Yushi Hu

language model (3) visual reasoning (2) zero-shot learning (2) instruction tuning (2) text-to-image generation (2) large language model (2) preference learning (1) visual question answering (1) reinforcement learning (1) text generation (1) information retrieval (1) multimodal learning (1) image captioning (1) text representation (1) question answering (1) few-shot learning (1) language model alignment (1) model merging (1) semantic alignment (1) in-context learning (1)