Embedded Files
About me
About me
I am a final-year Ph.D. candidate in the department of Industrial Engineering & Operations Research (IEOR) at University of California, Berkeley. I am very fortunate to be advised by Prof. Javad Lavaei. I also have the privilege of working closely with Prof. S. Shankar Sastry. I'm currently on the 2026-2027 academic job market.
Previously, I received my Bachelor of Science degree in both Industrial Engineering and Statistics at Seoul National University (SNU).
Research Interest: I work on interdisciplinary problems in control, optimization, and AI. My research advances trustworthy, sample-efficient, and robust approaches for real-world safety-critical/physical systems in adversarial environments. Core research directions include:
Robust Model Identification under uncertainty: developing methods to solve the inverse problem by learning systems from partial, noisy, or adversarially poisoned real-world observations.
Scalable and safe optimization under uncertainty: designing scalable convex/non-convex and non-smooth optimization algorithms with provable finite-time convergence rates and safety guarantees.
Multi-agent intelligence under uncertainty: scaling verifiable physical AI to multi-agent networks by aligning individual agent incentives with global specifications.
My long-term vision is to establish the rigorous foundation for next-generation multi-agent cyber-physical systems by unifying AI-driven model identification with formal mathematical verification.
Here is a link to my CV and a link to my recent INFORMS Job Talk.
Publications
Publications
Journal Papers
Journal Papers
"Online Bandit Nonlinear Control with Dynamic Batch Length and Adaptive Learning Rate"
Jihun Kim and Javad Lavaei,
Transactions on Machine Learning Research (TMLR), 2025.
[arXiv] [Published] [Talk Video]
"The landscape of deterministic and stochastic optimal control problems:
One-shot optimization versus Dynamic Programming"
Jihun Kim, Yuhao Ding, Yingjie Bi, and Javad Lavaei,
IEEE Transactions on Automatic Control, 2024.
Conference Papers (Peer-Reviewed)
Conference Papers (Peer-Reviewed)
Jihun Kim and Javad Lavaei,
to appear in 65th IEEE Conference on Decision and Control (CDC), 2026.
[arXiv]
"On the Sharp Input-Output Analysis of Nonlinear Systems under Adversarial Attacks"
Jihun Kim, Yuchen Fang, and Javad Lavaei,
International Conference on Machine Learning (ICML), 2026,
has been selected as a Spotlight Paper (TOP 2.2%, 536 / ~24,000 submissions)
"Subgradient Method for System Identification with Non-Smooth Objectives"
Baturalp Yalcin, Jihun Kim, and Javad Lavaei,
8th Learning for Dynamics & Control Conference (L4DC), 2026.
"System Identification from Partial Observations under Adversarial Attacks"
Jihun Kim and Javad Lavaei,
64th IEEE Conference on Decision and Control (CDC), 2025.
"Prevailing against Adversarial Noncentral Disturbances:
Exact Recovery of Linear Systems with the l_1-norm Estimator"
Jihun Kim and Javad Lavaei,
American Control Conference (ACC), 2025,
has been selected as a Best Student Paper Award Finalist (TOP 6 / 1000+ submissions).
Manuscripts under Revision
Manuscripts under Revision
"A Trust-Region Interior-Point Stochastic Sequential Quadratic Programming Method"
Yuchen Fang, Jihun Kim, Sen Na, James Demmel, and Javad Lavaei,
Major Revision in SIAM Journal on Optimization, 2026.
"Bridging Batch and Streaming Estimations to System Identification under Adversarial Attacks"
Jihun Kim and Javad Lavaei,
Major Revision in IEEE Transactions on Automatic Control, 2025.
Manuscripts under Review (Preprints)
Manuscripts under Review (Preprints)
Jihun Kim, Pan-Yang Su, Maria G. Mendoza, Victoria Marie Tuck, Chinmay Maheshwari, and S. Shankar Sastry
submitted to International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2026.
"Defense Filters for Robust Learning of Partially Observed Dynamical Systems"
Jihun Kim and Javad Lavaei,
submitted as an invited paper to IFAC Symposium on System Identification, 2026.
