Hyokun Yun

direct preference optimization (3) web agent (2) large language model (2) reinforcement learning from human feedback (2) language model alignment (2) preference learning (2) preference datum (2) instruction following (2) binary classification (1) probabilistic modeling (1) multi-task learning (1) knowledge distillation (1) data augmentation (1) chain-of-thought reasoning (1) model robustness (1) online learning (1) robust classification (1) preference optimization (1) graph theory (1) information retrieval (1)