Zhiyuan Ma

diffusion model (7) multimodal learning (3) knowledge distillation (3) large language model (3) retrieval-augmented generation (3) knowledge retrieval (2) 3d reconstruction (2) multi-view generation (2) few-shot learning (2) attention mechanism (2) task-oriented dialogue (2) preference optimization (2) residual learning (2) knowledge grounding (2) visual question answering (2) video generation (2) reinforcement learning (2) multi-modal learning (2) vision-language model (2) intention reasoning (2)