Xu, C., Liang, Z., Zhang, Y., Chan, C. M., Wang, J., Xiao, Y., Hu, M., Yang, X., & Mu, Y. (2026). M2Tok: Multi-head Multi-codebook Discrete Action Tokenization for Vision-Language-Action Models. https://omanscience.com/en/articles/m2tok-multi-head-multi-codebook-discrete-action-tokenization-for-vision-language-action-models