VLA Grounder: Language-Conditioning Space Optimization for Black-Box VLA Models
arXiv:2607.04517v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) models are commonly treated as end-to-end action policies conditioned on natural-language task descriptions. In practice, however, their behavior often depends sharply on how the instruction is phrased, suggesting that language is not merely a task label but an optimizable conditioning input. We study whether frozen VLA policies can be improved by optimizing language space rather than updating action weights. Our m…