TL;DR — In autoregressive VLA (vision-language-action) models, the action tokenizer is the key interface that compresses continuous robot commands into discrete tokens and then reconstructs predicted tokens back into executable commands. Existing tokenizers only reduce pointwise reconstruction error such as MSE; they do not check whether the “fine adjustments” between demonstrations survive compression. This paper newly defines PRC (Physical Rank Consistency), which measures the degree to which the ranking of physical distances is preserved in the reconstructed action space, and proposes ActionPiece, which supervises representation learning and quantization jointly to preserve that relation. Under the same Qwen3-VL-4B policy training setup, it achieves state-of-the-art results of 94.8% on LIBERO and 68.8% on unseen LIBERO-Plus (source: Abstract, Table 1).

Robotics on Jaehun's Blog

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

ActionPiece: Rethinking Action Tokenization Beyond Reconstruction Error, via Physical Ranking