Peng Yan

large language model (3) uncertainty estimation (2) reinforcement learning from human feedback (2) reward modeling (1) chain-of-thought reasoning (1) preference optimization (1) direct preference optimization (1) confidence calibration (1) egocentric vision (1) structural causal model (1) model alignment (1) probability calibration (1) multi-objective optimization (1) variational autoencoder (1) multimodal learning (1) causal reasoning (1) recommendation system (1) bayesian neural network (1) large vision-language model (1) causal inference (1)