Motus2 is a self‑evolving general world model designed for dexterous manipulation. It integrates a shared‑weight model that offers three control interfaces—a policy, a simulator, and an evaluator—forming a closed decision‑and‑learning loop for policy improvement. The system scales both model size and data, progressing from large‑scale monocular egocentric data to synchronized stereo data and robot‑domain adaptation, while also incorporating tactile feedback and a biomimetic platform with dual arms and hands.
By Hongzhe Bi, Zihao Zhou, Yihang Tang, Jingrui Pang, Shuhe Huang, Haitian Liu, Runqing Wang, Shuai Huang, Yichen Wang, Yiming Cheng, Ruowen Zhao, Zhenghua Li, Hengkai Tan, Xiaolong Liu, Jinhui Wan, Jiabao Liu, Min Zhao, Fan Bao, Jun Zhu
DexTouch-WM is an action‑conditioned world model that learns from scalable human touch to predict future RGB observations and bilateral tactile dynamics for dexterous robot manipulation. By using compatible piezoresistive arrays on both human and robot hands and retargeting human motion into the robot action space, the model can be supervised with human interaction data while keeping a fixed amount of real‑robot supervision. Experiments show that adding up to 100 hours of human interaction improves robot‑domain visual, geometric, and contact prediction, and the model can serve as a surrogate environment for policy evaluation and synthetic trajectory generation.
By Yan Qin, Yue Chen, Wenwei Lin, Shujia Liu, Chuqiao Lyu, Kailun Su, Chenze Yu, Ping Luo, Wenbo Ding, Tianxing Chen, Renjing Xu
arXiv:2607. 03964v1 Announce Type: cross Abstract: World models are rapidly becoming a core infrastructure for embodied intelligence and interactive agents: they provide controllable simulators in which agents can perceive, act, forecast, and acquire scalable experience.
By Jianjie Fang, Yongyan Xu, Ziyou Wang, Chen Gao, Yuchao Huang, Zhaolu Wang, Rongze Tang, Mingyuan Jia, Baining Zhao, Weichen Zhang, Xin Zhang, Haisheng Su, Yu Shang, Wei Wu, Xinlei Chen, Yong Li
Action-conditioned world models (ACWMs) promise to provide embodied AI with scalable predictive simulators for planning, policy evaluation, and data generation. Realizing this promise requires precise action-conditioned transitions rather than merely plausible outputs.
arXiv:2609.38059v1 Announce Type: cross
Abstract: Real-world robot learning is constrained by the cost of collecting experience and evaluating candidate behaviors. Video generation models offer a sca...
By Shenghe Zheng, Wenbo Li, Jiyao Zhang, Bin Xia, Haoyang Huang, Nan Duan, Jiaya Jia
The paper introduces DSP: Dexterity from Supervised Play, a framework where a robot learns a play policy from brief human demonstrations via behavior cloning and then autonomously gathers extensive interaction data to train a world model. During inference, the play policy guides model‑predictive control by proposing action sequences evaluated by the learned model, and a self‑play distillation step produces a closed‑loop, goal‑conditioned policy. Experiments on underactuated pushing and in‑hand pose reorientation show DSP outperforms hindsight behavior cloning by 69.6% in success rate and matches reinforcement learning performance while using 490 times less data.
The paper introduces DSP: Dexterity from Supervised Play, a framework where a robot learns a play policy from minutes of human play via behavior cloning. The robot then autonomously uses this policy to gather hours of interaction data, training a world model that guides model‑predictive control during inference. The approach is validated on underactuated pushing and in‑hand pose reorientation tasks, outperforming hindsight behavior cloning by 69.6% in real‑world success rate and matching reinforcement learning performance with 490× less data.
By Botao He, Yiming Dou, Yiannis Aloimonos, Jitendra Malik, Akash Sharma, Ruoshi Liu
arXiv:2608. 09298v1 Announce Type: cross Abstract: Action-conditioned world models (ACWMs) promise to provide embodied AI with scalable predictive simulators for planning, policy evaluation, and data generation.
By 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
The survey "World-Action Models for Robot Learning and Control" reviews recent advances in coupling future world prediction with executable action generation for robots in open environments. It clarifies the scope of World-Action Models (WAMs) relative to conventional world models, model-based RL, and Vision‑Language‑Action policies, and organizes existing methods through a unified taxonomy covering representations, transition modeling, action interfaces, architectures, training pipelines, data modalities, and scaling strategies. The paper also surveys applications in manipulation, navigation, and autonomous driving, summarizes datasets, benchmarks, and metrics, and discusses key challenges such as action alignment, spatial consistency, long‑horizon memory, and efficient inference.
By Zuxing Lu, Hongjia Zhai, Guanzhi Wang, Huajian Zeng, Jiaqi Yang, Jingyu Liu, Lei Cheng, Yuantai Zhang, Yuheng Qiu, Zezhou Cheng, Ivan Laptev, Danfei Xu, Benjamin Riviere, Giuseppe Loianno, Eric Xing, Xingxing Zuo
arXiv:2610.22340v2 Announce Type: replace-cross
Abstract: How can robots autonomously collect the contact-rich experience needed to learn dexterous manipulation? We present PlayPolicy: Dexterity from...
By Botao He, Yiming Dou, Yiannis Aloimonos, Jitendra Malik, Akash Sharma, Ruoshi Liu
arXiv:2609.27656v1 Announce Type: cross
Abstract: Physical intelligence requires more than predicting how the world may evolve: predictions must remain actionable as the world continues to change. We...
By Jisong Cai, Yao Mu, Ganlin Yang, Zhe Cao, Zhangzheng Tu, Xing Gao, Kailin Li, Xinyu Zhan, Lixin Yang, Yangkun Zhu, Haoxiang Ma, Ming Zhou, Qiaojun Yu, Yufei Xue, Liqun He, Yifei Yao, Yifan Zhu, Long Ling, Bingqi Jiang, Haoyu Guo, Xueyue Zhu, Bowen Zhou, Bin Zhao, Tianfan Xue, Chunhua Shen, Weinan Zhang
Open‑HumanScale presents the first fully open recipe for scaling egocentric human video pretraining to 50,000 hours, supported by the curated Open‑HumanScale‑50K corpus annotated with hand motion and natural language. Using this corpus, the authors develop HumanWAM‑Vanilla, a world–action model that achieves high success rates on RoboTwin 2.0 and RoboDojo after robot post‑training, and HumanWAM‑Goal, a visual‑goal‑conditioned model that further improves zero‑shot performance and demonstrates embodied in‑context learning on physical robots. The paper also releases the dataset, curation pipelines, pretrained checkpoints, and evaluation tools to enable reproducible scaling research in embodied AI.
By Juncheng Ma, Jiaxin Li, Jiankai Tu, Bo Liang, Guodong Lv, Yufan Deng, Junzhe Tang, Liangzhu Yang, Chen Bian, Zicong Cao, Baohao Zhu, Jianxin Bi, Tengfei Yan, Yinyuan Zhang, Kewei Zhang, Xinglong Chen, Kaiqi Chen, Duomin Wang, Xiaotian Tang, Liang Tan, Li Li, Yuan Xu, Haosen Yang, Yuqi Wang, Jingfei Xia, Songyan Huang, Zhiyang Dou, Zhen Dong, Enze Xie, Tat-Seng Chua, Daquan Zhou