Scholar
Donghwan Kim
Google Scholar ID: G74RcZQAAAAJ
KAIST
Optimization for Machine Learning
Follow
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
14 items
Evaluation Ability Does Not Imply Optimization Utility: LLM-as-a-Judge Signals in Closed-Loop Table Recognition
2026
Cited
0
Understanding Schedule-Free Methods in Nonconvex Optimization: Rate Guarantees and Escaping Saddles
2026
Cited
0
A Kernel Fisher Discriminant Analysis-Based Tree Ensemble Classifier: KFDA Forest
2026
Cited
0
Characterization of Multi-Model Agentic AI Systems on General Tasks via Trace-Driven Simulation
2026
Cited
0
MahaVar: OOD Detection via Class-wise Mahalanobis Distance Variance under Neural Collapse
2026
Cited
0
PhysHanDI: Physics-Based Reconstruction of Hand-Deformable Object Interactions
2026
Cited
0
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
Load more
Resume (English only)
Co-authors
17 total
Jeffrey Fessler
Professor of EECS, University of Michigan
Co-author 2
Co-author 3
Bruno De Man
Chief Scientist, GE Research
Lin Fu
GE Global Research
Co-author 6
Kyuwon Kim
KAIST
Jiseok Chae
KAIST
