Yi-lun Liao
PhD Candidate
Cambridge, Massachusetts, United States
Summary
🤩
Rockstar🎓
Top SchoolYi-lun Liao is an MIT EECS PhD candidate and researcher with eight years of experience at the intersection of machine learning and computational chemistry. He interned as a Research Scientist at Meta with the Open Catalyst Team, contributing to EquiformerV2 (ICLR 2024) and DeNS (TMLR 2024), work showcased in the OC demo. His background in electrical and electronics engineering from National Taiwan University underpins a strong foundation in signal processing and systems thinking applied to ML model design. Yi-lun combines deep academic rigor with practical collaboration on large-scale research projects, bridging theory and demo-ready systems. He is based in Cambridge, Massachusetts, and brings a track record of publishing and implementing state-of-the-art models for chemistry and materials problems. Notably, his internship contributions have been part of public-facing demonstrations that translate complex research into usable tools.
9 years of coding experience
PhD student in EECS, PhD student in EECS at Massachusetts Institute of TechnologyBachelor of Science - BS, Electrical and Electronics Engineering, Bachelor of Science - BS, Electrical and Electronics Engineering at National Taiwan University
English, Chinese
Github Skills (24)
convex-hull10
machine-learning9
computational-chemistry9
drug-discovery9
evaluation-framework8
denoising8
computational-physics8
pytorch8
geometric-deep-learning8
machine-learning-models7
self-supervised-learning7
deep-learning7
message-passing7
3d5
mobile-application5
Programming languages (1)
Github contributions (5)
atomicarchitects/equiformer_v2
Jun 2023 - Dec 2025
[ICLR 2024] EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations
Contributions:15 pushes, 1 branch, 39 comments in 2 years 6 months
catalyst-designcomputational-chemistrycomputational-physicsdeep-learningdrug-discovery
atomicarchitects/DeNS
Jul 2024 - Dec 2025
[TMLR 2024 J2C Certification] Generalizing Denoising to Non-Equilibrium Structures Improves Equivariant Force Fields
Contributions:3 pushes, 1 branch, 6 comments in 1 year 4 months
denoisingcomputational-chemistrydrug-discoveryforce-fieldsgeometric-deep-learning
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.