Donghwan Kim
Scholar

Donghwan Kim

Google Scholar ID: G74RcZQAAAAJ
KAIST
Optimization for Machine Learning
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
1,503
 
H-index
15
 
i10-index
22
 
Publications
20
 
Co-authors
17
list available
Contact
No contact links provided.
Publications
8 items
Why the Counterintuitive Phenomenon of Likelihood Rarely Appears in Tabular Anomaly Detection with Deep Generative Models?
2026
Cited
0
Mitigating the Likelihood Paradox in Flow-based OOD Detection via Entropy Manipulation
2026
Cited
0
Cocoon: A System Architecture for Differentially Private Training with Correlated Noises
2025
Cited
0
LieHMR: Autoregressive Human Mesh Recovery with $SO(3)$ Diffusion
2025
Cited
0
PARTE: Part-Guided Texturing for 3D Human Reconstruction from a Single Image
2025
Cited
0
DeClotH: Decomposable 3D Cloth and Human Body Reconstruction from a Single Image
2025
Cited
0
Stochastic Extragradient with Flip-Flop Shuffling&Anchoring: Provable Improvements
2024
Cited
0
NeuJeans: Private Neural Network Inference with Joint Optimization of Convolution and FHE Bootstrapping
Conference on Computer and Communications Security · 2023
Cited
7
Resume (English only)
Co-authors
17 total
Jeffrey Fessler
Jeffrey Fessler
Professor of EECS, University of Michigan
Co-author 2
Co-author 2
Co-author 3
Co-author 3
Bruno De Man
Bruno De Man
Chief Scientist, GE Research
Co-author 5
Co-author 5
Co-author 6
Co-author 6
Co-author 7
Co-author 7
Co-author 8
Co-author 8