M2Tok: Multi-head Multi-codebook Discrete Action Tokenization for Vision-Language-Action Models
Experimental results demonstrate the proposed ${M}^2$Tok, a Multi-head Multi-codebook Action Tokenizer designed to minimize reconstruction error and enhance policy performance, achieves superior reconstruction fidelity and significantly boosts the success rate of VLA models.
Chun-Pu Xu, Zhi-Xuan Liang, Yu-Hao Zhang et al.
· 0 citations