder turns video generation into an interactive, navigable world that remembers what it has seen and responds to camera motion in real time.
Fan Jiang, Zhaoxu Sun, Mengchao Wang, Ziyu Zhu, Chiyu Wang, Yunpeng Zhang, Wenlin Liu, Yun Wang, Xue Zheng, Rui Sun, Junfeng Ni, Hongyu Pan, Zhongxu Sun, Fei Yu, Zengye Ge, Mengmeng Du, Nianfei Fan, Mingchao Sun, Yu Liu, Yongchang, Yanqing Zhu, Jiahang Wang, Ning Ying, Yuze Xuan, Di Yang, Zhicheng Liu, Zhe Gao, Tingbing Xu, Jiacheng Sui, Wenjin Yang, Junnan Lai, Shufeng Liu, Yuan Liu, Zheng Zhou, Yingliang Peng, Dawei Cao, Kaifeng Sheng, Yuxiang Cai, Fei Lu, Mu Xu, Ning Guo
ABot-World-0 aims to make interactive video world models run in real time on a single desktop GPU while preserving controllable, coherent long-horizon environments.
AlayaWorld Team, Kaipeng Zhang, Chuanhao Li, Yifan Zhan, Yongtao Ge, Yuanyang Yin, Jiaming Tan, Kang He, Liaoyuan Fan, Mingliang Zhai, Ruicong Liu, Xiaojie Xu, Xuangeng Chu, Zhen Li, Zhengyuan Lin, Zhixiang Wang, Zian Meng, Zihui Gao
AlayaWorld is a large interactive video world model designed to generate persistent, explorable environments over long time horizons while responding quickly to user prompts and camera actions.
Zhen Li, Zian Meng, Shuwei Shi, Mingliang Zhai, Jiaming Tan, Chuanhao Li, Kaipeng Zhang
This paper argues that truly interactive AI game worlds need explicit, persistent state dynamics and introduces a large-scale dataset and framework to move beyond pixel-only video prediction.
Kairos Team, Fei Wang, Shan You, Qiming Zhang, Tao Huang, Zuoyi Fu, Zhisheng Zheng, Yunlong Xi, Feng Lv, Xiaoming Wu, Zeyu Liu, Cong Wan, Pu Li, Ruiqing Yang, Xiaoou Li, Wei Wang, Kangkang Zhu, Yuwei Zhang, Shi Fu, Zheng Zhang, Xiaoning Wu, Xuzeng Fan, Dacheng Tao, Xiaogang Wang
Kairos proposes a full-stack world model for physical AI that learns from mixed embodied data, remembers over long horizons, and runs efficiently on real hardware.
Anthony Hu, Václav Volhejn, Adrien Ramanana Rahary, Chris Mulder, Aditya Makkar, Amélie Royer, Manu Orsini, Alyx Liao, Adam Jelley, Eloi Alonso, Florian Laurent, Fredrik Norén, James Swingos, Jan Hünermann, Kent Rollins, Lucas Hosseini, Matthieu Le Cauchois, Maxim Peter, Pim de Witte, Tim Brown, Vincent Micheli, Moritz Böhle, Gabriel de Marmiesse, Viktoriia Sharmanska, Lucia Specia, Michael Black, Patrick Pérez
The paper builds the first real-time multiplayer world model for Rocket League, showing that a large diffusion model can simulate coordinated multi-agent gameplay with surprisingly stable long-horizon behavior.
Haoyu Zhao, Xingyue Zhao, Hangyu Li, Biao Gong, Kehan Li, Siteng Huang, Xin Li, Deli Zhao, Zhongyu Li
This paper turns a world model into a virtual teleoperation engine, letting humans generate robot training demonstrations without being physically connected to the robot.
