Yichen Zhu

knowledge distillation (6) model compression (4) 3d visual grounding (2) vision-language-action model (2) few-shot learning (2) point cloud (2) multimodal large language model (2) multimodal learning (2) multi-task learning (2) retrieval-augmented generation (2) embodied agent (2) teacher model (2) multi-modal learning (2) image synthesis (2) student model (2) weakly supervised learning (1) graph classification (1) action recognition (1) policy gradient (1) convex optimization (1)