The Stochastic Dynamics and Machine Learning (SDML) Lab at Korea University studies the dynamics inherent in both data and models.

On the data side, we develop probabilistic machine learning tools such as Gaussian processes and neural differential equations. On the model side, we study the connection between deep networks and neural differential equations, and the training dynamics of deep learning, in order to understand their theoretical properties. Applications include time series analysis, interpretability of sequential data, and financial modeling (pricing, hedging, and risk management).

Research topics

• Gaussian processes and Bayesian nonparametrics
• Neural ordinary and stochastic differential equations
• Training dynamics and theory of deep learning
• Time series, interpretability, and machine learning for finance

Recent publications

1. NeurIPS

   Refining Compositional Diffusion for Reliable Long-Horizon Planning

   Kyowoon Lee, Yunhao Luo, Anh Tong, and Jaesik Choi

   Advances in Neural Information Processing Systems (NeurIPS), 2026

   arXiv

   BibTeX

   @inproceedings{lee2026refining,
     title = {Refining Compositional Diffusion for Reliable Long-Horizon Planning},
     author = {Lee, Kyowoon and Luo, Yunhao and Tong, Anh and Choi, Jaesik},
     booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
     year = {2026}
   }
   

2. NeurIPS

   PRISM: Principal Subspace Alignment for Parameter-Efficient Fine-Tuning

   Anh Tong, Kyowoon Lee, and Jaesik Choi

   Advances in Neural Information Processing Systems (NeurIPS), 2026

   BibTeX

   @inproceedings{tong2026prism,
     title = {{PRISM}: Principal Subspace Alignment for Parameter-Efficient Fine-Tuning},
     author = {Tong, Anh and Lee, Kyowoon and Choi, Jaesik},
     booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
     year = {2026}
   }
   

3. NeurIPS

   SaMA: Morpho Adaptation via Asymmetric Expansion of Kronecker Product

   An V. Nguyen and Anh Tong

   Advances in Neural Information Processing Systems (NeurIPS), 2026

   BibTeX

   @inproceedings{nguyen2026sama,
     title = {{SaMA}: Morpho Adaptation via Asymmetric Expansion of {Kronecker} Product},
     author = {Nguyen, An V. and Tong, Anh},
     booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
     year = {2026}
   }
   

4. IJCAI

   LoCO: Low-rank Compositional Rotation Fine-tuning

   An Nguyen, Jaesik Choi, and Anh Tong

   International Joint Conference on Artificial Intelligence (IJCAI), 2026

   arXiv

   BibTeX

   @inproceedings{nguyen2026loco,
     title = {{LoCO}: Low-rank Compositional Rotation Fine-tuning},
     author = {Nguyen, An and Choi, Jaesik and Tong, Anh},
     booktitle = {International Joint Conference on Artificial Intelligence (IJCAI)},
     year = {2026}
   }
   

5. CSUR

   Towards Transparent Time Series Analysis: Exploring Methods and Enhancing Interpretability

   Youngjin Park, Anh Tong, Sehyun Lee, Jihyeon Seong, Qin Xie, and Jaesik Choi

   ACM Computing Surveys, 2026

   DOI

   BibTeX

   @article{park2026transparent,
     title = {Towards Transparent Time Series Analysis: Exploring Methods and Enhancing Interpretability},
     author = {Park, Youngjin and Tong, Anh and Lee, Sehyun and Seong, Jihyeon and Xie, Qin and Choi, Jaesik},
     journal = {ACM Computing Surveys},
     year = {2026},
     doi = {10.1145/3794839}
   }
   

All publications →