Jul 2026
RoboTTT: Context Scaling for Robot Policies
RoboTTT, a robot model and training recipe that scale visuomotor context to 8K timesteps, three orders of magnitude beyond state-of-the-art policies, without growing inference latency, unlocks new robot capabilities: one-shot in-context imitation from human video demonstrations, on-the-fly policy improvement, robustnes...
Yunfan Jiang, Yevgen Chebo-tar, Ruijie Zheng et al.
· arXiv.org · 9 citations