Jie Peng

large language model (5) adversarial training (2) byzantine attack (2) mixture of expert (2) model merging (2) distributed learning (2) multimodal learning (2) label poisoning attack (2) prompt engineering (1) in-context learning (1) adversarial robustness (1) knowledge graph question answering (1) out-of-distribution generalization (1) instruction tuning (1) uncertainty quantification (1) strongly convex optimization (1) distributed stochastic optimization (1) model unlearning (1) adversarial attack (1) distribution shift (1)