Yao-Ching Yu

information retrieval (2) retrieval-augmented generation (2) large language model (2) instruction tuning (1) web search (1) reward learning (1) ensemble method (1) instruction fine-tuning (1) reinforcement learning agent (1) dynamic reasoning (1) schema mapping (1) adaptive refinement (1) token generation (1) reasoning distillation (1) multi-dimensional exploration (1) dynamic reasoning network (1) intent-aware strategy selection (1) knowledge intensive reasoning (1) test-time reinforcement learning (1) confidence-based reward (1)