Beong-woo Kwak

large language model (6) dialogue system (3) reinforcement learning (2) zero-shot learning (1) knowledge distillation (1) question answering (1) transfer learning (1) multimodal learning (1) scene graph generation (1) model forgetting (1) reinforcement learning from human feedback (1) reward function (1) knowledge graph (1) language model (1) algorithmic reasoning (1) synthetic datum (1) recommendation system (1) multi-turn dialogue (1) reasoning model (1) chain-of-thought reasoning (1)