Love to learn new things.
Love to play the violin.
Embedded Files
Biography
Biography
I am a research scientist at Google DeepMind, focusing on responsibly shaping the next generation of large models and translating them into meaningful, real-world applications.
Before joining Google, I completed my Ph.D. in 2024 from KAIST EE and was extremely fortunate to have been advised by Prof. Steven Euijong Whang during my PhD journey. I am also a recipient of the Microsoft Research PhD Fellowship. Previously, I worked as a research intern at Google DeepMind & YouTube in 2023 and NVIDIA Research in 2022, working with wonderful mentors.
Publications
Publications
Responsible & Safe AI
Responsible & Safe AI
PFGuard: A Generative Framework with Privacy and Fairness Safeguards
S. Kim, Y. Roh, G. Heo, S. E. Whang
ICLR 2025LEVI: Generalizable Fine-tuning via Layer-wise Ensemble of Different Views [Paper]
Y. Roh, Q. Liu, H. Gui, Z. Yuan, Y. Tang, S. E. Whang, L. Liu, S. Bi, L. Hong, E. H. Chi, and Z. Zhao
ICML 2024Improving Fair Training under Correlation Shifts [Paper / Slides / Code]
Y. Roh, K. Lee, S. E. Whang, and C. Suh
ICML 2023Dr-Fairness: Dynamic Data Ratio Adjustment for Fair Training on Real and Generated Data [Paper / Code]
Y. Roh, W. Nie, D. Huang, S. E. Whang, A. Vahdat, and A. Anandkumar
TMLR 2023Sample Selection for Fair and Robust Training [Paper / Talk / Slides / Code]
Y. Roh, K. Lee, S. E. Whang, and C. Suh
NeurIPS 2021Machine Learning Robustness, Fairness, and their Convergence (Tutorial) [Paper / Talk / Slides]
J. Lee, Y. Roh, H. Song, and S. E. Whang
ACM SIGKDD 2021FairBatch: Batch Selection for Model Fairness [Paper / Talk / Slides / Code]
Y. Roh, K. Lee, S. E. Whang, and C. Suh
ICLR 2021Responsible AI Challenges in End-to-end Machine Learning [Paper]
S. E. Whang, K. Tae, Y. Roh, and G. Heo
IEEE Data Engineering Bulletin 2021FR-Train: A Mutual Information-Based Approach to Fair and Robust Training [Paper / Talk / Slides / Code / KAIST Breakthroughs]
Y. Roh, K. Lee, S. E. Whang, and C. Suh
ICML 2020Data Cleaning for Accurate, Fair, and Robust Models: A Big Data - AI Integration Approach [Paper]
K. Tae, Y. Roh, Y. Oh, H. Kim, and S. E. Whang
DEEM @ ACM SIGMOD 2019
Data-CEntric AI
Data-CEntric AI
Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspective [Paper]
S. E. Whang, Y. Roh, H. Song, and J. Lee
VLDB Journal 2023 (Early Access from 2022)Inspector Gadget: A Data Programming-Based Labeling System for Industrial Images [Paper]
G. Heo, Y. Roh, S. Hwang, D. Lee, and S. E. Whang
VLDB 2021A Survey on Data Collection for Machine Learning: A Big Data - AI Integration Perspective [Paper]
Y. Roh, G. Heo, and S. E. Whang
IEEE TKDE 2021 (Early Access from 2019)
Thesis
Thesis
Towards Practical Model Fairness for Trustworthy and Safe AI
Y. Roh
Ph.D. Thesis, KAIST, 2024
Experience
Experience
Google, Mountain View, CA | Jun. 2024 - Present
Research Scientist @ DeepMind | Jun. 2025 - Present
Software Engineer @ YouTube | Jun. 2024 - Jun. 2025Google DeepMind and YouTube, Mountain View, CA | Jun. 2023 - Dec. 2023
Research Intern
Mentors: Zhe Zhao, Sunny Liu, Huan Gui, Jeremy Yuan, Liang Liu, Lichan Hong, and Ed ChiNVIDIA, Santa Clara, CA (Remote) | Jun. 2022 - Dec. 2022
Research Intern
Mentors: Weili Nie, De-An Huang, Arash Vahdat, and Anima Anandkumar
Education
Education
Postdoctoral Researcher in Electrical Engineering, KAIST | Mar. 2024 - Jun. 2024
Ph.D. (Integrated with Master) in Electrical Engineering, KAIST | Sept. 2019 - Feb. 2024
Master in Electrical Engineering, KAIST | Sept. 2018 - Aug. 2019
B.S. in Electrical Engineering & Minor in Intellectual Property, KAIST | Feb. 2014 - Aug. 2018 (Summa Cum Laude )
Korea Science Academy | Feb. 2011 - Feb. 2014
Honors
Honors
Microsoft Research PhD Fellowship | 2022
Best Research Achievement Award, KAIST EE | Spring 2022
Research Breakthroughs, KAIST | Spring 2021
The Qualcomm Innovation Fellowship | Dec. 2020
Best TA Award, KAIST | Jun. 2020
Department Honors (Top-3) Scholarship, KAIST | Spring 2017
Dean's List, KAIST | Spring 2016
National Science & Engineering Scholarship | Spring 2016 - Spring 2018
Talks
Talks
The AI Feedback Loop: New Promises and Risks of Large Models
FutureTech Workshop on The Role of AI in Science @ MIT | Nov. 2024
Machine Learning Fairness and its Convergence with Robustness
Tutorial @ IEEE BigComp Conference | Feb. 2023
Machine Learning Robustness, Fairness, and their Convergence
Tutorial @ ACM SIGKDD Conference | Aug. 2021
Responsible AI Techniques for Model Training
TechTalk to the TensorFlow team @ Google Korea | Feb. 2020
Google Sites
Report abuse