News |

Invited talk at Chung-Ang University

Wed, 20 May 2026 00:00:00 +0000

I’ll be giving a talk at the Chung-Ang University, hosted by presenting my recent work (Provably Efficient Regularized Online RLHF with Generalized Bilinear Preferences).

One paper accepted to NeurIPS 2025! Congrats Woosung!

Thu, 18 Sep 2025 00:00:00 +0000

One paper (AdaSTaR: Adaptive Data Sampling for Training Self-Taught Reasoners) is accepted to NeurIPS 2025! This is joint work with Woosung Koh (who led the entire project and led all the experiments!) (Yonsei Economics), Wonbeen Oh, Jaein Jang, MinHyung Lee, Hyeongjin Kim, Ah Yeon Kim (his collaborators at Yonsei Economics), Joonkee Kim, Taehyeon Kim (LG AI Research), and Se-Young Yun (KAIST AI).

Woosung will be attending in person. Catch him at San Diego this December!

I gave an invited talk (virtual) at the Reading Group of Prof. Ilija Bogunovic of UCL!

Thu, 19 Jun 2025 00:00:00 +0000

Today, I gave an invited talk (virtual) at the Reading Group of Prof. Ilija Bogunovic of UCL. Thanks to Prof. Bogunovic and Dr. Sangwoong Yoon for hosting me :)

I have been chosen as one of the best reviewers for AISTATS 2025

Tue, 22 Apr 2025 00:00:00 +0000

I have been chosen as one of the best reviewers for AISTATS 2025! This is my first time receiving such an award, and I will take this as an encouragement to continue contributing thoughtfully to the research community. I’m grateful to the program committee for the recognition, and I look forward to supporting future conferences with the same care and dedication.

One paper accepted to ICLR 2025 DeLTa Workshop! Congrats Kunwoo!

Fri, 07 Mar 2025 00:00:00 +0000

One paper (Probability-Flow ODE in Infinite-Dimensional Function Spaces) is accepted to ICLR 2025 DeLTa Workshop! This is joint work with Kunwoo Na (who led the entire project and did all the experiments!) (SNU Chem Edu & Math), Se-Young Yun (KAIST AI), and Sungbin Lim (Korea Univ. Stat.).

One paper accepted to ICLR 2025! Congrats Woosung!

Thu, 23 Jan 2025 00:00:00 +0000

One paper (FlickerFusion: Intra-trajectory Domain Generalizing Multi-agent Reinforcement Learning) is accepted to ICLR 2025! This is joint work with Woosung Koh (who led the entire project and did all the experiments!) (Yonsei Economics), Wonbeen Oh, Siyeol Kim, Suhin Shin, Hyeongjin Kim, Jaein Jang (his collaborators at Yonsei Economics), and Se-Young Yun (KAIST AI).

Woosung will be attending in person. Catch him at Singapore!

I'll be spending my summer of 2025 as a research scientist intern at Adobe Research, San Jose!

Tue, 24 Dec 2024 00:00:00 +0000

I am thrilled to share that I will join Adobe Research (San Jose) as a summer research intern, working with Dr. Branislav “Brano” Kveton on active learning, bandits, RL, LLM, and more!!

I’ll be in San Jose from May to Aug of 2025. Feel free to hit me up if you are in the area!

I have been elected as the lab representative of the OSI Lab!

Fri, 29 Nov 2024 00:00:00 +0000

I have been elected as the next lab representative of the OSI Lab! I will be serving from 2025.01.01. to 2025.12.31., and will do my best!

I gave an invited talk at Hyperconnect, hosted by Dr. Gihun Lee!

Wed, 30 Oct 2024 00:00:00 +0000

Today I visited Hyperconnect (host: Dr. Gihun Lee) and gave an invited talk, “Bandits 101: A Maximally Non-technical Tutorial”.

One paper accepted to NeurIPS 2024 Workshop on Open-World Agents (OWA)!

