Publications

From Linear to Nonlinear: Provable Weak-to-Strong Generalization through Feature Learning

Junsoo Oh, Jerry Song, Chulhee Yun
ICML 2025 Workshop on High-dimensional Learning Dynamics 2025
KT Best Paper Award at KAIA Conference 2025 (CKAIA 2025)

Provable Benefit of Cutout and CutMix for Feature Learning

Junsoo Oh, Chulhee Yun
NeurIPS 2024 (Spotlight)
ICML 2024 Workshop on High-dimensional Learning Dynamics 2024: The Emergence of Structure and Reasoning
KT Best Paper Award at KAIA Conference 2024 (CKAIA 2024)

DASH: Warm-Starting Neural Network Training in Stationary Settings without Loss of Plasticity

Baekrok Shin∗ , Junsoo Oh∗ , Hanseul Cho, Chulhee Yun
NeurIPS 2024
ICML 2024 Workshop on Advancing Neural Network Training (WANT): Computational Efficiency, Scalability, and Resource Optimization

Provable Benefit of Mixup for Finding Optimal Decision Boudaries

Junsoo Oh, Chulhee Yun
ICML 2023