Hi, I'm Kevin Li
I am a fourth year Ph.D. student at CMU's Machine Learning Department, where I am fortunate enough to be co-advised by both Prof. Albert Gu and Prof. Zico Kolter and supported by the NSF Graduate Research Fellowship. Previously, I was a Computer Science and Biomedical Engineering undergrad at Georgia Tech, where I had a wonderful time advised by Prof. Polo Chau.
I am interested in developing better deep learning architectures and pretraining methods. Please reach out if you are interested in collaborating!
This summer, I was a Student Researcher at Google DeepMind. Previously, I was a Student Researcher at Google Research and a ML Research Intern at Bosch.
Featured Research Publications
Scaling laws for VLM inference for balancing image token count and LLM size.
ICLR
2025
Cross-architectural distillation from Transformers to Mamba models with just a fraction of the pretraining data.
NeurIPS
2024
Flexible sequence modeling with shared attention-recurrent representations.
arXiv
2026
NeurIPS 2026 ODI Workshop, Oral
Honors and Awards
Spring 2025
NSF Graduate Research Fellowship Program (GRFP) Awardee
Fall 2023
Best Poster Award, BMVC
For "Robust Principles: Architectural Design Principles for Adversarially Robust CNNs"
Spring 2023
Georgia Tech Provost’s Academic Excellence Award
Selected to represent the College of Computing for most outstanding scholastic record
Spring 2023
G.D. Jain Outstanding Senior in Biomedical Engineering Award
Selected for exemplifying all-around excellence through their significant accomplishments in several of the following categories of activities: service, academics, research, industry, and entrepreneurship
Fall 2022
CIKM 2022 NSF Travel Award
Fall 2022
President's Undergraduate Research Award (PURA)
Summer 2022
First Place, Qualcomm Intern Hackathon
Spring 2022
Undergraduate Teaching Assistant of the Year, Georgia Institute of Technology
Selected as one of three undergraduate teaching assistants to be awarded the institute-wide award for TAing CS4641/7641 Machine Learning
Spring 2022
Undergraduate Teaching Assistant of the Year, College of Computing
Selected as UTA of the year for the CSE school under the College of Computing for TAing CS4641/7641 Machine Learning
Fall 2021
Best Poster Honorable Mention, IEEE VIS
For "Argo Scholar: Interactive Visual Exploration of Literature in Browsers"
Research Experience
Oct. 2023 - Current
Carnegie Mellon University, Pittsburgh, PA
Advisor:
Albert Gu and Zico Kolter
Aug. 2020 - May 2023
Georgia Institute of Technology, Atlanta, GA
Undergraduate Research Assistant, Polo Club of Data Science
Advisor:
Duen Horng (Polo) Chau
Conducted research in machine learning, human-computer interaction, and the intersection of the two.