Demystifying Group Relative Policy Optimization: Its Policy Gradient is a U-Statistic
Paper
• 2603.01162 • Published
Stats-powered AI
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Learn-to-Distance: Distance Learning for Detecting LLM-Generated Text
AdaDetectGPT: Adaptive Detection of LLM-Generated Text with Statistical Guarantees
KyleyeeÂ
authored a paper 11 days ago
mamba413Â
updated a Space 22 days ago
KyleyeeÂ
authored a paper about 1 month ago
mamba413Â
authored a paper 3 months ago
KyleyeeÂ
authored 3 papers 3 months ago
Doubly Robust Alignment for Large Language Models
Paper
• 2506.01183 • Published
• 3
AdaDetectGPT: Adaptive Detection of LLM-Generated Text with Statistical Guarantees
Paper
• 2510.01268 • Published
• 3
Robust Reinforcement Learning from Human Feedback for Large Language Models Fine-Tuning
Paper
• 2504.03784 • Published
• 3