OpenReview
.net
OpenReview
.net
Login
OpenReview
.net
Login
Sung-Yub Kim
Researcher, Samsung
Joined
May 2021
Names
Sung-Yub Kim
(Preferred)
,
SungYub Kim
Emails
****@kaist.ac.kr
(Confirmed)
,
****@mli.kaist.ac.kr
(Confirmed)
Personal Links
Homepage
Google Scholar
DBLP
Career & Education History
Researcher
Samsung
(samsung.com)
2024
–
Present
PhD student
Korea Advanced Institute of Science and Technology
(kaist.ac.kr)
2019
–
2024
MS student
Seoul National University
(snu.ac.kr)
2017
–
2019
Undergrad student
Seoul National University
(snu.ac.kr)
2013
–
2017
Advisors, Relations & Conflicts
PhD Advisor
Eunho Yang
2019
–
2024
Expertise
Influence Function
2022
–
2024
Explainable AI
2022
–
2024
Bayesian inference
2019
–
2024
Publications
LANTERN++: Enhancing Relaxed Speculative Decoding with Static Tree Drafting for Visual Auto-regressive Models
Sihwan Park
,
Doohyuk Jang
,
Sung-Yub Kim
,
Souvik Kundu
,
Eunho Yang
SCOPE - ICLR 2025 Oral
Readers:
Everyone
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 Poster
Readers:
Everyone
MeZO-A$^{3}$dam: Memory-efficient Zeroth-order Adam with Adaptivity Adjustments for Fine-tuning LLMs
Sihwan Park
,
Jihun Yun
,
Sung-Yub Kim
,
June Yong Yang
,
Yeonsung Jung
,
Souvik Kundu
,
Kyungsu Kim
,
Eunho Yang
ICLR 2025 Conference Withdrawn Submission
Readers:
Everyone
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
,
Eunho Yang
NeurIPS 2024 poster
Readers:
Everyone
Post-Training Recovery from Injected Bias with Self-Influence
Yeonsung Jung
,
Jaeyun Song
,
June Yong Yang
,
Jin-Hwa Kim
,
Sung-Yub Kim
,
Eunho Yang
Submitted to ICLR 2024
Readers:
Everyone
GEX: A flexible method for approximating influence via Geometric Ensemble
SungYub Kim
,
Kyungsu Kim
,
Eunho Yang
NeurIPS 2023 poster
Readers:
Everyone
RGE: A Repulsive Graph Rectification for Node Classification via Influence
Jaeyun Song
,
SungYub Kim
,
Eunho Yang
ICML 2023 Poster
Readers:
Everyone
Scale-invariant Bayesian Neural Networks with Connectivity Tangent Kernel
SungYub Kim
,
Sihwan Park
,
Kyung-Su Kim
,
Eunho Yang
Published: 01 Feb 2023, Last Modified: 01 Mar 2023
ICLR 2023 notable top 25%
Readers:
Everyone
Bias Decay Matters : Improving Large Batch Optimization with Connectivity Sharpness
SungYub Kim
,
Sihwan Park
,
Yong-Deok Kim
,
Eunho Yang
29 Sept 2021 (modified: 13 Feb 2023)
ICLR 2022 Conference Withdrawn Submission
Readers:
Everyone
Generalized Tsallis Entropy Reinforcement Learning and Its Application to Soft Mobile Robots
Kyungjae Lee
,
Sungyub Kim
,
Sungbin Lim
,
Sungjoon Choi
,
Mineui Hong
,
Jae In Kim
,
Yong-Lae Park
,
Songhwai Oh
Published: 01 Jan 2020, Last Modified: 12 May 2023
Robotics: Science and Systems 2020
Readers:
Everyone
View all 12 publications
Co-Authors
Doohyuk Jang
Eunho Yang
Jae In Kim
Jaeyun Song
Jihun Yun
Jin-Hwa Kim
June Yong Yang
Kyung-Su Kim
Kyungjae Lee
Kyungsu Kim
Mineui Hong
Sihwan Park
Songhwai Oh
Souvik Kundu
Sung Ju Hwang
Sungbin Lim
Sungjoon Choi
Yeonsung Jung
Yong-Deok Kim
Yong-Lae Park
Yongsu Baek