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

arXiv:2609.25820 · cs.RO, cs.LG · Submitted 2026-09-22 · Read on arXiv

cs.RO, cs.LG

Submitted: 2026-09-22

Updated: 2026-09-22

Comments: 5 pages, 1 figure, 4 tables

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

Quantization — 15× in this paper · explained in 12 episodes
Reconstruction Error — 12× in this paper · explained in 2 episodes
Tokenization — 11× in this paper · explained in 2 episodes
Fidelity — 10× in this paper · explained in 2 episodes
Ablation — 4× in this paper · explained in 1 episode
Closed-Loop Control — 3× in this paper · explained in 3 episodes
Perplexity — 2× in this paper · explained in 3 episodes
Vision-Language-Action (VLA) Models — 2× in this paper · explained in 2 episodes
Action Chunking — 1× in this paper · explained in 1 episode
Action Space — 1× in this paper · explained in 1 episode
Adaptation — 1× in this paper · explained in 1 episode
Conference on Robot Learning — 1× in this paper
Decode — 1× in this paper · explained in 2 episodes
Generalization — 1× in this paper · explained in 13 episodes
International Conference on Learning Representations — 1× in this paper
Principal Component Analysis — 1× in this paper
Principal Component Analysis (PCA) — 1× in this paper · explained in 4 episodes