Shanghaoran Quan

Architectures (1)

large language model (2) reinforcement learning (1) multi-task learning (1) reward modeling (1) preference learning (1) knowledge transfer (1) prompt engineering (1) code generation (1) multilingual code (1) instruction tuning (1) safety alignment (1) reinforcement learning from human feedback (1) low-rank adaptation (1) parameter efficient fine-tuning (1) mixture of expert (1) supervised fine-tuning (1) jailbreak attack (1) multi-agent collaboration (1) context granularity (1) data generation (1)