PPL
Zheng Lin
Papers (7)
Hera: Learning Long-Horizon Coordination for Device-Cloud Collaborative LLM AgentsAttention-Guided Reward for Reinforcement Learning-based Jailbreak against Large Reasoning ModelsRe-Triggering Safeguards within LLMs for Jailbreak DetectionGuaranteed Jailbreaking Defense via Disrupt-and-Rectify SmoothingFuture Validity is the Missing Statistic: From Impossibility to $Φ$-Estimation for Grammar-Faithful Speculative DecodingGradient Starvation in Binary-Reward GRPO: Why Group-Mean Centering Fails and Why the Simplest Fix WorksMiA-Signature: Approximating Global Activation for Long-Context Understanding