Sungyoon Lee

17 papers A* 7C 1Journal 7Unranked 2
YearRankTypeTitle / Venue / Authors
2025 A* conf
Prediction Risk and Estimation Risk of the Ridgeless Least Squares Estimator under General Assumptions on Regression Errors.
ICLR
Sungyoon Lee, Sokbae Lee
2025 A* conf
Variance Sensitivity Induces Attention Entropy Collapse and Instability in Transformers.
EMNLP
Jonghyun Hong, Sungyoon Lee
2024 J jnl
Sliced Wasserstein adversarial training for improving adversarial robustness.
J. Ambient Intell. Humaniz. Comput.
Woojin Lee, Sungyoon Lee, Hoki Kim, Jaewook Lee
2023 A* conf
A new characterization of the edge of stability based on a sharpness measure aware of batch gradient distribution.
ICLR
Sungyoon Lee, Cheongjae Jang
2023 J jnl
Bridged adversarial training.
Neural Networks
Hoki Kim, Woojin Lee, Sungyoon Lee, Jaewook Lee
2023 J jnl
GradDiv: Adversarial Robustness of Randomized Neural Networks via Gradient Diversity Regularization.
IEEE Trans. Pattern Anal. Mach. Intell.
Sungyoon Lee, Hoki Kim, Jaewook Lee
2023 A* conf
Implicit Jacobian regularization weighted with impurity of probability output.
ICML
Sungyoon Lee, Jinseong Park, Jaewook Lee
2023 J jnl
The Mean Squared Error of the Ridgeless Least Squares Estimator under General Assumptions on Regression Errors.
CoRR
Sungyoon Lee, Sokbae Lee
2022 A* conf
A Reparametrization-Invariant Sharpness Measure Based on Information Geometry.
NeurIPS
Cheongjae Jang, Sungyoon Lee, Frank C. Park, Yung-Kyun Noh
2022 J jnl
Variational cycle-consistent imputation adversarial networks for general missing patterns.
Pattern Recognit.
Woojin Lee, Sungyoon Lee, Junyoung Byun, Hoki Kim, Jaewook Lee
2021 J jnl
Bridged Adversarial Training.
CoRR
Hoki Kim, Woojin Lee, Sungyoon Lee, Jaewook Lee
2021 J jnl
GradDiv: Adversarial Robustness of Randomized Neural Networks via Gradient Diversity Regularization.
CoRR
Sungyoon Lee, Hoki Kim, Jaewook Lee
2021 A* conf
Towards Better Understanding of Training Certifiably Robust Models against Adversarial Examples.
NeurIPS
Sungyoon Lee, Woojin Lee, Jinseong Park, Jaewook Lee
2020 A* conf
Lipschitz-Certifiable Training with a Tight Outer Bound.
NeurIPS
Sungyoon Lee, Jaewook Lee, Saerom Park
2014 — conf
Myo-Signal Based Intuitive Driving Interface: Development and Evaluation.
BIC-TA
Jinuk Kim, Sungyoon Lee, Jaehyo Kim
2013 C conf
Development and evaluation of myoelectric driving interface.
ICCE
Jaesung Oh, Minsuk Kwon, Youngwon Kim, Jungsoo Kim, Sungyoon Lee, Jaehyo Kim
2013 — conf
User dependent interface based on facial expression.
GCCE
Euisun Kim, Yunseok Lee, Sungyoon Lee, Jaehyo Kim