Lu Lin

large language model (4) graph neural network (3) adversarial attack (3) backdoor attack (2) adversarial learning (2) model alignment (2) derivative estimation (2) gradient compression (2) jailbreak attack (2) federated learning (2) nonparametric regression (2) hallucination mitigation (2) language model alignment (1) distributed learning (1) robust regression (1) preference optimization (1) text generation (1) stochastic optimization (1) in-context learning (1) ai safety (1)