Xiaotian Liu

PhD Candidate, Dartmouth CS

prof_pic.jpg

Hi, I’m Xiaotian Liu, a third-year Ph.D. candidate at Dartmouth College, advised by Dr. Yaoqing Yang. My research interests include scientific machine learning, generative models, reinforcement learning for algorithm discovery, and optimization theory.

Before coming to Dartmouth, I received both my B.S. in Mathematics and Computer Science and my M.S. in Computer Science from Wake Forest University (Go Deacs!) where I was advised by Dr. Grey Ballard.

Outside of research, I enjoy snowboarding and am currently learning how to ski.

news

Apr 30, 2026 Two papers accepted at ICML 2026! IRNO received a Spotlight distinction.
Nov 21, 2025 Passed my Ph.D. qualification exam!
Sep 25, 2024 Paper accepted at NeurIPS 2024: Sharpness-Diversity Tradeoff: Improving Flat Ensembles with SharpBalance.
Jun 12, 2024 Paper accepted at Kobe Journal of Mathematics: Bounding Crossing Numbers in Hexagonal Mosaics.
Sep 15, 2023 Started my Ph.D. at Dartmouth College, advised by Dr. Yaoqing Yang.
May 15, 2023 Paper accepted at Numerical Linear Algebra with Applications: CP Decomposition for Tensors via Alternating Least Squares with QR Decomposition.
Aug 02, 2022 Paper accepted at IEEE TPAMI: Dual Contrastive Prediction for Incomplete Multi-View Representation Learning.

selected publications

  1. ICML
    irno.png
    Iterative Refinement Neural Operators are Learned Fixed-Point Solvers: A Principled Approach to Spectral Bias Mitigation
    Xiaotian Liu, Shuyuan Shang, Xiaopeng Wang, and 2 more authors
    In International Conference on Machine Learning, 2026
  2. ICML
    rl4nla.png
    RL4RLA: Teaching ML to Discover Randomized Linear Algebra Algorithms through Diverse Examples
    Jinglong Xiong*, Xiaotian Liu*, Ruoxin Wang, and 4 more authors
    In International Conference on Machine Learning, 2026
  3. NeurIPS
    sharpbalance.png
    Sharpness-Diversity Tradeoff: Improving Flat Ensembles with SharpBalance
    Haiquan Lu*, Xiaotian Liu*, Yefan Zhou*, and 6 more authors
    In Advances in Neural Information Processing Systems, 2024
  4. TPAMI
    DCP.png
    Dual Contrastive Prediction for Incomplete Multi-View Representation Learning
    Yijie Lin, Yuanbiao Gou, Xiaotian Liu, and 3 more authors
    IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022

academic service

Reviewer

  • Conference: ICLR (2025, 2026), ICML (2026), AISTATS (2025, 2026), ACL (2024)
  • Journal: IEEE TNNLS, IEEE TPAMI