نسخة أولية وصول مفتوح
ReWeight: Leveraging Human Data for VLA Post-Training via Demonstration Retrieval and Sample Weighting
Post-training vision-language-action (VLA) models for specific robots and tasks requires in-domain demonstrations, yet collecting diverse robot data is costly. Egocentric human demonstrations provide a scalable alternative, but directly mixing human and robot data can introduce cross-embodiment discrepancies and degrad …