Huazheng Wang

multi-armed bandit (5) adversarial attack (4) large language model (4) regret bound (3) representation learning (3) language model (2) adversarial learning (2) domain-invariant representation (2) online learning (2) bayesian regret (2) domain adaptation (2) direct preference optimization (2) human feedback (2) tree search (2) reinforcement learning from human feedback (2) bayesian optimization (2) machine reading comprehension (2) off-policy learning (2) adversarial domain adaptation (2) thompson sampling (2)