PPL
Cuiyun Gao
Papers (4)
Enhancing the Code Reasoning Capabilities of LLMs via Consistency-based Reinforcement LearningASRU: Activation Steering Meets Reinforcement Unlearning for Multimodal Large Language ModelsPPU-Bench:Real World Benchmark for Personalized Partial Unlearning in Vision Language ModelsSchedule-and-Calibrate: Utility-Guided Multi-Task Reinforcement Learning for Code LLMs