Ph.D. Student

Computer Science Department

University of Virginia

Email: {first_name}{last_name}@virginia.edu

X(Twitter) | Linkedin | CV

Github | Google Scholar

Hi!👋 I’m Xinyu (/ʃɪn.ju:/) Zhu, currently a 3rd-year Ph.D. student at the University of Virginia, advised by Prof. ****Yu Meng. I have been working on LLMs post-training. I received my master degree at Tsinghua University, advised by Prof. ****Yujiu Yang.

✨News

• [09/2026] One paper on efficient RLVR with minimal training is accepted at NeurIPS 2026! 🎉
• [08/2026] Grateful to receive the Tinker Research Grant from Thinking Machines ($5,000 credits)!
• 🚀🚀🚀 [07/2026] Check out our new work Self-Guided Test-Time Training for Long-Context LLMs! 🤩
• [05/2026] I moved to Bellevue and started my internship at Meta Superintelligence Labs, looking forward to meeting new friends around Bellevue/Seattle/Redmond! 😄
• [04/2026] One paper on synthetic data for LLM alignment ****is accepted at ACL 2026! 🎉
• 🔥🔥🔥 [03/2026] Check out our new paper CHIMERA! We release a compact synthetic reasoning dataset of 9K expert-level problems across 8 disciplines, enabling a 4B model to match significantly larger reasoning models!
• [03/2026] Grateful to receive the Lambda's Research Grant ($5,000 credits)!
• [09/2025] Two works on how negative-reward-only RL can improve LLM reasoning and transferring small RL-tuned models’ reasoning capability to large base model are accepted to NeurIPS 2025! ****🎉 See you in San Diego! 🤩
• [06/2025] Check out our new preprint and X thread on how negative-reward-only RL can improve LLM reasoning! 🚀
• Old news

👨‍🎓Education

• University of Virginia 2024—Now Ph.D. in Computer Science
• Tsinghua University 2021—2024 Master in Electronic and Information Engineering
• Xidian University 2017—2021 Bachelor in Electronic Science and Technology

📝Selected Works (* indicates equal contribution)