Sijun Tan (谭嗣俊)

I am a third-year CS PhD student at UC Berkeley, advised by Raluca Ada Popa. I am affiliated to Berkeley’s Sky Computing Lab.

Previously, I graduated from University of Virginia with a Bachelor’s degree in Computer Science and Mathematics, where I was advised by David Wu and Yuan Tian. I also worked with Professors Haifeng Xu and Xiaohui Bei. I interned at Facebook AI Research (FAIR) and worked at Ant Group as a senior algorithm engineer.

My current research focuses on LLM post-training and Agentic AI. I am the project lead at Agentica, and we are on a mission to democratize reinforcement learning for training language models and agents.

We are looking for highly motivated students to work with! If you are interested in research opportunities, please send me an email.

news

Apr 10, 2025 We released DeepCoder, a 14B model reaching O3 mini level on coding and math.
Feb 11, 2025 We released DeepScaleR, a 1.5B model that surpasses o1-preview by scaling RL🔥. Check out our code.
Oct 16, 2024 We are excited to release JudgeBench: a challenging benchmark to evaluate LLM-based judges. Check out our leaderboard and code.

selected publications

  1. Notion
    DeepCoder: A Fully Open-Source 14B Coder at O3-mini Level
    Michael Luo*, Sijun Tan*, Roy Huang*, Ameen Patel, Alpay Ariyak, Qingyang Wu, Xiaoxiang Shi, Rachel Xin, Colin Cai, Maurice Weber, Ce Zhang, Li Erran Li, Raluca Ada Popa, and Ion Stoica
    2025
  2. Notion
    DeepScaleR: Surpassing O1-Preview with a 1.5B Model by Scaling RL
    Michael Luo*, Sijun Tan*, Justin Wong, Xiaoxiang Shi, William Y. Tang, Manan Roongta, Colin Cai, Jeffrey Luo, Tianjun Zhang*, Li Erran Li, Raluca Ada Popa, and Ion Stoica
    2025
  3. ICLR
    JudgeBench: A Benchmark for Evaluating LLM-based Judges
    Sijun Tan*, Siyuan Zhuang*, Kyle Montgomery*, Willian Y. Tang, Alejandro Cuadron, Chenguang Wang, Raluca Ada Popa, and Ion Stoica
    International Conference on Learning Representations (ICLR), 2025
  4. EMNLP
    LLoCO: Learning Long Contexts Offline
    Sijun Tan*, Xiuyu Li*, Shishir Patil, Ziyang Wu, Tianjun Zhang, Kurt Keutzer, Joseph E. Gonzalez, and Raluca Ada Popa
    Empirical Methods in Natural Language Processing (EMNLP), 2024
  5. OSDI
    Flock: A Framework for Deploying On-Demand Distributed Trust
    Darya Kaviani*, Sijun Tan*, Pravein Govindan Kannan, and Raluca Ada Popa
    Operating Systems Design and Implementation (OSDI), 2024
  6. IEEE S&P
    MPCAuth: Multi-factor Authentication for Distributed-trust Systems
    Sijun Tan, Weikeng Chen, Ryan Deng, and Raluca Ada Popa
    IEEE Symposium on Security and Privacy (Oakland), 2023
  7. IEEE S&P
    CryptGPU: Fast Privacy Preserving Machine Learning on the GPU
    Sijun Tan, Brian Knott, Yuan Tian, and David J Wu
    IEEE Symposium on Security and Privacy (Oakland), 2021