Kunchang Li

zero-shot learning (3) multimodal learning (2) large language model (2) video understanding (2) few-shot learning (2) video generation (2) diffusion model (2) multi-agent system (2) knowledge distillation (1) video recognition (1) multi-task learning (1) self-supervised learning (1) style transfer (1) in-context learning (1) vision transformer (1) 3d vision (1) point cloud (1) transfer learning (1) multi-modal learning (1) token selection (1)