This work systematically compares six causal structures, eight latent representations, and four training objectives, covering popular design choices in existing WAMs, to provide a systematic understanding of how core design choices affect world-action modeling and what principles can guide the development of future WAM...
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.
Across 30 RoboDojo tasks, using zero shot for Open and one demonstration elsewhere, RoboICL improves on official zero-shot \gptastra{} by 20--27 progress-score points in every category, and leads the leaderboard baselines on Memory and Open, achieves comparable performance to the strongest Precision baseline, and remai...