Jun Song

reinforcement learning (4) vision-language model (4) multimodal large language model (3) vision language model (3) benchmark evaluation (3) multimodal learning (3) image generation (2) mobile agent (2) large vision language model (2) vision transformer (2) video understanding (2) token compression (2) visual question answering (2) question answering (1) self-supervised learning (1) direct preference optimization (1) preference learning (1) action recognition (1) visual reasoning (1) dataset creation (1)