Guanghao(Gary) Wei

MLE @ ByteDance | ex-RA @ Cornell Relax ML Lab

avatar.jpg

ByteDance Ltd.

San Jose, CA 95110

My research interests lie at the intersection of Machine Learning Systems, High Performance Computing, and AI for Science, where I leverage my mathematical and engineering talents to pioneer cutting-edge solutions. I was a Research Assistant at Cornell Relax ML Lab advised by Prof. Chris De Sa on efficient machine learning algorithms and systems. Grounded in mathematical principles, our work aims to expedite large-scale, high-performance machine learning systems that are efficient, parallel, and distributed in real-world settings. Parallel to this, I collaborate on AI-driven molecule generation with talented Ph.D. students.

My academic journey has led me to a Master of Engineering in Computer Science at Cornell University. Prior to this, I pursued dual B.S. degrees in Computer Science and Mathematics at the University of Massachusetts Amherst, complemented by a minor in Japanese. My specialization in Mathematics focused on Applied Math and Scientific Computing. Prior to my graduation, I engaged in research at the UMass BioNLP Lab under Prof. Hong Yu, concentrating on bio-medical and clinical NLP applications within Electronic Health Records.

Check out garywei.dev for my personal website!

news

Sep 26, 2024 I am excited to share that our paper, “Navigating Chemical Space with Latent Flows,” has been accepted by NeurIPS 2024. :partying_face:
Jun 16, 2024 I am thrilled to announce that our paper, “Navigating Chemical Space with Latent Flows,” received the Spotlight (Top 10%) at the ICML 2024 AI for Science workshop. :trophy:
Feb 29, 2024 I am happy to continue my position at the Relax Lab at Cornell University as a graduate researcher. :computer:
Dec 31, 2023 I am delighted to have graduated from Cornell University with a Master of Engineering in Computer Science. :mortar_board:

latest posts

selected publications

  1. Navigating Chemical Space with Latent Flows
    Guanghao Wei*Yining Huang*Chenru DuanYue Song, and Yuanqi Du
    In Advances in Neural Information Processing Systems, 2024
  2. wei2023grabsampler.jpg
    GraB-sampler: Optimal Permutation-based SGD Data Sampler for PyTorch
    Guanghao Wei
    2023