Beyond Reconstruction Error: Analytical and Data-Driven Action Tokenization for Autoregressive Vision-Language-Action Models
It is shown that reconstruction fidelity alone cannot reliably select action representations for autoregressive control, motivating joint evaluation of geometric fidelity, sequence predictability, decoder stability, and closed-loop performance.
Yu-Xin Yang, Gao-Han He, Chang-Xue Guan et al.
· 0 citations