Teng Xiao

graph neural network (4) large language model (3) variational inference (2) collaborative filtering (2) logged feedback (2) reinforcement learning (2) large language model alignment (2) direct preference optimization (2) adversarial robustness (1) certified robustness (1) contrastive learning (1) bayesian inference (1) matrix factorization (1) em algorithm (1) domain generalization (1) policy optimization (1) semi-supervised learning (1) self-supervised learning (1) graph representation learning (1) imitation learning (1)