Huaijie Wang

knowledge distillation (2) transformer architecture (1) model quantization (1) reinforcement learning (1) continual learning (1) offline reinforcement learning (1) policy optimization (1) neural network optimization (1) language grounding (1) behavior cloning (1) value function (1) game ai (1) credit assignment (1) semantic prior (1) real-time strategy game (1) visual prototype (1) multi-step reasoning (1) large language model (1) constrained rl (1) 1-bit quantization (1)