- Spectral-guided Physical Dynamics Distillation

Youjin Kim, Dagyeong Na, Jae Yong Lee+, Junseok Kwon+, The Fourteenth International Conference on Learning Representations (ICLR),  Rio de Janeiro, Brazil, 2026  [pdf] [code]

+ Corresponding authors 

ACK: 2021-0-01341, Artificial Intelligence Graduate School Program

- Towards Generalizable Time Series Forecasting via IB-Regularized Transformer-Diffusion

Dagyeong Na, Jinho Kang, and Junseok Kwon, IEEE International Conference on Data Mining (ICDM), Washington DC, USA, 2025 [pdf] [code]

ACK: 2021-0-01341, Artificial Intelligence Graduate School Program

- Deep Disentangled Metric Learning

Jinhee Park, Jisoo Park, Dagyeong Na, Junseok Kwon, Association for the Advancement of Artificial Intelligence (AAAI),  Philadelphia, Pennsylvania, USA, 2025 [pdf] [code]

- MRDiff: Time Series Anomaly Detection Using Multi-level Reconstruction Diffusion 

Dagyeong Na, and Junseok Kwon , IEEE International Conference on Data Mining (ICDM) Workshop on Data-Centric AI, Abu Dhabi, UAE, 2024  [pdf] [code]  

- Enhancing Global and Local Context Modeling in Time Series Through Multi-Step Transformer-Diffusion Interaction

Dagyeong Na, Jinho Kang, Byounswoo Kang, Junseok Kwon, IEEE Access (ACCESS),   vol. 13, page 142251-142261, 2025 [pdf]

ACK: RS-2021-II211341, Artificial Intelligence Graduate School Program, Chung-Ang University Graduate Research Scholarship