Shihan Dou

Privacy (1)

large language model (12) reinforcement learning (6) reward model (5) reinforcement learning from human feedback (3) language model (3) text classification (3) mutual information (3) distribution shift (3) instruction tuning (2) knowledge retention (2) question answering (2) preference alignment (2) compiler feedback (2) code generation (2) representation learning (2) out-of-distribution generalization (2) sequential decision making (1) model robustness (1) reward modeling (1) object detection (1)