- ๐ Undergraduate student at Beijing University of Posts and Telecommunications (BUPT), School of Computer Science
- ๐ฌ Research interests: RLVR ยท RLHF ยท Optimization Algorithms
- ๐ฑ Currently exploring the intersection of reinforcement learning and large language model alignment
- ๐ Beijing, China
| Area | Description |
|---|---|
| RLVR | Reinforcement Learning from Verifiable Rewards โ scalable reward signals beyond human feedback |
| RLHF | Reinforcement Learning from Human Feedback โ aligning LLMs with human preferences |
| Optimizer | Adaptive optimization methods (AdamW, Muon, Shampoo, etc.) for deep learning |
APO_OFFICAL โ [ICML 2026] The official repository for Anchored Policy Optimization: Mitigating Exploration Collapse via Support-Constrained Rectification
SPPO โ [ACL 2026 Oral] SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks official repos.
No recent public activity.
2026-06-19็ฌฌๅ็ซ ๏ผๅ้ๅค็ๆบ2026-04-27Uncertain Estimate2026-04-27็ฌ่ฎฐ๏ผDPO ไธ GRPO ็ๅ ๅจๅๆๆงๅๆ2026-04-27็ฌฌๅไธ็ซ ๏ผๆไปถ็ณป็ปๅฎ็ฐ2026-04-27็ฌฌๅ ซ็ซ ๏ผๅ ๅญ็ฎก็
"The pursuit of intelligence โ from theory to practice." ยท Last updated: auto-refreshed every 3 hours