Buyun Liang

Buyun Liang

Computer and Information Science Ph.D. Student

University of Pennsylvania

Biography

I am a Computer and Information Science Ph.D. student at the University of Pennsylvania, advised by Prof. René Vidal. My research interests have spanned optimization for AI, trustworthy AI and AI for science. Before joining Penn, I obtained a M.S. degree in Computer Science at the University of Minnesota, Twin Cities, advised by Prof. Ju Sun, a M.S. degree in Materials Science at the University of Minnesota, Twin Cities, advised by Prof. J. Ilja Siepmann, and a B.S. degree in Physics at Nanjing University.

Download my Curriculum Vitae .

Interests
  • Trustworthy AI
  • Optimization for AI
  • AI for Science
Education

  • Ph.D. in Computer and Information Science, 2023 -

    University of Pennsylvania, Philadelphia, PA, USA 🇺🇸

  • M.S. in Computer Science, 2020 - 2023

    University of Minnesota, Minneapolis, MN, USA 🇺🇸

  • M.S. in Materials Science, 2018 - 2020

    University of Minnesota, Minneapolis, MN, USA 🇺🇸

  • B.S. in Physics, 2014 - 2018

    Nanjing University, Nanjing, Jiangsu, China 🇨🇳

Publications

.js-id-selected
Selected OPT for AI Trustworthy AI AI for Science All
Hengyue Liang, Buyun Liang, Le Peng, Ying Cui, Tim Mitchell, Ju Sun (2023). Optimization for Adversarial Robustness Evaluations and Implications from the Solution Patterns. Under review at International Journal of Computer Vision (IJCV).

Paper

Hengyue Liang, Buyun Liang, Le Peng, Ying Cui, Tim Mitchell, Ju Sun (2023). Implications of Solution Patterns on Adversarial Robustness. In Computer Vision and Pattern Recognition (CVPR) Workshop of Adversarial Machine Learning on Computer Vision (Art of Robustness).

Paper

Buyun Liang, Tim Mitchell, Ju Sun (2022). NCVX: A General-Purpose Optimization Solver for Constrained Machine and Deep Learning. In Neural Information Processing Systems (NeurIPS) Workshop on Optimization for Machine Learning (OPT 2022).

Paper Poster

Hengyue Liang, Buyun Liang, Ying Cui, Tim Mitchell, Ju Sun (2022). Optimization for Robustness Evaluation beyond ℓp Metrics. In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2023) & Neural Information Processing Systems (NeurIPS) Workshop on Optimization for Machine Learning (OPT 2022).

Paper Poster

Software

NCVX PyGRANSO
NCVX (NonConVeX) is a user-friendly and scalable python software package targeting general nonsmooth NCVX problems with nonsmooth constraints.
Code Website ICCOPT22 Slides SDM 2023 slides MMLS 2023 Poster 3M Poster (2023)
NCVX PyGRANSO

Powerlifting

.js-id-selected
Selected All
2023 USAPL Ivy League Cup
Body Weight: 74.15kg. Squat: 145kg; Bench Press: 107.5kg; Deadlift: 185kg. Total 437.5kg.
Video
2023 USAPL Ivy League Cup
2023 USA Powerlifting Central and Midwest Regional Championships
Body Weight: 80.25kg. Squat: 160kg; Bench Press: 112.5kg; Deadlift: 195kg. Total 467.5kg.
Video
2023 USA Powerlifting Central and Midwest Regional Championships
2022 USA Powerlifting Minnesota Junior, Open & Master State Championships
Body Weight: 76.35kg. Squat: 157.5kg; Bench Press: 105kg; Deadlift: 180kg. Total 442.5kg.
Video
2022 USA Powerlifting Minnesota Junior, Open & Master State Championships

Contact