AI-SOVEREIGN
Home / AI Research / BiCAT: Bimanual Coordination Action Tokenization
BIAI Research

BiCAT: Bimanual Coordination Action Tokenization

by NationalUniversityofSingapore · Xuanwei Liu, Guipu Cao, Zhongyi Luo, Jiafei Duan

Autoregressive vision-language-action (VLA) models predict discrete action tokens with the next-token objective of their vision-language backbone, so the action tokenizer defines the interface between the policy and the robot. In bimanual manipulation, the two arms share a repertoire of movements yet coordinate through complementary roles, and an action representation should capture both. However, most existing tokenizers encode both arms as a single concatenated action vector, in which motion patterns common to the two arms are not shared and cross-arm dependencies remain entangled within each token. The policy must therefore learn both aspects implicitly. We propose Bimanual Coordination…

Upvotes4
Comments2
Published16 Nov 2026

More from NationalUniversityofSingapore