Jingwen Liu
Photo of Jingwen Liu

Jingwen Liu

PhD Student in Computer Science
Columbia University

jingwenliu [at] cs.columbia.edu

Google Scholar CV
I am on the job market for 2026–27, looking for research scientist and research engineer positions.

Hi, I’m Jingwen, a PhD student in the Columbia Core AI Lab (CAIL) and Theory of Computation Group at Columbia University, where I am extremely fortunate to be advised by Daniel Hsu and Alex Andoni. I obtained my undergraduate degree at UC San Diego, where I majored in mathematics and computer science. During my time at UCSD, I’m extremely honored to work with glorious Sanjoy Dasgupta and Russell Impagliazzo, who sparked my interest in ML theory and TCS research. I was also very lucky to work with Xiaolong Wang, who introduced me to CS research.

Research My recent research focuses on improving large language models with underlying scientific principles and understanding, spanning model architecture, training/optimization, and RL self-improvement.

Experience

Publications

  1. NeurIPS2026
    Fixed Universal Transformers
    Jingwen Liu, Alexandr Andoni, Daniel Hsu
    Advances in Neural Information Processing Systems (NeurIPS), 2026
    arXiv
  2. ICML2026
    Less Data, Faster Training: repeating smaller datasets speeds up learning via sampling biases
    Jingwen Liu, Ezra Edelman, Surbhi Goel, Bingbin Liu
    International Conference on Machine Learning (ICML), 2026
    Contributed talk, Workshop on Scientific Methods for Understanding Deep Learning, ICLR 2026
    arXivPoster
  3. ALT2026
    Group-realizable multi-group learning by minimizing empirical risk
    (α-β order) Navid Ardeshir, Samuel Deng, Daniel Hsu, Jingwen Liu
    The 37th International Conference on Algorithmic Learning Theory (ALT), 2026
    arXiv
  4. NeurIPS2025
    Fast attention mechanisms: a tale of parallelism
    Jingwen Liu, Hantao Yu, Clayton Sanford, Alexandr Andoni, Daniel Hsu
    Advances in Neural Information Processing Systems (NeurIPS), 2025
    arXivPoster
  5. NeurIPS2024
    Group-wise oracle-efficient algorithms for online multi-group learning
    (random order) Samuel Deng, Daniel Hsu, Jingwen Liu
    Advances in Neural Information Processing Systems (NeurIPS), 2024
    arXivPoster
  6. CVPR2022
    VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolution
    Zeyuan Chen, Yinbo Chen, Jingwen Liu, Xingqian Xu, Vidit Goel, Zhangyang Wang, Humphrey Shi, Xiaolong Wang
    Conference on Computer Vision and Pattern Recognition (CVPR), 2022
    arXivWebsite

Teaching and Service

Teaching Assistant

  • Theoretical Foundations of LLMs, Daniel Hsu Columbia, Spring 2025
  • Machine Learning Theory, Daniel Hsu Columbia, Spring 2024
  • Machine Learning, Sanjoy Dasgupta UCSD, Winter 2023
  • Mathematics for Algorithms and Systems, Russell Impagliazzo UCSD, Fall 2022
  • Software Project for Computer Architecture, Hung-Wei Tseng UCSD, Summer 2022
  • Introduction to Programming, Gerald Soosairaj UCSD, Spring 2022

Grader

  • Abstract Algebra UCSD, Fall 2021
  • Differential Equations UCSD, Spring 2021
  • Mathematical Reasoning UCSD, Winter 2021

Reviewing

  • COLT 2025, 2026
  • ICML 2025
  • NeurIPS 2024, 2025

Service

Miscellaneous

I am deeply grateful to my advisors and many others in the community for their great mentorship, including Bingbin Liu, Surbhi Goel, Samuel Deng, Yuhao Li, Hantao Yu, Clayton Sanford, Navid Ardeshir, Samantha Chen, Geelon So, Ezra Edelman, Sihan Liu and this list goes on and on… I would like to pass on this culture, so feel free to reach out to me if you think I might be helpful!

I like playing ping pong, climbing, skiing and karaoke :)