Preprint
Aug 2026
Grounded Semantic Re-Binding for Robust Instruction Generalization in Vision-Language-Action Models
This work demonstrates that robust semantic grounding can be achieved through elegant structural design, bypassing the inefficient brute-force data scaling paradigm and introduces ParaVLA, a natively decoupled 0.33B-parameter model exhibiting near-perfect robustness to instruction rewording.
Zhaokai Yin, Zhi-Peng Zhang
· 0 citations