SOURCE-LINKED INTELLIGENCE

Beyond Reconstruction Error: Analytical and Data-Driven Action Tokenization for Autoregressive Vision-Language-Action Models

arXiv · AI, language, vision and robotics · article · Sep 22, 2026 · UTC

Discrete action tokenization is central to autoregressive vision-language-action (VLA) models, yet action representations are often evaluated primarily through reconstruction fidelity. We ask which representation properties actually matter for closed-loop control by comparing fixed analytical, data-driven linear, and nonlinear neural representations under a unified tokenization interface. Across rate-distortion analysis, sequence-modeling diagnostics, and 3,500 LIBERO rollouts, representation rankings change with the evaluation criterion. PCA achieves lower nominal reconstruction error than Te

Read original source ↗ Open in workspace

recordType

paper

region

Global