Generalizable robot manipulation requires policies that can anticipate how visual scenes evolve while executing language instructions. While recent Vision-Language-Action models benefit from large-scale pretraining, their predominantly static pretraining objectives provide limited supervision for physical dynamics and temporal causality, leaving control-relevant knowledge to be learned from downstream robot demonstrations.
The paper introduces P³-WAM, a unified world action model for egocentric dexterous manipulation that integrates 3D perception, action-conditioned prediction, and goal-directed planning. It operates in three modes—Perceive, Predict, and Plan—using a mixture-of-transformers architecture that shares base weights and adapts to modality-specific inputs. Experiments demonstrate that unified training improves performance across all three capabilities, outperforming specialized baselines on 3D hand reconstruction and action-conditioned video prediction while producing more instruction‑adherent manipulation videos.
By Zirui Wu, Chen Guo, Tianjian Jiang, Zeren Jiang, Zeming Li, Lingchen Yang, Longteng Duan, Ying Xue, Handi Yin, Shenyuan Gao, Martin R. Oswald, Jun Zhang, Ping Tan, Jie Song
Scaling robot learning requires large-scale, diverse demonstrations, yet real-world data collection via teleoperation remains prohibitively expensive and time-consuming. While video diffusion models offer a promising avenue for data scaling, existing generative approaches are often limited to superficial visual augmentation, or suffer from embodiment hallucinations that yield physically infeasible motions.
arXiv:2606. 00054v1 Announce Type: cross Abstract: Recent progress in generalizable embodied control has been driven by large-scale pretraining of Vision-Language-Action (VLA) models.
By Zhiyuan Feng, Qixiu Li, Huizhi Liang, Rushuai Yang, Yichao Shen, Zhiying Du, Zhaowei Zhang, Yu Deng, Li Zhao, Hao Zhao, Zongqing Lu, Oier Mees, Marc Pollefeys, Jiaolong Yang, Baining Guo
arXiv:2609.22332v1 Announce Type: cross
Abstract: Generalizable robot manipulation requires predicting how a scene will evolve, identifying where interactions are feasible, and determining how to act...
By Jiadi You, Qize Yu, Yue Chen, Minghong Cai, Zhide Zhong, Yuran Wang, Bowen Ping, Jiaqi Liang, Zhenhao Shen, Haodong Yan, Yinchuan Li, Ruihai Wu, Xiaojuan Qi, Yingcong Chen
RawVLA introduces a streaming neural image signal processor that adaptively renders RAW observations for vision‑language‑action (VLA) policies, focusing on imaging factors that influence embodied behavior. The authors systematically analyze how five ISP dimensions—gain, sensor noise, chromatic response, tonal response, and bit depth—affect action prediction and manipulation success, showing that RAW‑to‑RGB processing significantly shapes outcomes. They also present RawVLA‑Bench, a RAW‑domain manipulation benchmark that evaluates image processing as an explicit variable across clean and adverse conditions, demonstrating that RawVLA maintains performance under standard settings while markedly improving robustness under degraded imaging.
By Shuhong Liu, Heng Zhou, Lingfeng Qian, Yuhao Fang, Xianbao Hou, Qianyu Zhou, Lin Gu, Wei Sui, Jianfei Yang, Ziteng Cui
ZimaBlue is a scalable framework that learns generalizable World Action Models (WAMs) from large-scale egocentric videos. It follows a three-stage curriculum: causal video pre‑training, video‑action mid‑training with a unified action representation, and final specialization to a target robot. The system employs an asynchronous Slow‑Fast architecture to enable real‑time 30 Hz action prediction, achieving a jump in real‑robot zero‑shot success from 36.1% to 77.8% when leveraging over 120,000 hours of embodied video.
By 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
InfiNoVA is a data‑augmentation framework that transforms synchronized multi‑camera demonstrations into a dense, geometrically consistent set of training views by reconstructing each manipulation trajectory as a time‑varying 3D Gaussian. The method renders novel observations from sampled camera poses while preserving the original state‑action pairs, improving frame‑level fidelity and temporal consistency compared to generative synthesis. Across four real‑world manipulation tasks, policies trained with InfiNoVA achieve 5.4× higher average success under unseen randomized viewpoints than VISTA‑based augmentation and 1.7× higher success than training on all five physical camera views.
By Sai Puneeth Reddy Gottam, Elmar Rueckert, Vedant Dave
arXiv:2607. 11643v1 Announce Type: cross Abstract: Recent foundation image and video generation models offer strong generalization and controllability, but their direct application to embodied scenarios is limited by requirements for multi-view consistency, geometric coherence, and robot embodiment constraints.
By Xinghang Li, Jun Guo, Qiwei Li, Long Qian, Hang Lai, Yueze Wang, Hongyu Yan, Jiahang Cao, Xi Chen, Jingen Qu, Jiaxi Song, Nan Sun, Hanye Zhao, Futeng Liu, Wanli Peng, Heyun Wang, Yunhong Wang, Caoyu Xia, Jack Zhao, Diyun Xiang, Hangjun Ye, Heng Qu, Huaping Liu, Jason Li
arXiv:2606. 10025v1 Announce Type: cross Abstract: We present GHOST, a framework for learning visuomotor manipulation policies that generalize beyond the training distribution.
By Sriram Krishna, Ben Eisner, Haotian Zhan, Ying Yuan, Haoyu Zhen, Chuang Gan, Shubham Tulsiani, David Held
arXiv:2606. 20118v1 Announce Type: cross Abstract: Vision-language-action (VLA) policies have shown strong potential for general-purpose manipulation, yet they often fail on novel, out-of-distribution objects whose appearance or geometry deviates from the training distribution.
By Jonghoon Lee, Seong Hyeon Park, Byungwoo Jeon, Minha Lee, Jinwoo Shin
arXiv:2610.33685v1 Announce Type: cross
Abstract: Vision-Language-Action (VLA) models are bottlenecked by the scarcity of robot data. Egocentric human manipulation videos offer an abundant, diverse,...
By Qingyuan Cai, Bo Zhang, Yongzhen Huang, Jianyu Chen