Wonyeol Lee

Assistant Professor
Computer Science & Engineering, POSTECH
wonyeol.lee.cs@gmail.com  |  CV

I am an Assistant Professor at POSTECH, where I lead the Foundations of Programming & Computing (FPC) Lab. Before joining POSTECH, I was a Postdoctoral Associate at Carnegie Mellon University, working with Feras Saad. I received my PhD degree in Computer Science from Stanford University, advised by Alex Aiken. During my PhD, I also spent time at KAIST for military service, working with Hongseok Yang. Prior to that, I obtained my BS degree in Computer Science and Mathematics from POSTECH.

I am recruiting motivated & talented students, including undergraduates. If you are interested in programs or computations and enjoy asking fundamental or mathematical questions, please email me.

Research

My research aims to make continuous computations more reliable and scalable. To this end, I work across several areas, such as programming languages (PL) and machine learning (ML), and study diverse continuous computations with a focus on their mathematical properties, such as correctness and efficiency.

Broadly, my interests fall into three directions:

• Analyze existing continuous computations from a theoretical perspective.

• Design new continuous computations with theoretical guarantees.

• Understand the fundamental limits of continuous computations.

Specifically, I explore topics such as:

• Continuous Computations

  • Continuous Computing [floating point | math library | neural network]

  • Differentiable Computing [non-differentiability | automatic differentiation | gradient estimation]

  • Probabilistic Computing [random variate generation | probabilistic inference]

• Mathematical Properties

  • Correctness [program analysis | real analysis]

  • Efficiency

  • Fundamental Limits [universal approximation]

Publications

1. Floating-Point Neural Networks Are Provably Robust Universal Approximators Geonho Hwang*, Wonyeol Lee*, Yeachan Park, Sejun Park, Feras Saad CAV 2025 (International Conference on Computer Aided Verification) [paper | code]

2. Floating-Point Neural Networks Can Represent Almost All Floating-Point Functions Geonho Hwang, Yeachan Park, Wonyeol Lee, Sejun Park ICML 2025 (International Conference on Machine Learning) [paper]

3. Random Variate Generation with Formal Guarantees Feras Saad, Wonyeol Lee PLDI 2025 (ACM Conference on Programming Language Design and Implementation) [paper | code]

4. Semantics of Integrating and Differentiating Singularities Jesse Michel, Wonyeol Lee^†, Hongseok Yang PLDI 2025 (ACM Conference on Programming Language Design and Implementation) [paper | code]

5. What Does Automatic Differentiation Compute for Neural Networks? Sejun Park, Sanghyuk Chun, Wonyeol Lee ICLR 2024 (Spotlight) (International Conference on Learning Representations) [paper | code]

6. Expressive Power of ReLU and Step Networks under Floating-Point Operations Yeachan Park, Geonho Hwang, Wonyeol Lee, Sejun Park Neural Networks, 2024 [paper]

7. Reasoning About Floating Point in Real-World Systems Wonyeol Lee PhD Dissertation, 2023 [paper | slides]

8. On the Correctness of Automatic Differentiation for Neural Networks with Machine-Representable Parameters Wonyeol Lee, Sejun Park, Alex Aiken ICML 2023 (International Conference on Machine Learning) [paper | slides]

9. Training with Mixed-Precision Floating-Point Assignments Wonyeol Lee, Rahul Sharma, Alex Aiken TMLR, 2023 (Transactions on Machine Learning Research) [paper | code]

10. Smoothness Analysis for Probabilistic Programs with Application to Optimised Variational Inference Wonyeol Lee, Xavier Rival, Hongseok Yang POPL 2023 (ACM Conference on Principles of Programming Languages) [paper | slides | video | code]

11. On Correctness of Automatic Differentiation for Non-Differentiable Functions Wonyeol Lee, Hangyeol Yu, Xavier Rival, Hongseok Yang NeurIPS 2020 (Spotlight) (Annual Conference on Neural Information Processing Systems) [paper | slides | video]

12. Differentiable Algorithm for Marginalising Changepoints Hyoungjin Lim, Gwonsoo Che, Wonyeol Lee, Hongseok Yang AAAI 2020 (AAAI Conference on Artificial Intelligence) [paper]

13. Towards Verified Stochastic Variational Inference for Probabilistic Programs Wonyeol Lee, Hangyeol Yu, Xavier Rival, Hongseok Yang POPL 2020 (ACM Conference on Principles of Programming Languages) [paper | slides | video | code]

14. Reparameterization Gradient for Non-Differentiable Models Wonyeol Lee, Hangyeol Yu, Hongseok Yang NeurIPS 2018 (Annual Conference on Neural Information Processing Systems) [paper | slides | code]

15. On Automatically Proving the Correctness of math.h Implementations Wonyeol Lee, Rahul Sharma, Alex Aiken POPL 2018 (ACM Conference on Principles of Programming Languages) [paper | slides (short) | video]

16. Verifying Bit-Manipulations of Floating-Point Wonyeol Lee, Rahul Sharma, Alex Aiken PLDI 2016 (ACM Conference on Programming Language Design and Implementation) [paper | slides | video]

17. A Proof System for Separation Logic with Magic Wand Wonyeol Lee, Sungwoo Park POPL 2014 (ACM Conference on Principles of Programming Languages) [paper]

18. CT-IC: Continuously Activated and Time-Restricted Independent Cascade Model for Viral Marketing Wonyeol Lee, Jinha Kim, Hwanjo Yu ICDM 2012 (IEEE International Conference on Data Mining) [paper | journal | slides]

19. Edge Detection Using Morphological Amoebas in Noisy Images Wonyeol Lee, Seyun Kim, Youngwoo Kim, Jaeyoung Lim, Dong Hoon Lim ICIP 2009 (IEEE International Conference on Image Processing) [paper | journal]

trips | last updated: 05/2025