Caijun Xu

Ph.D. Student · Fudan University & SII

prof_pic.jpg

Fudan University & SII

Alex Research

Advisor: Prof. Yixin Cao

xxcaijun@gmail.com

Hi, I’m Caijun Xu (徐才峻) — a Ph.D. student at Fudan University & SII, working with Prof. Yixin Cao in Alex Research.

My research centers on data synthesis and reasoning for large language models, including reinforcement learning for multi-step reasoning, trajectory generation, and verifier & feedback design. Before my Ph.D., I received a B.Eng. from Beihang University (BUAA), where I worked on graph neural networks and knowledge graphs for recommendation.

Feel free to reach out — I’m always happy to chat about reasoning, RL, and synthetic-data pipelines. You can also find me on Google Scholar and GitHub.

research interests

LLM Reasoning Reinforcement Learning Synthetic Data Verifier & Feedback Knowledge Graphs Recommender Systems

highlights

  • Paper SCALER: Synthetic Scalable Adaptive Learning Environment for Reasoning accepted to ACL 2026 Findings.
  • Paper KG-based recommendation paper accepted to CIKM 2024.
  • Medal ICPC Asia Regional (Xi'an & Jinan) and CCPC Silver (Harbin) medals.

news

May 04, 2026 📄🎉 SCALER: Synthetic Scalable Adaptive Learning Environment for Reasoning — accepted to ACL 2026 Findings.
Oct 20, 2024 📄🎉 Exploring High-Order User Preference with Knowledge Graph for Recommendation — accepted to CIKM 2024 (short paper).
Dec 03, 2023 🥉 Won ICPC Bronze Medal (Jinan).
Nov 05, 2023 🥈 Won CCPC Silver Medal (Harbin).
Oct 22, 2023 🥉 Won ICPC Bronze Medal (Xi’an).

selected publications

  1. ACL’26 Findings
    SCALER: Synthetic Scalable Adaptive Learning Environment for Reasoning
    Caijun Xu, Changyi Xiao, Zhongyuan Peng, and 2 more authors
    In Findings of the Association for Computational Linguistics: ACL 2026, 2026
  2. CIKM’24
    Exploring High-Order User Preference with Knowledge Graph for Recommendation
    Caijun Xu, Fuwei Zhang, Zhao Zhang, and 2 more authors
    In Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, 2024