CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning ModelsJanuary 1, 2025·Zhihang Lin,Mingbao LinYuan Xie,Rongrong Ji· 0 min read URL Cite DOITypeConference paperPublicationAdvances in Neural Information Processing Systems 38publicationsLast updated on January 1, 2025 AuthorsYuan XieChair ProfessorFang Professor of Engineering | Chair Professor | IEEE/ACM/AAAS Fellow ← 3D Guard-Layer: An Integrated Agentic AI Safety System for Edge Artificial Intelligence January 1, 2025Enhancing Large-Scale AI Training Efficiency: The C4 Solution for Real-Time Anomaly Detection and Communication Optimization January 1, 2025 →
