Fengyun Rao

multimodal learning (4) multimodal large language model (4) video understanding (3) diffusion model (3) reinforcement learning (2) vision-language model (2) multi-modal learning (2) visual perception (2) multimodal reasoning (2) probabilistic modeling (1) data augmentation (1) preference alignment (1) temporal reasoning (1) question answering (1) image generation (1) visual question answering (1) video generation (1) action recognition (1) supervised learning (1) image captioning (1)