← Back to all news
arXiv AI By Shijie Lian, Bin Yu, Zhaolong Shen, Xiaopeng Lin, Yichao Du, Zhirui Zhang, Laurence T. Yang, Kai Chen

ActionPiece: Rethinking Action Tokenization for Autoregressive Vision-Language-Action Models

Read the original on arXiv AI →

ActionPiece rethinks how actions are tokenized for autoregressive vision‑language‑action models by introducing physical rank consistency (PRC) to evaluate relational fidelity of reconstructed actions. The method jointly supervises representation learning and quantization to preserve local physical distance rankings, improving both PRC and policy success. Experiments on LIBERO, LIBERO‑Plus, SimplerEnv, and VLA‑Arena show significant gains over baseline tokenizers.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
1d ago

${M}^2$Tok: Multi-head Multi-codebook Discrete Action Tokenization for Vision-Language-Action Models

The paper introduces ${M}^2$Tok, a Multi-head Multi-codebook Action Tokenizer that reduces reconstruction loss in discrete action tokenization for Vision‑Language‑Action models. By decomposing latent action features into multiple heads and assigning independent codebooks to each, the tokenizer expands representational expressivity and improves policy performance. Experiments on RoboTwin, Simpler‑Env, and zero‑shot real‑world tasks show superior reconstruction fidelity and higher success rates compared to prior methods.

By Chunpu Xu, Zhixuan Liang, Yuhao Zhang, Chi-Min Chan, Jessie Wang, Yang Xiao, Mengkang Hu, Xiaokang Yang, Yao Mu
llmsnlpefficiencymultimodalbenchmarks
More like this →