Sung-Yub Kim

Research Scientist @ SAMSUNG

I’m a researcher in the LLM team @ AI Center, Samsung Electronics.

My research interest includes:

  • Post-hoc analysis & adaptation of Foundation models (e.g., Large-Language Models and Vision-Language Models).
  • Explainability and interpretability of Foundation models.
  • Generalization of Foundation models via the lens of loss landscape.

Education

Published Papers

[7] LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative Decoding
Doohyuk Jang, Sihwan Park, June Yong Yang, Yeonsung Jung, Jihun Yun, Souvik Kundu, Sung-Yub Kim, Eunho Yang
ICLR, 2025 (Co-Correspondence Author)

[6] A Simple Remedy for Dataset Bias via Self-Influence: A Mislabeled Sample Perspective
Yeonsung Jung*, Jaeyun Song*, June Yong Yang*, Jin-Hwa Kim, Sung-Yub Kim, and Eunho Yang (*: equal contribution)
NeurIPS, 2024

[5] TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias
Sanghyun Jo*, Soohyun Ryu*, Sungyub Kim, Eunho Yang, Kyungsu Kim (*: equal contribution)
European Conference on Computer Vision (ECCV), 2024

[4] GEX: A flexible method for approximating influence via Geometric Ensemble
Sung-Yub Kim, Kyungsu Kim, Eunho Yang
NeurIPS, 2023 (1st Author)

[3] RGE: A Repulsive Graph Rectification for Node Classification via Influence
Jaeyun Song*, Sung-Yub Kim*, Eunho Yang (*: equal contribution)
ICML, 2023 (Co-1st Author)

[2] Scale-invariant Bayesian Neural Networks with Connectivity Tangent Kernel
Sung-Yub Kim, Sihwan Park, Kyungsu Kim, Eunho Yang
ICLR, 2023 (Spotlighted) (1st Author)

[1] Generalized Tsallis Entropy Reinforcement Learning and Its Application to Soft Mobile Robots
Kyungjae Lee, Sung-Yub Kim, Sungbin Lim, Sungjoon Choi, Mineui Hong, Jaein Kim, Yong-Lae Park, and Songhwai Oh
Robotics: Science and Systems Foundation

Projects (in school)

  • Autonomous Intelligent Digital Companion Framework and Application
    Korea Electronics Technology Institute, 2019-2021

  • A study on adaptive point and regional OOD detection techniques based on sub-task generation
    Samsung, 2020-2023

  • A machine learning and statistical inference framework for explainable artificial intelligence
    Institute of Information & Communications Technology Planning & Evaluation (IITP), 2022-2023

  • A Study on Optimization and Network Interpretation Method for Large-Scale Machine Learning
    National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT), 2022-2023