Vidhi Jain

robot manipulation (2) mobile manipulation (2) zero-shot learning (1) multi-task learning (1) imitation learning (1) sim-to-real transfer (1) robot navigation (1) visual question answering (1) preference learning (1) motion transfer (1) language model (1) vision-language model (1) task planning (1) dense captioning (1) spatial language (1) cross-attention transformer (1) object grasping (1) region description (1) egocentric view (1) language-conditioned policy (1)