BiCAT mirrors the right arm's signed joints so both arms share motion tokens
DJiafei · x · 2026-11-18
Part 3 of the BiCAT thread explains how two token streams share a motion language: both arms share one workspace and are symmetric about the body, like human hands. BiCAT flips the right arm's signed joints, so mirrored motions receive the same tokens.
This lets the model learn each mirrored motion pattern once instead of separately for each arm, reducing the cost of learning bimanual coordination.
More from Embodied
- NUS's BiCAT action tokenizer for bimanual robots: 113/150 real-robot wins, 2.7x lower latency than OAT — DJiafei · 2026-11-18
- Two arms, two token streams, one shared vocabulary: new robot manipulation work open-sourced — DJiafei · 2026-11-18
- BiCAT gives each robot arm its own token stream instead of one flat vector — DJiafei · 2026-11-18
- BiCAT builds bimanual coordination directly into a VLA's action tokens — DJiafei · 2026-11-18
- Startups put Meta glasses on day laborers to harvest first-person video for robotics companies — hiclemi · 2026-11-18
- NVIDIA RTX Spark compact desktops ship with 128GB unified memory for local AI agents — NVIDIA Blog · 2026-11-18