Hee-Sung Kim
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
ML×1AI×1
Frequent co-authors
Research Timeline
2026
Inconsistency-Aware Minimization: Improving Generalization with Unlabeled Data
The paper introduces Inconsistency-Aware Minimization (IAM), a novel training objective that uses a label-free measure called local inconsistency to improve model generalization, particularly in semi-supervised settings.
Highlighted terms show continued research focus across papers