Published in ICML; FPI @ ICLR Workshop, 2025
Recommended citation: Yun, T.*, Om, K.*, Lee, J., Yun, S., & Park, J. (2025). "Posterior Inference with Diffusion Models for High-dimensional Black-box Optimization." ICML; FPI @ ICLR Workshop.
Download Paper
Published in NeurIPS SPIGM Workshop (Oral), 2025
Recommended citation: Om, K.*, Sim, K.*, Yun, T.*, Kang, H., & Park, J. (2025). "Posterior Inference in Latent Space for Scalable Constrained Black-box Optimization." NeurIPS Workshop on Structured Probabilistic Inference & Generative Modeling (Oral).
Download Paper
Published in ICLR (Poster), 2026
Recommended citation: Lee, J., Kim, M., Choi, S., Song, I., Yun, S., Kang, H., Shin, W., Yun, T., Om, K., & Park, J. (2026). "Diffusion Alignment as Variational Expectation-Maximization." ICLR.
Download Paper
Published in ICLR (Poster), 2026
Recommended citation: Kang, H.*, Lee, J.*, Shin, W.*, Om, K., & Park, J. (2026). "Diffusion Fine-Tuning via Reparameterized Policy Gradient of the Soft Q-Function." ICLR.
Download Paper
Published:
In this seminar hosted by KAIST’s System Intelligence Lab (SILAB), the talk focused on interpreting control problems through the lens of probabilistic inference.
Published:
In this seminar hosted by KAIST’s System Intelligence Lab (SILAB), the talk focused on generative model based optimization on Riemannian Manifold.
Summer Lecture, Korea University, 2023
I served as a Teaching Assistant for the Deep Learning Programming Study under the guidance of Professor Sungbin Lim. In this role, I helped students master the fundamentals of building deep learning pipelines using advanced Python tools.
Undergraduate course, KAIST, Industrial & Systems Engineering, 2024
As a Teaching Assistant for the Statistical Machine Learning course (IE343) at KAIST, I support undergraduate students in developing a strong foundation in machine learning concepts and techniques.