Kookjin Lee

h-index

Research activity per year

Fingerprint

Dive into the research topics where Kookjin Lee is active. These topic labels come from the works of this person. Together they form a unique fingerprint.

1 Similar Profiles

18 Conference contribution
15 Article
5 Conference article
2 Paper

EFFICIENTLY PARAMETERIZED NEURAL METRIPLECTIC SYSTEMS
Gruber, A., Lee, K., Lim, H., Park, N. & Trask, N., 2025, 13th International Conference on Learning Representations, ICLR 2025. International Conference on Learning Representations, ICLR, p. 85828-85852 25 p. (13th International Conference on Learning Representations, ICLR 2025).
Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
2 Link opens in a new tab Scopus citations
FastLRNR and Sparse Physics Informed Backpropagation
Cho, W., Lee, K., Park, N., Rim, D. & Welper, G., Feb 2025, In: Results in Applied Mathematics. 25, 100547.
Research output: Contribution to journal › Article › peer-review

Open Access
2 Link opens in a new tab Scopus citations
Latent Space Energy-based Neural ODEs
Cheng, S., Kong, D., Xie, J., Lee, K., Wu, Y. N. & Yang, Y., 2025, In: Transactions on Machine Learning Research. 2025
Research output: Contribution to journal › Article › peer-review
1 Link opens in a new tab Scopus citations
NEURAL FUNCTIONS FOR LEARNING PERIODIC SIGNAL
Cho, W., Jo, M., Lee, K. & Park, N., 2025, 13th International Conference on Learning Representations, ICLR 2025. International Conference on Learning Representations, ICLR, p. 38314-38354 41 p. (13th International Conference on Learning Representations, ICLR 2025).
Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
1 Link opens in a new tab Scopus citations
PIORF: PHYSICS-INFORMED OLLIVIER-RICCI FLOW FOR LONG-RANGE INTERACTIONS IN MESH GRAPH NEURAL NETWORKS
Yu, Y. Y., Choi, J., Park, J., Lee, K. & Park, N., 2025, 13th International Conference on Learning Representations, ICLR 2025. International Conference on Learning Representations, ICLR, p. 71606-71630 25 p. (13th International Conference on Learning Representations, ICLR 2025).
Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
2 Link opens in a new tab Scopus citations

1 Active
3 Finished

CAREER: Accelerating Scientific Discovery via Deep Learning with Strong Physics Inductive Biases
Lee, K. (PI)
National Science Foundation (NSF)
9/1/24 → 8/31/29
Project: Research project
EAGER: Combatting disinformation and racial bias: A deep-learning-assisted investigation of temporal dynamics of disinformation
Lee, K. (PI) & Kwon, K. H. (CoI)
National Science Foundation (NSF)
6/1/22 → 5/31/25
Project: Research project
Subcontract: SANDIA beyond fingerprinting grand challenge LDRD
Lee, K. (PI)
Sandia National Laboratories (SNL)
3/1/22 → 9/19/24
Project: Research project
Development of a graduate course on deep learning
Li, B. (CoI), Yang, Y. (PI) & Lee, K. (CoI)
INDUSTRY: Domestic Company
12/27/21 → 12/26/23
Project: Research project

Code from Parametrized neural ordinary differential equations: applications to computational physics problems
Lee, K. (Creator) & Parish, E. J. (Creator), The Royal Society, 2021
DOI: 10.6084/m9.figshare.16557722.v1, https://rs.figshare.com/articles/dataset/Code_from_Parametrized_neural_ordinary_differential_equations_applications_to_computational_physics_problems/16557722/1
Dataset
Supplementary material from "Parametrized neural ordinary differential equations: applications to computational physics problems"
Lee, K. (Creator) & Parish, E. J. (Creator), The Royal Society, 2021
DOI: 10.6084/m9.figshare.c.5599853, https://rs.figshare.com/collections/Supplementary_material_from_Parametrized_neural_ordinary_differential_equations_applications_to_computational_physics_problems_/5599853
Dataset
Code from Parameterized neural ordinary differential equations: applications to computational physics problems
Lee, K. (Creator) & Parish, E. J. (Creator), The Royal Society, 2021
DOI: 10.6084/m9.figshare.16557722.v2, https://rs.figshare.com/articles/dataset/Code_from_Parametrized_neural_ordinary_differential_equations_applications_to_computational_physics_problems/16557722/2
Dataset
Figure S4: from Parameterized neural ordinary differential equations: applications to computational physics problems
Lee, K. (Creator) & Parish, E. J. (Creator), The Royal Society, 2021
DOI: 10.6084/m9.figshare.16627263.v2, https://rs.figshare.com/articles/journal_contribution/Figure_S4_from_Parametrized_neural_ordinary_differential_equations_applications_to_computational_physics_problems/16627263/2
Dataset
Figure S2: from Parameterized neural ordinary differential equations: applications to computational physics problems
Lee, K. (Creator) & Parish, E. J. (Creator), The Royal Society, 2021
DOI: 10.6084/m9.figshare.16627260.v2, https://rs.figshare.com/articles/journal_contribution/Figure_S2_from_Parametrized_neural_ordinary_differential_equations_applications_to_computational_physics_problems/16627260/2
Dataset

Kookjin Lee

Fingerprint

Collaborations and top research areas from the last five years

Dive into details

EFFICIENTLY PARAMETERIZED NEURAL METRIPLECTIC SYSTEMS

FastLRNR and Sparse Physics Informed Backpropagation

Latent Space Energy-based Neural ODEs

NEURAL FUNCTIONS FOR LEARNING PERIODIC SIGNAL

PIORF: PHYSICS-INFORMED OLLIVIER-RICCI FLOW FOR LONG-RANGE INTERACTIONS IN MESH GRAPH NEURAL NETWORKS

CAREER: Accelerating Scientific Discovery via Deep Learning with Strong Physics Inductive Biases

EAGER: Combatting disinformation and racial bias: A deep-learning-assisted investigation of temporal dynamics of disinformation

Subcontract: SANDIA beyond fingerprinting grand challenge LDRD

Development of a graduate course on deep learning

Code from Parametrized neural ordinary differential equations: applications to computational physics problems

Supplementary material from "Parametrized neural ordinary differential equations: applications to computational physics problems"

Code from Parameterized neural ordinary differential equations: applications to computational physics problems

Figure S4: from Parameterized neural ordinary differential equations: applications to computational physics problems

Figure S2: from Parameterized neural ordinary differential equations: applications to computational physics problems

Kookjin Lee

Fingerprint

Collaborations and top research areas from the last five years

Research output

Projects

Datasets