Hao Henry Wang

retrieval-augmented generation (2) in-context learning (1) multimodal learning (1) visual reasoning (1) instruction tuning (1) tree search (1) data selection (1) supervised fine-tuning (1) multimodal large language model (1) inference acceleration (1) speculative decoding (1) draft model (1) iterative training (1) chain of thought (1) chart understanding (1) group relative policy optimization (1) gui agent (1) large language model (1) tree pruning (1) self-play optimization (1)