Jie Peng

large language model (4) label poisoning attack (2) multimodal learning (2) mixture of expert (2) model merging (2) adversarial training (2) byzantine attack (2) distributed learning (2) prompt engineering (1) in-context learning (1) adversarial robustness (1) out-of-distribution generalization (1) instruction tuning (1) variance reduction (1) language model (1) uncertainty quantification (1) adversarial attack (1) strongly convex optimization (1) model unlearning (1) distributed stochastic optimization (1)