Chulhee “Charlie” Yun
Chulhee “Charlie” Yun
Home
News
Publications
Teaching
Research Group
Service
News
Four papers got accepted to NeurIPS 2024. Among them, a paper on the theoretical analysis of Cutout/CutMix data augmentation was selected for a **spotlight presentation!**
Sep 26, 2024
I will be serving as an Area Chair for ICLR 2025!
Aug 20, 2024
One paper got accepted to the ICML 2024 Workshop on <a href="https://longcontextfm.github.io/" target="_blank">Long-Context Foundation Models</a> and another paper to appear at the ICML 2024 Workshop on <a href="https://want-ai-hpc.github.io/icml2024/" target="_blank">Advancing Neural Network Training: Computational Efficiency, Scalability, and Resource Optimization</a>.
Jun 19, 2024
Three papers got accepted to the ICML 2024 Workshop on <a href="https://sites.google.com/corp/view/hidimlearning/home" target="_blank">High-dimensional Learning Dynamics 2024: The Emergence of Structure and Reasoning</a>.
Jun 17, 2024
Our <a href="https://arxiv.org/abs/2402.10475" target="_blank">paper</a> on the benefit of alternating updates in minimax optimization got accepted to ICML 2024! (update: the paper was selected as a **spotlight paper!**)
May 2, 2024
One <a href="https://arxiv.org/abs/2402.10475" target="_blank">paper</a> was accepted to the ICLR 2024 Workshop on <a href="https://sites.google.com/view/bgpt-iclr24" target="_blank">Bridging the Gap Between Practice and Theory in Deep Learning</a>. We prove that alternating gradient descent-ascent (GDA) converges faster than simultaneous GDA, and propose an even faster variant!
Mar 5, 2024
Our <a href="https://arxiv.org/abs/2310.01082" target="_blank">paper</a> on the optimization characteristics of linear Transformers got accepted to ICLR 2024!
Jan 17, 2024
I had the honor to take part in the Fifth Korean-American Kavli Frontiers of Science Symposium as a session speaker.
Jan 12, 2024
Two papers got accepted to the NeurIPS 2023 Workshop on <a href="https://sites.google.com/view/m3l-2023" target="_blank">Mathematics of Modern Machine Learning (M3L)</a>! (update: both papers were selected for **oral presentations!**)
Oct 28, 2023
Four papers got accepted to NeurIPS 2023; among them, our <a href="https://arxiv.org/abs/2306.09850" target="_blank">SAM analysis paper</a> was selected for a **spotlight presentation!** Congratulations and thank you to my co-authors!
Sep 22, 2023
»
Cite
×