MMODELYST
People/Junlin Liu
PPL

Junlin Liu

Papers (3)
Evolutionary Enhanced Multi-Agent Reinforcement Learning for Cooperative Air CombatGradient Starvation in Binary-Reward GRPO: Why Group-Mean Centering Fails and Why the Simplest Fix WorksThe Coupling Tax: How Shared Token Budgets Undermine Visible Chain-of-Thought Under Fixed Output Limits