Publications

* denotes equal contribution

2026

  1. arXiv
    EdgeBench: Unveiling Scaling Laws of Learning from Real-World Environments
    Deyao Zhu, Xin Zhou, Shengling Qin, Xuekai Zhu, Hangliang Ding, Shu Zhong , Zixin Wen, Zhonglin Xie, Chenhui Gou, Linxuan Ren, and 37 more authors
    arXiv preprint, arXiv: 2607.05155, 2026
    arXiv
  2. TMLR
    DRAW: Domain Weight Randomization with Bayesian Updating for LLM Pre-Training
    Ruonan Wang, Yongqi Qiao, Zhonglin Xie, and Kun Yuan
    Transactions on Machine Learning Research (TMLR), 2026
    HTML

2025

  1. NeurIPS
    Accelerating Optimization via Differentiable Stopping Time
    Zhonglin Xie, Yiman Fong , Haoran Yuan, and Zaiwen Wen
    Advances in Neural Information Processing Systems 38 (NeurIPS 2025), Spotlight, 2025
    arXiv HTML
  2. arXiv
    Accelerated Natural Gradient Method for Parametric Manifold Optimization
    Chenyi Li*, Shuchen Zhu*, Zhonglin Xie, and Zaiwen Wen
    arXiv preprint, arXiv: 2504.05753, 2025
    arXiv
  3. ICML
    OptMATH: A Scalable Bidirectional Data Synthesis Framework for Optimization Modeling
    Hongliang Lu*, Zhonglin Xie*, Yaoyu Wu, Can Ren, Yuxuan Chen, and Zaiwen Wen
    Forty-Second International Conference on Machine Learning (ICML), 2025
    arXiv HTML Code Poster Slides Dataset
  4. Math. Prog.
    ODE-based Learning to Optimize
    Zhonglin Xie, Wotao Yin, and Zaiwen Wen
    Mathematical Programming, 2025
    DOI arXiv HTML Video Code Poster Slides

2023

  1. DAC
    LRSDP: Low-Rank SDP for Triple Patterning Lithography Layout Decomposition
    Yu Zhang*, Yifan Chen*, Zhonglin Xie, Hong Xu, Zaiwen Wen, Yibo Lin, and Bei Yu
    In 60th ACM/IEEE Design Automation Conference, DAC 2023, San Francisco, CA, USA, July 9-13, 2023, 2023
    DOI HTML

2021

  1. JCIN
    Joint Bandwidth Allocation and Path Selection in WANs with Path Cardinality Constraints
    Jinxin Wang, Fan Zhang, Zhonglin Xie, Zaiwen Wen, and Gong Zhang
    J. Commun. Inf. Networks, 2021
    DOI HTML