Research

Primordial Black Holes as a Factory of Axions: Extragalactic Photons from Axions

2026

Prog. Theor. Exp. Phys.

Tae-Geun Kim, Jong-Chul Park, Seong Chan Park, Yeji Park

Dark MatterPBHAxion

Abstract: We investigate the extragalactic photon signals produced by axion-like particles emitted from primordial black holes via Hawking radiation.

@article{kim2023primordial, title={Primordial Black Holes as a Factory of Axions: Extragalactic Photons from Axions}, author={Kim, Tae-Geun and Park, Jong-Chul and Park, Seong Chan and Park, Yeji}, journal={Progress of Theoretical and Experimental Physics}, pages={ptag011}, year={2026}, doi={10.1093/ptep/ptag011} }

DOI arXiv

Learning Hamiltonian Dynamics with Bayesian Data Assimilation

2025

arXiv preprint

Taehyeun Kim, Tae-Geun Kim, Anouk Girard, Ilya Kolmanovsky

Machine LearningHamiltonianBayesian

Abstract: We propose a framework combining Hamiltonian neural networks with Bayesian data assimilation for learning dynamical systems.

@article{kim2025learning, title={Learning Hamiltonian Dynamics with Bayesian Data Assimilation}, author={Kim, Taehyeun and Kim, Tae-Geun and Girard, Anouk and Kolmanovsky, Ilya}, journal={arXiv preprint arXiv:2501.18808}, year={2025} }

arXiv

Neural Hamilton: Can A.I. Understand Hamiltonian Mechanics?

2024

arXiv preprint

Tae-Geun Kim, Seong Chan Park

Machine LearningOperator LearningHamiltonian

Abstract: We investigate whether neural network architectures can learn Hamiltonian dynamics directly from the Hamiltonian function using operator learning.

@article{kim2024neural, title={Neural Hamilton: Can A.I. Understand Hamiltonian Mechanics?}, author={Kim, Tae-Geun and Park, Seong Chan}, journal={arXiv preprint arXiv:2410.20951}, year={2024} }

arXiv Code

HyperbolicLR: Epoch insensitive learning rate scheduler

2024

arXiv preprint

Tae-Geun Kim

Machine LearningOptimization

Abstract: We propose HyperbolicLR, a learning rate scheduler that is insensitive to the total number of training epochs.

@article{kim2024hyperboliclr, title={HyperbolicLR: Epoch insensitive learning rate scheduler}, author={Kim, Tae-Geun}, journal={arXiv preprint arXiv:2407.15200}, year={2024} }

arXiv

Unsupervised sequence-to-sequence learning for automatic signal quality assessment in multi-channel electrical impedance-based hemodynamic monitoring

2024

Comput. Meth. Prog. Bio.

Chang Min Hyun, Tae-Geun Kim, Kyounghun Lee

Machine LearningBiomedicalSignal Processing

Abstract: We propose an unsupervised sequence-to-sequence learning framework for automatic signal quality assessment in multi-channel EIT-based hemodynamic monitoring.

@article{hyun2024unsupervised, title={Unsupervised sequence-to-sequence learning for automatic signal quality assessment in multi-channel electrical impedance-based hemodynamic monitoring}, author={Hyun, Chang Min and Kim, Tae-Geun and Lee, Kyounghun}, journal={Computer Methods and Programs in Biomedicine}, pages={108079}, year={2024}, doi={10.1016/j.cmpb.2024.108079} }

DOI arXiv

DeeLeMa: Missing information search with Deep Learning for Mass estimation

2023

Phys. Rev. Research

Kayoung Ban, Dong Woo Kang, Tae-Geun Kim, Seong Chan Park, Yeji Park

Machine LearningParticle PhysicsMass Estimation

Abstract: We propose DeeLeMa, a deep learning framework for mass estimation using missing information search in particle physics events.

@article{ban2023deelema, title={DeeLeMa: Missing information search with Deep Learning for Mass estimation}, author={Ban, Kayoung and Kang, Dong Woo and Kim, Tae-Geun and Park, Seong Chan and Park, Yeji}, journal={Physical Review Research}, volume={5}, number={4}, pages={043186}, year={2023}, doi={10.1103/PhysRevResearch.5.043186} }

DOI arXiv Code

Accelerating PBH Phenomenology via Neural Operators

2026

The 2nd AI+HEP in East Asia @ KEK

Tsukuba, Japan

Oral

From Primordial Black Holes to Nuclei: Solving Inverse Problems in Physics with Operator Learning

2025

Nuclear Lunch Seminar @ Fudan University

Shanghai, China

Invited

Can AI Understand Hamiltonian Mechanics?

2025

Summer Institute 2025

Yeosu, Korea

Oral

Slides

A Neural Operator for Primordial Black Hole Physics

2025

The 4th Workshop on Symmetry and Structure of the Universe

Jeonju, Korea

Oral

Slides

PBH Phenomenology with Operator Learning

2025

LSSU Seminar @ JBNU

Jeonju, Korea

Invited

Slides

AI with Hamiltonian Mechanics: From Predictions to Understanding

2025

AI+HEP in East Asia 2025

Daejeon, Korea

Oral

Slides