AI RESEARCH
S-VAM: Shortcut Video-Action Model by Self-Distilling Geometric and Semantic Foresight
arXiv CS.CV
•
ArXi:2603.16195v1 Announce Type: new Video action models (VAMs) have emerged as a promising paradigm for robot learning, owing to their powerful visual foresight for complex manipulation tasks. However, current VAMs, typically relying on either slow multi-step video generation or noisy one-step feature extraction, cannot simultaneously guarantee real-time inference and high-fidelity foresight. To address this limitation, we propose S-VAM, a shortcut video-action model that foresees coherent geometric and semantic representations via a single forward pass.