نسخة أولية وصول مفتوح
RoboIRS: Inference-Time Internal Representation Steering for Generalist Robot Policies
Vision-language-action (VLA) and world-action models (WAMs) often degrade under out-of-distribution task variations despite retaining partial task capability. To recover such capability, we propose RoboIRS, an inference-time internal representation steering method that uses successful and failed rollouts to train linea …