| 2025 | CAV | Floating-Point Neural Networks are Provably Robust Universal Approximators. | Geonho Hwang, Wonyeol Lee, Yeachan Park, Sejun Park, Feras Saad |
| 2025 | ICML | Floating-Point Neural Networks Can Represent Almost All Floating-Point Functions. | Geonho Hwang, Yeachan Park, Wonyeol Lee, Sejun Park |
| 2024 | ICLR | What does automatic differentiation compute for neural networks? | Sejun Park, Sanghyuk Chun, Wonyeol Lee |
| 2023 | ICML | On the Correctness of Automatic Differentiation for Neural Networks with Machine-Representable Parameters. | Wonyeol Lee, Sejun Park, Alex Aiken |
| 2020 | AAAI | Differentiable Algorithm for Marginalising Changepoints. | Hyoungjin Lim, Gwonsoo Che, Wonyeol Lee, Hongseok Yang |
| 2016 | PLDI | Verifying bit-manipulations of floating-point. | Wonyeol Lee, Rahul Sharma, Alex Aiken |
| 2014 | POPL | A proof system for separation logic with magic wand. | Wonyeol Lee, Sungwoo Park |
| 2012 | ICDM | CT-IC: Continuously Activated and Time-Restricted Independent Cascade Model for Viral Marketing. | Wonyeol Lee, Jinha Kim, Hwanjo Yu |
| 2009 | ICIP | Edge detection using morphological amoebas in noisy images. | Wonyeol Lee, Se Yun Kim, Young Woo Kim, Jae Young Lim, Dong Hoon Lim |