OraCore · Topic ·research

RoboTTT scales robot memory to 8K timesteps

RoboTTT pushes robot policy context to 8K timesteps and improves long-horizon control without raising inference latency.

1 articles in this thread ·Last updated 14h ago·First seen Jul 17, 2026

Timeline

  1. RoboTTT scales robot memory to 8K timesteps seed

    RoboTTT pushes robot policy context to 8K timesteps and improves long-horizon control without raising inference latency.