Wei Hao

large language model (2) uncertainty quantification (1) out-of-distribution generalization (1) ai safety (1) model serving (1) kalman filter (1) multi-object tracking (1) adversarial attack (1) deep neural network (1) jailbreak attack (1) edit distance (1) prompt injection (1) tail latency (1) latency optimization (1) performance predictability (1) text detection (1) text rewriting (1) safety training (1) llm-generated text detection (1) camera relocalization (1)