Fri, 11 Oct 2024 00:00:00 +0000

One paper (FlickerFusion: Intra-trajectory Domain Generalizing Multi-Agent RL) is accepted to NeurIPS 2024 Workshop on Open-World Agents (OWA)! This is led by the wonderful undergraduate intern Woosung “Reiss” Koh (Yonsei Econ) and his collaboraotors at Yonsei University (Wonbeen Oh, Siyeol Kim, Suhin Shin, Hyeongjin Kim, Jaein Jang), with me as the mentor and my advisor Se-Young Yun (KAIST AI).

I’ll be attending the workshop and presenting in person. See you all at Vancouver, Canada!

One paper accepted to NeurIPS 2024!

Thu, 26 Sep 2024 00:00:00 +0000

One paper (A Unified Confidence Sequence for Generalized Linear Models, with Applications to Bandits) is accepted to NeurIPS 2024! This is joint work with my advisor Se-Young Yun (KAIST AI), and Kwang-Sung Jun (Univ. of Arizona CS).

I’ll be attending in person. See you all at Vancouver, Canada!

Two papers accepted to CKAIA 2024 + one is selected as one of the best papers!

Tue, 30 Jul 2024 00:00:00 +0000

Two papers (A Unified Confidence Sequence for Generalized Linear Models, with Applications to Bandits, Gradient Descent with Polyak’s Momentum Finds Flatter Minima via Large Catapults) are accepted to CKAIA 2024.

The first paper has been selected as one of the best papers!!

The first paper is joint work with Se-Young Yun (KAIST AI) and Kwang-Sung Jun (Univ. of Arizona CS).
The second paper is joint work with the wonderful undergradudate intern Prin Phunyaphibarn (KAIST Math, equal contributions), my advisor Chulhee Yun (KAIST AI), and collaborators Bohan Wang (USTC) and Huishuai Zhang (Peking University, previously at Microsoft Research Asia - Theory Centre).

I'll be giving a talk at the DeLTA Seminar in Copenhagen, Denmark.

Sun, 30 Jun 2024 00:00:00 +0000

I’ll be visiting ’s group on July 1st and giving a talk at the .

Catch you all in Copenhagen, Denmark!

I'll be spending the next two weeks in Stockholm, attending Stochastic Networks Conference 2024 and visiting KTH!

Sun, 30 Jun 2024 00:00:00 +0000

I’ll be in Stockholm for the next two weeks (07.02 - 07.14).

For the first week (07.02 - 07.05), I’ll be attending the . Also, as part of the Learning in Networks - Structure, Dynamics, and Control, I’ll be giving a talk about my AISTATS 2023 paper (Nearly Optimal Latent State Decoding in Block MDPs) on 07.04.

For the second week (07.06 - 07.14), I’ll be visiting Prof. Alexandre Proutiere as a visiting student and work on problems related to mixture of Markov chains.

I have successfully organized the 1st Korean AI Theory Community Workshop (Bandits)

Thu, 20 Jun 2024 00:00:00 +0000

I have successfully organized the 1st Korean AI Theory Community Workshop (Bandits). Refer to the for more details.

A total of 33 Korean researchers working on bandits attended, including 6 speakers. Thanks to everyone!

Two papers accepted to two ICML workshops, one as oral!

Wed, 19 Jun 2024 00:00:00 +0000

One paper (Gradient Descent with Polyak’s Momentum Finds Flatter Minima via Large Catapults) is accepted to ICML 2024 Workshop: 2nd Workshop on High-dimensional Learning Dynamics (HiLD): The Emergence of Structure and Reasoning. This is joint work with the wonderful undergradudate intern Prin Phunyaphibarn (KAIST Math, equal contributions), my advisor Chulhee Yun (KAIST AI), and collaborators Bohan Wang (USTC) and Huishuai Zhang (Peking University, previously at Microsoft Research Asia - Theory Centre).

Also, another paper (A Unified Confidence Sequence for Generalized Linear Models, with Applications to Bandits) is accepted to ICML 2024 Workshop: Aligning Reinforcement Learning Experimentalists and Theorists (ARLET) as an oral presentation! This is joint work with my advisor Se-Young Yun (KAIST AI) and Kwang-Sung Jun (Univ. of Arizona CS).

