I am a Ph.D. candidate in the School of Computer Science and Engineering at Chung-Ang University (CAU), advised by Prof. Junseok Kwon. I received M.S. in Computer Science and Engineering and B.S. in Electrical and Electronics Engineering at CAU. I am currently interning with LG AI Research as a research intern.


My research goal is to build probabilistic models upon mathematical disciplines (e.g., optimal transport, Riemannian geometry, differential game, stochastic geometry) and solve challenging real-world tasks. Specifically, my interests include generative modeling, time-series prediction, and uncertainty calibration.

Publications

  • Sung Woo Park, Hyomin Kim, Hyeseong Kim, and Junseok Kwon, Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS, ICLRW), 2022, Riemannian Neural SDE: Learning Stochastic Representations on Manifolds


  • Sung Woo Park, and Junseok Kwon, Expert System with Applications (ESWA), 2022, Riemannian Submanifold Framework for Log-Euclidean Metric Learning on Symmetric Positive Definite Manifolds


  • Sung Woo Park, Kyungjae Lee, and Junseok Kwon, Proc. of International Conference on Learning Representations (ICLR), 2022, Neural Markov Controlled SDE: Stochastic Optimization for Continuous-Time Data


  • Sung Woo Park, and Junseok Kwon, IEEE Transaction on Pattern Analysis and Machine Intelligence (TPAMI) 2022, SphereGAN: Sphere Generative Adversarial Network Based on Geometric Moment Matching and Its Applications


  • Sung Woo Park, and Junseok Kwon, The 38th International Conference on Machine Learning (ICML), 2021, Wasserstein Distributional Normalization For Robust Distributional Certification of Noisy Labeled Data


  • Sung Woo Park, Dong Wook Shu, and Junseok Kwon, The 38th International Conference on Machine Learning (ICML), 2021, Generative Adversarial Networks for Markovian Temporal Dynamics: Stochastic Continuous Data Generation


  • Guisik Kim, Sung Woo Park, and Junseok Kwon, IEEE Transaction on Image Processing (TIP), vol. 30, 2021, Pixel-wise Wasserstein Autoencoder for Highly Generative Dehazing


  • Sung Woo Park, Dong Wook Shu, and Junseok Kwon, The 34th Annual Conference on Neural Information Processing Systems (NeurIPS), 2020, Deep Diffusion-Invariant Wasserstein Distributional Classification


  • Dong Wook Shu*, Sung Woo Park*, and Junseok Kwon, International Conference on Computer Vision (ICCV), 2019, 3D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutions (*equal contribution)


  • Sung Woo Park and Junseok Kwon, Computer Vision and Pattern Recognition (CVPR), Oral presentation, 2019, Sphere Generative Adversarial Network Based on Geometric Moment Matching

Preprints

  • Sung Woo Park, Byung Woo Park, and Junseok Kwon, Stochastic Differential Game for Network Calibration, Under Review