Andrew Zhao

large language model (2) adversarial learning (2) multi-task learning (1) in-context learning (1) multitask learning (1) ai safety (1) upper confidence bound (1) red teaming (1) contextual bandit (1) language model (1) language model agent (1) intrinsic reward (1) safety evaluation (1) unsupervised reinforcement learning (1) prompt optimization (1) markov decision process (1) functional representation (1) agent system (1) function class (1) knowledge extraction (1)