publications

2026

  1. NeurIPS
    Is √d Separation Necessary for Gradient EM to Learn Gaussian Mixtures in High Dimensions?
    Yiran Zhang, Mo Zhou, Weihang Xu, Maryam Fazel, and Simon S. Du
    In NeurIPS, 2026
    arXiv
  2. NeurIPS
    Frontier Language Models Struggle to Copy: Text Can Be Better Viewed in 2D
    Haodong Wen*, Yiran Zhang*, Yingfa Chen*, and Kaifeng Lyu
    In NeurIPS, 2026
    * Equal contribution.
    arXiv
  3. FOCS
    A Polynomial-Time Algorithm for the Next-to-Shortest Path Problem on Positively Weighted Directed Graphs
    Kuowen Chen, Nicole Wein, and Yiran Zhang
    In FOCS, 2026
    arXiv
  4. ICLR
    Convergence Dynamics of Over-Parameterized Score Matching for a Single Gaussian
    Yiran Zhang, Weihang Xu, Mo Zhou, Maryam Fazel, and Simon Shaolei Du
    In ICLR, 2026
    arXiv

2025

  1. FOCS
    Adaptivity Gaps for Stochastic Probing with Subadditive Functions
    Jian Li, Yinchen Liu, and Yiran Zhang
    In FOCS, 2025
    arXiv
  2. ICALP
    New Results on a General Class of Minimum Norm Optimization Problems
    Kuowen Chen, Jian Li, Yuval Rabani, and Yiran Zhang
    In ICALP, 2025
    arXiv