
-
- 02-760-0467
- jaewoongchoi@skku.edu
- 다산경제관 4층 32406호실
-
관심분야
통계적 머신러닝, 생성모델
학력
- (M.S./Ph.D) 서울대학교 수리과학부
- (B.S.) 서울대학교 수리과학부
약력/경력
- 고등과학원 AI 기초과학센터 AI Research Fellow 2022.03-2025.02
학술지 논문
- (2025) Analyzing the latent space of GAN through local dimension estimation for disentanglement evaluation. PATTERN RECOGNITION. 157, 1
- (2023) Disentangling the correlated continuous and discrete generative factors of data. PATTERN RECOGNITION. 133, 1
수상/공훈
- 세종과학펠로우십, 한국연구재단, 2024-2029,
- 고등과학원 학술상, 2023.
- NeurIPS Travel Award, 2023.
- Samsung AI Forum – Poster 3rd Prize, 2022.
- National Excellence Scholarship (Natural Sciences and Engineering), Korea Student Aid Foundation, 2011-2015.
학술회의논문
- (2026) Efficient Generative Modeling beyond Memoryless Diffusion via Adjoint Schrödinger Bridge Matching. International Conference on Machine Learning. 대한민국
- (2026) UOTIP: Unbalanced Optimal Transport Map for Unpaired Inverse Problems. International Conference on Machine Learning. 대한민국
- (2025) Unpaired Point Cloud Completion via Unbalanced Optimal Transport. International Conference on Machine Learning. 캐나다
- (2025) Overcoming Spurious Solutions in Semi-Dual Neural Optimal Transport: A Smoothing Approach for Learning the Optimal Transport Plan. International Conference on Machine Learning. 캐나다
- (2025) Improving Neural Optimal Transport via Displacement Interpolation. International Conference on Learning Representations. 싱가포르
- (2025) Robust Barycenter Estimation using Semi-Unbalanced Neural Optimal Transport. International Conference on Learning Representations. 싱가포르
- (2024) Scalable Wasserstein Gradient Flow for Generative Modeling through Unbalanced Optimal Transport. International Conference on Machine Learning. 오스트리아
- (2024) Analyzing and Improving Optimal-Transport-based Adversarial Networks. International Conference on Learning Representations. 오스트리아
- (2023) Understanding the Latent Space of Diffusion Models through the Lens of Riemannian Geometry. Conference on Neural Information Processing Systems. 미국
- (2023) Generative Modeling through the Semi-dual Formulation of Unbalanced Optimal Transport. Conference on Neural Information Processing Systems. 미국
- (2023) MAGANet: Achieving Combinatorial Generalization by Modeling a Group Action. International Conference on Machine Learning. 미국
- (2023) Finding the Global Semantic Representation in GAN through Fréchet Mean. International Conference on Learning Representations. 르완다
- (2022) Do Not Escape From the Manifold: Discovering the Local Coordinates on the Latent Space of GANs. International Conference on Learning Representations. 대한민국
발전기금