"System Identification under Noise and Attack Regimes: Agnostic and Composite Robustness"
Jihun Kim and Javad Lavaei,
under review at IEEE Transactions on Automatic Control, 2026.
"Structural Correspondence and Universal Approximation in Diagonal plus Low-Rank Neural Networks"
Ying Chen, Aoxi Li, Jihun Kim, and Javad Lavaei,
submitted to International Conference on Learning Representations (ICLR), 2026.
Peer-Reviewed Workshop Papers
Peer-Reviewed Workshop Papers
Jihun Kim,
Optimization for Machine Learning (OPT), 2025, NeurIPS Workshop.
“6MapNet: Representing Soccer Players from Tracking Data by a Triplet Network”
Hyunsung Kim, Jihun Kim, Dongwook Chung, Jonghyun Lee, Jinsung Yoon, and Sang-Ki Ko,
Machine Learning and Data Mining for Sports Analytics (MLSA), 2021, ECML/PKDD Workshop.
AWARDS & HONORS
AWARDS & HONORS
2026 UC Berkeley Outstanding Graduate Student Instructor (OGSI) Award.
Top Reviewer Award, Conference on Neural Information Processing Systems (NeurIPS), 2026.
Gold Reviewer Award, International Conference on Machine Learning (ICML), 2026.
2025 Best Student Paper Award Finalist, American Control Conference (ACC), 2025.
2022-2027 Kwanjeong Fellowship (Stipend).
2022 UC Berkeley 1st year Fellowship.
2021 Merit-Based Scholarship (Full Amount), S&T Scholarship (Stipend).
2020 SNU Development Fund Scholarship (Full Amount).
Award for Excellence as a Tutor in Peer Tutoring Program, SNU.
Lee Joong-Han Award, Academic Sector, Dept. of Industrial Engineering.
Best Digital Transformation(DT) Division Summer intern, SK hynix.
2017 SNU Sinyang Cultural Foundation Scholarship (Full Amount).
2016 Eminence Scholarship (Full Amount), Merit-Based Scholarship for first-year student
TEACHING EXPERIENCEs
TEACHING EXPERIENCEs
IEOR 160: Nonlinear and Discrete Optimization TA (Spring 2024, Spring 2025)
UGBA 104: Introduction to Business Analytics TA (Summer 2025, Summer 2026)
IEOR 262A: Mathematical Programming I TA (Fall 2025)
IEOR 240: Optimization Analytics TA (Fall 2026)
@ University of California, Berkeley
Operations Research 1 Tutor (Fall 2021)
Statistics for Industrial Engineering Tutor (Spring 2021)
Human Factors Engineering Tutor (Fall 2020)
Calculus 1 (English Medium Instruction) Tutor, College English Tutor (Spring 2020)
@ Seoul National University
ACADEMIC SerVICES
ACADEMIC SerVICES
Reviewer for:
IEEE Transactions on Automatic Control, 2026.
Mathematical Programming, 2025, 2026.
IEEE Control Systems Letters (L-CSS), 2026.
Conference on Neural Information Processing Systems (NeurIPS), 2026.
International Conference on Machine Learning (ICML), 2026.
Conference on Decision and Control (CDC), 2025, 2026.
American Control Conference (ACC), 2025, 2026.
International Conference on Learning Representations (ICLR), 2025.
Competences
Competences
Programming: Python, MySQL, R, MATLAB, Xpress Mosel
Skills: CVX, Gurobi, SOSTOOLS (optimization), Tensorflow, PyTorch, Scikit-learn (ML/DL)
Languages: Korean (Native), English (Fluent), Chinese (Rudimentary)
Hobby : Watching baseball, soccer, & football (KBO, MLB, EPL, NFL), Playing the violin
WORKING EXPERIENCEs
WORKING EXPERIENCEs
Sports data analysis intern @ Fitogether Inc.
Aimed to find the best embedding vector for soccer players via contrastive representation learning
Practical soccer player retrieval only using tracking data
Semiconductor image data analysis intern @ SK hynix
Aimed to find the explainable AI to highlight the basic reason why some semiconductor images are classified as abnormal
Winner of 2020 Summer Digital Transformation Division intern Competition
CONTACT
CONTACT
Email: jihun.kim@berkeley.edu
Page updated
Report abuse