Michael S Ryoo

long-form video (2) video understanding (2) zero-shot learning (1) multi-task learning (1) action recognition (1) transfer learning (1) visual question answering (1) self-supervised learning (1) multimodal learning (1) partially observable environment (1) generalization capability (1) vision language model (1) embodied agent (1) trajectory feedback (1) model scaling (1) retrieval-augmented generation (1) long video understanding (1) video question answering (1) scalable model (1) online exploration (1)