My coauthors (Chulhee, Kwang-Sung) will be attending the conference in-person. Catch them if you can in Vienna!

I'll be giving a talk at a mini-workshop at Universitat Pompeu Fabra, hosted by Prof. Gergely Neu

Mon, 06 May 2024 00:00:00 +0000

After AISTATS 2024, I’ll be at Universitat Pompeu Fabra to give a talk at a mini-workshop on RL theory, hosted by . I’ll be presenting my AISTATS 2024 paper (Improved Regret Bounds of (Multinomial) Logistic Bandits via Regret-to-Confidence-Set Conversion).

I will be attending the "Summer School on Optimal Transport, Stochastic Analysis and Applications to Machine Learning" at Daejeon, South Korea!

Sat, 20 Jan 2024 00:00:00 +0000

From 06.03 to 06.07, I will be attending the “Summer School on Optimal Transport, Stochastic Analysis and Applications to Machine Learning”! On Thursday (06.06), I will be presenting my paper (Nearly Optimal Latent State Decoding in Block MDPs) at a lightning session.

I’ll be attending in person. See you all at Daejeon, South Korea!

One paper accepted to AISTATS 2024!

Sat, 20 Jan 2024 00:00:00 +0000

One paper (Improved Regret Bounds of (Multinomial) Logistic Bandits via Regret-to-Confidence-Set Conversion) is accepted to AISTATS 2024! This is joint work with my advisor Se-Young Yun (KAIST AI) and Kwang-Sung Jun (Univ. of Arizona CS).

I’ll be attending in person. See you all at Valencia, Spain!

One paper accepted to ICLR 2024!

Tue, 16 Jan 2024 00:00:00 +0000

One paper (Querying Easily Flip-flopped Samples for Deep Active Learning) is accepted to ICLR 2024! This is joint work with Seong Jin Cho (who led the entire project and did all the experiments!) (KAIST EE), Gwangsu Kim (JBNU Statistics), Jinwoo Shin (KAIST AI), and Chang D. Yoo (KAIST EE).

I’ll be attending in person. See you all at Vienna, Austria!

Our OPODIS 2023 paper has received best student paper award!!

Tue, 21 Nov 2023 00:00:00 +0000

Our OPODIS 2023 paper (Flooding with Absorption: An Efficient Protocol for Heterogeneous Bandits over Complex Networks) has received the best student paper award! Again, this is joint work with Laura Schmid and Se-Young Yun (KAIST AI).

Laura will be attending the conference in person. Catch her if you can at Tokyo!

Our preprint on improved confidence set construction for (multinomial) logistic bandits now available on arXiv!

Tue, 31 Oct 2023 00:00:00 +0000

Our preprint Improved Regret Bounds of (Multinomial) Logistic Bandits via Regret-to-Confidence-Set Conversion is now available on arXiv! ( ) This is joint work with Kwang-Sung Jun (Univ. of Arizona CS) and Se-Young Yun (KAIST AI).

One paper accepted to OPODIS 2023!

Mon, 30 Oct 2023 00:00:00 +0000

One paper (Flooding with Absorption: An Efficient Protocol for Heterogeneous Bandits over Complex Networks) is accepted to OPODIS 2023! This is joint work with Laura Schmid and Se-Young Yun (KAIST AI).

Laura will be attending the conference in person. Catch her if you can at Tokyo!

One paper accepted to NeurIPS 2023 Workshop on Mathematics of Modern Machine Learning (M3L) as an oral presentation!

Sun, 29 Oct 2023 00:00:00 +0000

One paper (Large Catapults in Momentum Gradient Descent with Warmup: An Empirical Study) is accepted to NeurIPS 2023 Workshop on Mathematics of Modern Machine Learning (M3L) as an oral presentation! This is joint work with the wonderful undergradudate intern Prin Phunyaphibarn (KAIST Math, equal contributions), my advisor Chulhee Yun (KAIST AI), and collaborators Bohan Wang (USTC) and Huishuai Zhang (Microsoft Research Asia - Theory Centre).

