PPL
Li Song
Papers (4)
GAC: Noise-Aware Adaptive Mixing for Hybrid SFT-RL Post-TrainingDomain-Adaptive Communication-Rate Optimization for Sim-to-Real Humanoid-Robot Wireless XR TeleoperationAuditRepairBench: A Paired-Execution Trace Corpus for Evaluator-Channel Ranking Instability in Agent RepairMaximizing Rollout Informativeness under a Fixed Budget: A Submodular View of Tree Search for Tool-Use Agentic Reinforcement Learning