Muling Wu

large language model (5) federated learning (2) human preference (2) pre-trained language model (2) representation engineering (2) parameter-efficient fine-tuning (2) parameter efficient fine-tuning (2) representation editing (2) model privacy (2) reinforcement learning (1) neural network interpretability (1) model safety (1) intellectual property (1) reinforcement learning from human feedback (1) contrastive learning (1) unsupervised learning (1) privacy preservation (1) language model (1) code generation (1) representation learning (1)