Zhikun Xu

@JerrryKun

research intern @AMD, pursuing CS PhD @SCAI_ASU | Prev: Applied Math (B.S. & M.S.) @FudanUni, Research Internship @awscloud @AlibabaGroup

Joined November 2018

99Following

45Followers

Zhikun Xu Retweeted

jakedineenasu@jakedineenasu · Jun 11

🔍 Introducing QA-LIGN: A reflective alignment approach using a draft→reflection→revision pipeline. We create symbolic reward models that serve as both natural language critics & general reward models, bridging rule-based rewards and RLAIF. 📄 Paper: arxiv.org/pdf/2506.08123

1.0K

Zhikun Xu@JerrryKun · Feb 27

Really interesting work! For better demonstrations, the models should give correct and vivid examples or counterexamples!👀 This also resonates with our CounterMATH paper!

WWenhu Chen@WenhuChen · Feb 27

Thanks for sharing our work! Building AI for education has always been my dream. In this paper, we investigate whether it's possible to synthesize minute-long videos to help students learn about different STEM theorems. Awesome work by my student Max Ku.

653