copy and paste this google map to your website or blog!
Press copy button and paste into your blog or website.
(Please switch to 'HTML' mode when posting into your blog. Examples: WordPress Example, Blogger Example)
About Me - Jaeyun Song My research goal is to enhance privacy preservation and robustness in the training and inference of large generative models Initially, I focused on addressing robustness challenges, such as class imbalance (ICLR’22, ICML’22), structural noise in GNNs (ICML’23), and the dataset bias (NeurIPS’24)
GitHub - Jaeyun-Song TAM: TAM: Topology-Aware Margin Loss for Class . . . This work investigates the phenomenon that imbalance handling algorithms for node classificaion excessively increase the false positives of minor classes To mitigate this problem, we propose TAM, which adjusts the margin of each node according to the deviation from class-averaged topology The code for semi-supervised node classification
Jaeyun Song님 - PHD Student - 한국과학기술원 (KAIST) | LinkedIn My research goal is to enhance privacy preservation and robustness in the training and inference of large generative models 🎉 I’m thrilled to announce that our paper, “LANTERN: Accelerating
Jaeyoon Song Currently, I am exploring the capabilities of large language models in real-world forecasting I enjoy programming and design in my work and free time Jaeyoon Song studies computational social science at MIT Sloan School of Management
Jaeyun Song, UT ’22, talks about his experience with Passport to UT 2018 Hello! My name is Jaeyun Song I am from Seoul, the capital of the Republic of Korea I have finished my freshman year at UT and am taking a Dynamics Maymester class in Toulouse, France and Barcelona, Spain I am in the class of 2022, majoring in Mechanical Engineering
Jaeyun Song | IEEE Xplore Author Details Affiliations: [KAIST, South Korea] A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity