Chetan Bansal

large language model (3) reward modeling (1) domain adaptation (1) knowledge transfer (1) knowledge distillation (1) preference alignment (1) preference optimization (1) instruction following (1) synthetic data generation (1) reinforcement learning from human feedback (1) machine learning (1) program analysis (1) reward hacking (1) model fine-tuning (1) model collaboration (1) domain-specific knowledge (1) web agent (1) small language model (1) weak-strong collaboration (1) collaborative framework (1)