BiCAT builds bimanual coordination directly into a VLA's action tokens
DJiafei · x · 2026-11-18
DJiafei introduces BiCAT (Bimanual Coordination Action Tokenization), addressing how current VLA tokenizers flatten both robot arms into a single vector.
- Core insight: a bimanual robot is two arms, not one arm with twice the joints; human arms share a movement repertoire while taking complementary roles (one holds, one folds).
- Each arm gets its own token stream, with motion patterns shared across arms and coordination explicitly modeled.
- Mirroring trick: since both arms share one workspace and are symmetric about the body, BiCAT flips the right arm's signed joints so mirrored motions receive the same tokens.
Related event: NUS Introduces BiCAT, a Bimanual Coordination Action Tokenizer for Robots(4 posts)→
More from Embodied
- Rodney Brooks, Roomba creator, calls today's humanoids learning dexterity 'pure fantasy' — lukas_m_ziegler · 2026-11-18
- Two arms, two token streams, one shared vocabulary: new robot manipulation work open-sourced — DJiafei · 2026-11-18
- NUS's BiCAT action tokenizer for bimanual robots: 113/150 real-robot wins, 2.7x lower latency than OAT — 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
- San Bernardino County deploys autonomous firefighting drones to kill wildfires early — import_jmr · 2026-11-18