Yong Lin

out-of-distribution generalization (4) reinforcement learning from human feedback (3) large language model (3) distribution shift (3) bilevel optimization (2) domain generalization (2) sample reweighting (2) reward model (2) uncertainty estimation (2) invariant risk minimization (2) active learning (2) spurious correlation (2) preference learning (1) coreset selection (1) model robustness (1) uncertainty quantification (1) model selection (1) continual learning (1) feature selection (1) policy learning (1)