Jun Song

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