Vision-Language-Action (VLA) models provide strong behavioral priors for robotic manipulation, yet efficiently adapting them to downstream tasks remains challenging. Recent work addresses this challenge by adapting frozen VLAs through online reinforcement learning (RL), whose sample efficiency depends on the quality of...
De-Hao Huang, Jian-Bang Liu, Jian-Pan Gao et al.· 0 citations
ActGaze is a training approach that guides VLA policies to gaze on task-relevant regions, much like humans gaze on critical visual cues while executing precise movements, and consistently outperforms the base VLA policy and other visual-grounding approaches.
Predictive Sensorimotor Representation learning is introduced, a framework that learns a hierarchy of predictive representations from multimodal sensorimotor signals and integrates them into the action stream of a visuomotor policy, and is instantiate within a Vision-Language-Action model, resulting in PSR-VLA.