Songzhu Mei

multi-agent reinforcement learning (2) large language model (2) value factorization (2) distributional reinforcement learning (1) model inference (1) sample selection (1) neural network expressivity (1) supervised fine-tuning (1) mixing network (1) dormant neuron (1) weight transfer (1) cooperative game (1) inference acceleration (1) heterogeneous computing (1) speculative decoding (1) game-theoretic analysis (1) shapley value (1) risk-sensitive reinforcement learning (1) multi-perspective analysis (1) influence score (1)