DASH is presented, a Decoupled Asynchronous System for Humanoids that removes this coupling between vision-language-action backbone and action head, and achieves clearly higher pick-and-place success than the synchronous pipeline.
Bing-Zhang Wang, Nathan Zhao, Jia-Leng Ni et al.· 0 citations
Egocentric human video offers a scalable data source for dexterous manipulation, yet using it to train humanoid robots presents two challenges: (1) an embodiment gap, as human hands differ structurally from robot end-effectors and low-cost egocentric recordings lack the torso kinematics required by conventional retarge...
Hui-Min Pan, Y. Ren, Kun-Peng Song et al.· arXiv.org· 0 citations
Generative robot policies provide expressive behavior priors, but updating a large diffusion or flow-matching model through online interaction is costly. Latent-space reinforcement learning avoids updating the pretrained generator by controlling its initial sampling noise, yet high-dimensional noise can have strongly a...