Jun-Gong Han

PhaseLoRA: Control-Regime-Conditioned Low-Rank Adaptation for Continuous-Action Vision-Language-Action Policies

A lightweight LoRA parameterization that conditions adaptation at each action-chunk prediction step using two weakly supervised descriptors: fine-control tendency and event/boundary intensity is proposed, establishing within-trajectory conditioning as an effective lightweight PEFT axis for continuous-action VLA policie...