AI RESEARCH
Stable Language Guidance for Vision-Language-Action Models
arXiv CS.CL
•
ArXi:2601.04052v2 Announce Type: replace-cross Vision-Language-Action (VLA) models have nstrated impressive capabilities in generalized robotic control; however, they remain notoriously brittle to linguistic perturbations. We identify a critical ``modality collapse'' phenomenon where strong visual priors overwhelm sparse linguistic signals, causing agents to overfit to specific instruction phrasings while ignoring the underlying semantic intent. To address this, we propose Residual Semantic Steering (RSS), a probabilistic framework that disentangles physical affordance from semantic execution.