Google Scholar · LinkedIn · Email

My research lies at the intersection of machine learning and computational science. I develop reinforcement learning and bandit algorithms and apply them to automated analog circuit optimization and verification, using model-based reinforcement learning, Bayesian optimization, and surrogate modeling.

:research: Publications

1. Oh, Y., Won, J., Park, Y., Hwang, B., and Kim, S. ATLAS: Adaptive TDA-guided Landscape-Aware Transistor Sizing. IEEE/ACM International Conference on Computer-Aided Design (ICCAD) (2026). Accepted; to appear.
2. Oh, Y. Robust Linear Dueling Bandits with Post-serving Context under Unknown Delays and Adversarial Corruptions. Proceedings of the 43rd International Conference on Machine Learning (ICML), PMLR 306:94256–94289 (2026).
3. Oh, Y., Park, J., and Paik, T. Neural Variance-aware Dueling Bandits with Deep Representation and Shallow Exploration. Proceedings of the 29th International Conference on Artificial Intelligence and Statistics (AISTATS), PMLR 300:550–558 (2026).
4. Oh, Y., Park, J., Paik, T., Kim, S., Kim, S., Lee, Y. H., and Pan, D. Z. M3: Mamba-assisted Multi-Circuit Optimization via Model-based RL with Effective Scheduling. IEEE/ACM International Conference on Computer-Aided Design (ICCAD), pp. 1–8 (2025).
5. Kim, S., Wang, Z., Lee, S., Oh, Y., Zhu, H., Kim, D., and Pan, D. Z. PPAAS: PVT and Pareto Aware Analog Sizing via Goal-Conditioned Reinforcement Learning. IEEE/ACM International Conference on Computer-Aided Design (ICCAD), pp. 1–9 (2025).
6. Poddar, S., Oh, Y., Lai, Y., Zhu, H., Hwang, B., and Pan, D. Z. INSIGHT: A Universal Neural Simulator Framework for Analog Circuits with Autoregressive Transformers. 62nd ACM/IEEE Design Automation Conference (DAC), pp. 1–7 (2025).
7. Ahn, H., Hyeon, J., Oh, Y., Hwang, B., and Moon, T. Prevalence of Negative Transfer in Continual Reinforcement Learning: Analyses and a Simple Baseline. International Conference on Learning Representations (ICLR) (2025).
8. Kim, D., Park, J., Oh, Y., and Hwang, B. TraceFormer: S-parameter Prediction Framework for PCB Traces based on Graph Transformer. 61st ACM/IEEE Design Automation Conference (DAC), pp. 1–6 (2024).
9. Oh, Y., Kim, D., Lee, Y. H., and Hwang, B. CRONuS: Circuit Rapid Optimization with Neural Simulator. Design, Automation & Test in Europe (DATE), pp. 1–6 (2024).
10. Lee, Y. H., Oh, Y., Jeong, G., et al. GRAFT: Graph-assisted Reinforcement Learning for Automated SSD Firmware Testing. IEEE/ACM International Conference on Computer-Aided Design (ICCAD), pp. 1–8 (2023).
11. Oh, Y., et al. Model-augmented Prioritized Experience Replay. International Conference on Learning Representations (ICLR) (2022).
12. Oh, Y., et al. Learning to Sample with Local and Global Contexts in Experience Replay Buffer. International Conference on Learning Representations (ICLR) (2021).
13. Oh, Y., Yun, G. S., and Hwang, H. J. Mathematical analysis of long-time behavior of magnetized fluid instabilities with shear flow. arXiv preprint arXiv:1706.08036 (2017).
14. Oh, Y., et al. Effect of time-varying flow-shear on the nonlinear stability of the boundary of magnetized toroidal plasmas. AIP Advances 8(2):025224 (2018).
15. Oh, Y., et al. Variational approach to powder-binder separation in Poiseuille and Couette flows. Physics of Fluids 29(3):033102 (2017).