I’ll be attending and presenting in person. See you all at New Orleans, USA!

Received NeurIPS 2023 Scholar Award!

Sat, 21 Oct 2023 00:00:00 +0000

I’m delighted to share that I received the NeurIPS 2023 Scholar Award! Registration and 7-day stay at a nearby hotel will be fully supported!

One paper accepted to NeurIPS 2023!

Fri, 22 Sep 2023 00:00:00 +0000

One paper (Fair Streaming Principal Component Analysis: Statistical and Algorithmic Viewpoint) is accepted to NeurIPS 2023! This is joint work with my advisors Se-Young Yun and Chulhee Yun (KAIST AI), and my wonderful collaborator Hanseul Cho (KAIST AI).

I’ll be attending in person. See you all at New Orleans, USA!

Our arXiv paper on collaborative bandits over a network has been updated!

Fri, 22 Sep 2023 00:00:00 +0000

We have updated our arXiv paper on collaborative bandits over a network, with the new title Flooding with Absorption: An Efficient Protocol for Heterogeneous Bandits over Complex Networks as well as several significant changes in the overall organization and experiments.

Two papers accepted to CKAIA 2023!

Thu, 13 Jul 2023 00:00:00 +0000

Two papers (Fair Streaming Principal Component Analysis: Statistical and Algorithmic Viewpoint, Communication-Efficient Collaborative Heterogeneous Bandits in Networks) is accepted to CKAIA 2023! These are joint works with Hanseul Cho, Chulhee Yun, Laura Schmid, and Se-Young Yun (KAIST AI).

These are short versions of our submitted works of the same titles.

Our preprint on multi-agent heterogeneous bandits over a communication network now available on arXiv!

Fri, 10 Mar 2023 00:00:00 +0000

Our preprint Communication-Efficient Collaborative Heterogeneous Bandits in Networks is now available on arXiv! ( ) This is joint work with Laura Schmid and Se-Young Yun (KAIST AI).

This is the full version of our MobiHoc 2023 submission of the same title.

Best oral presentation for KSC 2022 + invitation to submit to KTCP

Wed, 08 Feb 2023 00:00:00 +0000

Our KSC 2022 paper (Preliminary Empirical Analyses of Clustering in Block MDPs) has been selected as one of the best oral presentataions! Additionally, we have been invited to submit an extended version of our conference paper to the KIISE Transactions on Computing Practices (KTCP)!

This is joint work with my advisor Se-Young Yun (KAIST AI).

One invited paper and one poster accepted for presentation at the INFORMS APS 2023!

Fri, 20 Jan 2023 00:00:00 +0000

Our recent AISTATS paper, Nearly Optimal Latent State Decoding in Block MDPs, has been invited to be presented at the invited session “Stochastic learning in structured systems” at INFORMS APS 2023 (chair: Prof. Jaron Sanders). Also, our recent preprint, Communication-Efficient Collaborative Heterogeneous Bandits in Networks has been selected to be presented as a poster as well!

I’ll be attending in person. See you all at Nancy, France!

One paper accepted to AISTATS 2023!

Fri, 20 Jan 2023 00:00:00 +0000

One paper (Nearly Optimal Latent State Decoding in Block MDPs) is accepted to AISTATS 2023! This is joint work with my advisor Se-Young Yun (KAIST AI), and Yassir Jedra and Alexandre Proutiére (KTH EECS).

I’ll be attending in person. See you all at Valencia, Spain!

I've successfully defended my MSc thesis!

Thu, 15 Dec 2022 00:00:00 +0000

I’ve successfully defended my MSc thesis, titled Near-Optimal Clustering in Block Markov Decision Processes! Special thanks to the thesis committee: Se-Young Yun, Chulhee Yun, and Kee-Eung Kim (KAIST AI).

Thesis as well as presentation file coming soon!

I'm heading to Stockholm to attend the Nobel Prize Lectures!

