Rolling-WAM is presented, a formulation that distributes joint denoising across successive replanning cycles and delivers a 4.5x steady-state replanning speedup over standard joint WAMs.
Abstract
World Action Models (WAMs) couple action generation with future visual prediction for robotic manipulation. However, completing the joint video-action denoising process at each replanning cycle incurs substantial latency, delaying action updates and limiting closed-loop responsiveness. We present Rolling-WAM, a formulation that distributes joint denoising across successive replanning cycles. Our method maintains a sliding window of video-action chunks at staggered noise levels. At each step, a rolling noise schedule fully denoises the imminent action chunk for execution, while partially refining farther-future chunks. As the window advances with new camera observations, the retained future chunks continue their denoising process. This distributes the computational cost over time while carrying an evolving visual-action context across chunk boundaries. Evaluations on LIBERO, RoboTwin, and a real-world Unitree G1 humanoid show that Rolling-WAM achieves competitive manipulation performance. By removing the need to denoise the entire prediction horizon from scratch, it delivers a 4.5x steady-state replanning speedup over standard joint WAMs.
World action models (WAMs) that use future visual prediction at inference time incur substantial generation costs. Asynchronous execution reduces waiting by overlapping inference with robot motion, but visual predictions used for subsequent action generation must anticipate the effects of actions already scheduled for...
Xu-Yao Huang, Yi-Xuan Wang, Zeng-Yao Ye et al.· 1 citation
This work proposes DeltaWAM, which jointly predicts visual deltas and actions using dense-anchor, sparse-delta, and action streams, with three architectures that differ in representation and computation sharing, and develops Streaming Delta Memory (SDM), which updates cached anchor context with compact observed deltas,...
Han Yan, Zi-Shang Xiang, Hao-Kai Jiang et al.· 0 citations
World action models (WAMs) have emerged as a promising paradigm for robotic control by jointly predicting future visual dynamics and actions from an initial observation and instruction. However, existing WAMs struggle with long-horizon prediction, as generating dense video rollouts is highly inefficient. Some recent WA...
Fei Zhang, Zhao-Chong An, D. Frost et al.· 1 citation
Method is presented, a dual-system WAM that preserves broader-horizon world-action generation while enabling high-frequency closed-loop action updates by decoupling global planning and local refinement and shows that it naturally supports edge--cloud deployment with substantially lower communication overhead than the b...
Yi-Xin Zheng, Jiangran Lyu, Yun-Tian Deng et al.· 0 citations
Pilot, an efficient engine that reduces sparse inference overhead through lightweight scoring and cross-step reuse of token selections, is introduced, an efficient engine that reduces sparse inference overhead through lightweight scoring and cross-step reuse of token selections.
Xin-Ling Xie, Hao-Dong Wang, Jia-Zhi Mi et al.· arXiv.org· 0 citations
CtrlWAM is presented, which executes perturbed actions in a simulator and pairs them with their noised visual consequences for joint WAM learning, and further extends the action interface from ego-only control to a variable number of agent streams, allowing a unified model to represent predicted or commanded futures fo...
Chensheng Peng, Wen-Hao Ding, Ran Tian et al.· 1 citation
From feet to fingertips — we are teaching robots intelligent whole-body control, fine dexterity, and teamwork to complete a broad range of complex tasks.