News
Research, publications, talks, and academic service.
2026
- Sep 25, 2026Three papers accepted to NeurIPS 2026: regularized regret, budgeted LLM evaluation, and online RLHF.
- Jul 10, 2026Our LLM evaluation paper received the Best Paper Award (Long Paper track) at the ICML CTB Workshop.
Invited talk at Chung-Ang University
I’ll be giving a talk at the Chung-Ang University, hosted by Kyoungseok Jang presenting my recent work (Provably Efficient Regularized Online RLHF with Generalized Bilinear Preferences).
- May 14, 2026Recognized as an ICML Gold Reviewer. Reviewing service →
2025
One paper accepted to NeurIPS 2025! Congrats Woosung!
AdaSTaR: Adaptive Data Sampling for Training Self-Taught Reasoners
- Summer 2025Research Scientist Intern at Adobe Research, San Jose. Experience →
I gave an invited talk (virtual) at the Reading Group of Prof. Ilija Bogunovic of UCL!
Two Theoretical Advances on Sample-Efficient Preference Learning
One paper accepted to ICLR 2025 DeLTa Workshop! Congrats Kunwoo!
Probability-Flow ODE in Infinite-Dimensional Function Spaces
One paper accepted to ICLR 2025! Congrats Woosung!
FlickerFusion: Intra-trajectory Domain Generalizing Multi-agent Reinforcement Learning
2024
I gave an invited talk at Hyperconnect, hosted by Dr. Gihun Lee!
Bandits 101: A Maximally Non-technical Tutorial
One paper accepted to NeurIPS 2024 Workshop on Open-World Agents (OWA)!
FlickerFusion: Intra-trajectory Domain Generalizing Multi-Agent RL
One paper accepted to NeurIPS 2024!
A Unified Confidence Sequence for Generalized Linear Models, with Applications to Bandits
I’ll be giving a talk at the DeLTA Seminar in Copenhagen, Denmark.
Improved Regret Bounds of (Multinomial) Logistic Bandits via Regret-to-Confidence-Set Conversion
I’ll be spending the next two weeks in Stockholm, attending Stochastic Networks Conference 2024 and visiting KTH!
Digital Futures focus period on Learning in Networks - Structure, Dynamics, and Control
Two papers accepted to two ICML workshops, one as oral!
ARLET Workshop (oral), HiLD Workshop
I’ll be giving a talk at a mini-workshop at Universitat Pompeu Fabra, hosted by Prof. Gergely Neu
Improved Regret Bounds of (Multinomial) Logistic Bandits via Regret-to-Confidence-Set Conversion
One paper accepted to AISTATS 2024!
Improved Regret Bounds of (Multinomial) Logistic Bandits via Regret-to-Confidence-Set Conversion
One paper accepted to ICLR 2024!
Querying Easily Flip-flopped Samples for Deep Active Learning
2023
Our OPODIS 2023 paper has received best student paper award!!
Flooding with Absorption: An Efficient Protocol for Heterogeneous Bandits over Complex Networks
Our preprint on improved confidence set construction for (multinomial) logistic bandits now available on arXiv!
Improved Regret Bounds of (Multinomial) Logistic Bandits via Regret-to-Confidence-Set Conversion
One paper accepted to OPODIS 2023!
Flooding with Absorption: An Efficient Protocol for Heterogeneous Bandits over Complex Networks
One paper accepted to NeurIPS 2023 Workshop on Mathematics of Modern Machine Learning (M3L) as an oral presentation!
Large Catapults in Momentum Gradient Descent with Warmup: An Empirical Study
Received NeurIPS 2023 Scholar Award!
Free registration and free accomodation!
One paper accepted to NeurIPS 2023!
Fair Streaming Principal Component Analysis: Statistical and Algorithmic Viewpoint
Our arXiv paper on collaborative bandits over a network has been updated!
Flooding with Absorption: An Efficient Protocol for Heterogeneous Bandits over Complex Networks
Our preprint on multi-agent heterogeneous bandits over a communication network now available on arXiv!
Communication-Efficient Collaborative Heterogeneous Bandits in Networks
Best oral presentation for KSC 2022 + invitation to submit to KTCP
Preliminary Empirical Analyses of Clustering in Block MDPs
One paper accepted to AISTATS 2023!
Nearly Optimal Latent State Decoding in Block MDPs
2022
I’ve successfully defended my MSc thesis!
Near-Optimal Clustering in Block Markov Decision Processes
I’m heading to Stockholm to attend the Nobel Prize Lectures!
The Way to Stockholm, Korea Foundation of Advanced Studies (KFAS)
One paper accepted to KSC 2022!
Preliminary Empirical Analyses of Clustering in Block MDPs
Our preprint on theoretical analysis of block MDP now available on arXiv!
Nearly Optimal Latent State Decoding in Block MDPs
One paper accepted to CKAIA 2022 + selected as one of the best papers!
Near-Optimal Clustering in Block MDPs with Implications on Reward-Free RL
One paper accepted to KCC 2022!
A Statistical Analysis of Stochastic Gradient Noises for GNNs
2021
One paper accepted to AAAI 2022!
Fast and Efficient MMD-based Fair PCA via Optimization over Stiefel Manifold
One paper accepted to JKAIA 2021 + selected as one of the best papers!
MMD-based Fair PCA via Manifold Optimization
One paper accepted to SSBSE 2021!
Preliminary Evaluation of SWAY in Permutation Decision Space via a Novel Euclidean Embedding