Scholar
Wonyeol Lee
Google Scholar ID: g3TYhjcAAAAJ
Assistant Professor, POSTECH
Citations & Impact
Citations
308
H-index
8
i10-index
8
Publications
20
Co-authors
16
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Publications:
- - Optimising Density Computations in Probabilistic Programs via Automatic Loop Vectorisation, POPL 2026
- - Floating-Point Neural Networks Are Provably Robust Universal Approximators, CAV 2025
- - Floating-Point Neural Networks Can Represent Almost All Floating-Point Functions, ICML 2025
- - Random Variate Generation with Formal Guarantees, PLDI 2025
- - Semantics of Integrating and Differentiating Singularities, PLDI 2025
- - What Does Automatic Differentiation Compute for Neural Networks?, ICLR 2024 (Spotlight)
- - Expressive Power of ReLU and Step Networks under Floating-Point Operations, Neural Networks, 2024
- - Reasoning About Floating Point in Real-World Systems, PhD Dissertation, 2023
- - On the Correctness of Automatic Differentiation for Neural Networks with Machine-Representable Parameters, ICML 2023
- - Training with Mixed-Precision Floating-Point Assignments, TMLR, 2023
- - Smoothness Analysis for Probabilistic Programs with Application to Optimised Variational Inference, POPL 2023
- - On Correctness of Automatic Differentiation for Non-Differentiable Functions, NeurIPS 2020 (Spotlight)
Research Experience
- 2024-Present: Assistant Professor, POSTECH; 2023-2024: Postdoctoral Associate, Carnegie Mellon University (Host: Feras Saad); 2017-2020: Researcher, KAIST (Host: Hongseok Yang); 2017: Research Intern, Microsoft Research India; 2016: Research Intern, Microsoft Research Redmond
Education
- 2014-2023: PhD in Computer Science, Stanford University (Advisor: Alex Aiken); 2010-2014: BS in Computer Science and Mathematics, POSTECH
Background
- Research Interests: Programming Languages, Mathematics, Programs/Computations. Overview: Currently an Assistant Professor at POSTECH, aiming to make foundational software more reliable and scalable.
Miscellany
- Personal Interests: Actively recruiting motivated students with a background in programming languages/mathematics and an interest in programs/computations.
