Biqing Qi

large language model (8) language model (4) multi-agent system (4) reinforcement learning (3) memory module (2) neural network (2) collaborative generation (2) state space model (2) supervised fine-tuning (2) code generation (2) multimodal learning (2) test-time scaling (2) reinforcement learning from human feedback (2) attention mechanism (2) multimodal large language model (2) knowledge distillation (2) model compression (2) preference optimization (2) continual learning (2) preference learning (1)