GigaWorld Team, Angyuan Ma, Boyuan Wang, Bohan Li, Chaojun Ni, Guo Li, Guan Huang, Guosheng Zhao, Hao Li, Hengtao Li, Jingyu Liu, Jiwen Lu, Qiuping Deng, Tingdong Yu, Xuancheng Xu, Xinyu Zhou, Xiuwei Xu, Xinze Chen, Xiaofeng Wang, Xiaoyu Tian, Yang Wang, Yifan Chang, Yukun Zhou, Yun Ye, Zhenyu Wu, Zhanqian Wu, Zheng Zhu
This paper shows how world models can serve as practical stand-ins for expensive robot testing, and introduces a benchmark and model designed to make that evaluation much more reliable.
Nicklas Hansen, Xiaolong Wang
This paper shows that hallucinations in world models are not random: they happen where training data is sparse, and the authors use that insight to detect, reduce, and fine-tune around them.
Yihao Wang, Yuheng Ji, Mingyu Cao, Yanqing Shen, Runze Xiao, Huaihai Lyu, Senwei Xie, Euan Liu, Klara Tian, Tianfeng Long, Yichi Zhang, Zhengliang Cai, Ruike Chen, Jifan Zhao, Ruochuan Shi, Zihan Tang, Jing Lyu, Wenxing Tan, Ningbo Zhang, Yangtao Hu, Yuming Gao, Xiansheng Chen, Junkai Zhao, Congsheng Xu, Boan Zhu, Ziqi Wang, Yupu Feng, Qiongqiong Zhang, Yingli Zhao, Yulong Ao, Shaoxuan Xie, You Liu, Guocai Yao, Leiduo Zhang, Xiaodan Liu, Yunyan Zhang, Yance Jiao, Xinyan Yang, Jiaxing Wei, Xu Liu, Tengfei Pan, Shaokai Nie, Chunlei Men, Sen Cui, Xiaojie Jin, Hongyang Li, Jianlan Luo, Yao Mu, Yunchao Wei, Jun Yan, Hang Zhao, Xiaolong Zheng, Jiaming Li, Yonghua Lin, Tiejun Huang, Zhongyuan Wang, Pengwei Wang
Orca is a general world model that learns a shared latent representation from video, language, and other signals so it can better predict, describe, and act in the world.
Arnav Kumar Jain, Yilin Wu, Jesse Farebrother, Gokul Swamy, Andrea Bajcsy
WEAVER is a faster, longer-horizon world model for robot manipulation that can help robots predict outcomes, improve policies, and plan actions more effectively in the real world.
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 Fefilat...
Cosmos 3 is a unified multimodal world model that can understand and generate text, images, video, audio, and actions, aiming to become a general backbone for embodied AI.
Zhikai Pan, Chih-Ting Liao, Chunrui Liu, Xi Xiao, Yitong Qiao, Chunlei Meng, Zhangquan Chen, Xin Cao
This paper tests whether LLMs can build spatial mental maps from text across languages, and finds a consistent reasoning cliff that suggests current models struggle to form robust world models.
Boxiang Qiu, Liliang Chen, Yue Liao, Nan Wang, Lintao Wang, Jiayi Luo, Wenzhi Zhao, Shengcong Chen, Di Chen, Ye Li, Chen Gao, Shuicheng Yan, Si Liu, Maoqing Yao, Guanghui Ren
GE-Sim 2.0 is a faster, more useful robotic world simulator that not only predicts video from actions but also helps train and evaluate manipulation policies in a closed loop.
NVIDIA, :, Aarti Basant, Amlan Kar, Despoina Paschalidou, Fangyin Wei, Francesco Ferroni, Guillermo Garcia Cobo, Haithem Turki, Huan Ling, Jaewoo Seo, James Lucas, Jay Zhangjie Wu, Jialiang Wang, Jonathan Lorraine, Jun Gao, Kai He, Katarina Tothova, Kevin Xie, Michał Tyszkiewicz, Qi Wu, Riccardo de Lutio, Ruilong Li, Sanja Fidler, Seung Wook Kim, Tianchang Shen, Tianshi Cao, Tobias Pfaff, William Lew, Xindi Wu, Xuanchi Ren, Yifan Lu, Yuxuan Zhang, Zan Gojcic, Zian Wang
OmniDreams is a real-time AI driving simulator that generates photorealistic future scenes from actions, aiming to make autonomous vehicle testing safer, broader, and more realistic.