Wanyuan Wang

model compression (1) deep reinforcement learning (1) zero-shot learning (1) sequential decision making (1) preference learning (1) attention mechanism (1) in-context learning (1) mechanism design (1) model reduction (1) incentive compatibility (1) mixed integer linear programming (1) mixed-integer linear programming (1) budget feasibility (1) large language model (1) log parsing (1) vehicle repositioning (1) supply demand balance (1) budget-feasible mechanism (1) diffusion mechanism (1) graph auction (1)