PPL
Jiawen Zhang
Papers (5)
DirectorBench: Diagnosing Long-Form Video Generation with Personalized Multi-Agent EvaluationREFLECTOR: Internalizing Step-wise Reflection against Indirect JailbreakEvaluating Cognitive Age Alignment in Interactive AI AgentsConfidence-Aware Alignment Makes Reasoning LLMs More ReliableMitigating Many-shot Jailbreak Attacks with One Single Demonstration