Tue, 06 Dec 2022 00:00:00 +0000

As part of the program The Way to Stockholm, sponsored by the Korea Foundation of Advanced Studies (KFAS), I’ll be in Stockholm from 12/06 to 12/12 to attend the Nobel Prize Lectures, Nobel Prize Dialogue, and more! Along with seven other colleagues, I was selected out of 80~90 applicants.

One paper accepted to KSC 2022!

Mon, 21 Nov 2022 00:00:00 +0000

One paper (Preliminary Empirical Analyses of Clustering in Block MDPs) is accepted to KSC 2022! This is joint work with Se-Young Yun (KAIST AI).

More details to come!

Our preprint on theoretical analysis of block MDP now available on arXiv!

Fri, 19 Aug 2022 00:00:00 +0000

Our preprint Nearly Optimal Latent State Decoding in Block MDPs is now available on arXiv! ( ) This is joint work with Yassir Jedra and Alexandre Proutiere (KTH EECS), and Se-Young Yun (KAIST AI).

This is the full version of our CKAIA 2022 paper Near-Optimal Clustering in Block MDPs with Implications on Reward-Free RL.

One paper accepted to CKAIA 2022 + selected as one of the best papers!

Thu, 28 Jul 2022 00:00:00 +0000

One paper (Near-Optimal Clustering in Block MDPs with Implications on Reward-Free RL) is accepted to CKAIA 2022! This is joint work with Yassir Jedra and Alexandre Proutiere (KTH DCS), and Se-Young Yun (KAIST AI).

This is a short version of our submitted preprint Nearly Optimal Latent State Decoding in Block MDPs.

One paper accepted to KCC 2022!

Sun, 29 May 2022 00:00:00 +0000

One paper (A Statistical Analysis of Stochastic Gradient Noises for GNNs) is accepted to KCC 2022! This is joint work with Minchan Jeong, Namgyu Ho, and Se-Young Yun (KAIST AI).

More details to come!

One paper accepted to AAAI 2022!

Wed, 01 Dec 2021 00:00:00 +0000

One paper (Fast and Efficient MMD-based Fair PCA via Optimization over Stiefel Manifold) is accepted to AAAI 2022! This is joint work with Gwangsu Kim and Chang D. Yoo (KAIST EE), Matt Olfat (UC Berkeley IEOR & Citadel), and Mark Hasegawa-Johnson (UIUC EE).

More details to come!

Update (12.08): AAAI 2022 goes full virtual…

One paper accepted to JKAIA 2021 + selected as one of the best papers!

Mon, 01 Nov 2021 00:00:00 +0000

One paper (MMD-based Fair PCA via Manifold Optimization) is accepted to JKAIA 2021! This is joint work with Gwangsu Kim and Chang D. Yoo (KAIST EE), Matt Olfat (UC Berkeley IEOR & Citadel), and Mark Hasegawa-Johnson (UIUC EE).

This is a short version of our preprint Fast and Efficient MMD-based Fair PCA via Optimization over Stiefel Manifold.

One paper accepted to SSBSE 2021!

Sun, 11 Jul 2021 00:00:00 +0000

One paper (Preliminary Evaluation of SWAY in Permutation Decision Space via a Novel Euclidean Embedding) is accepted to SSBSE 2021! This is joint work with Chani Jung, Yoo Hwa Park, Dongmin Lee, Juyeon Yoon, and Shin Yoo (KAIST CS).

News |

Invited talk at Chung-Ang University

One paper accepted to NeurIPS 2025! Congrats Woosung!

I gave an invited talk (virtual) at the Reading Group of Prof. Ilija Bogunovic of UCL!

I have been chosen as one of the *best reviewers* for AISTATS 2025

One paper accepted to ICLR 2025 DeLTa Workshop! Congrats Kunwoo!

One paper accepted to ICLR 2025! Congrats Woosung!

I'll be spending my summer of 2025 as a research scientist intern at Adobe Research, San Jose!

I have been elected as the lab representative of the OSI Lab!

I gave an invited talk at Hyperconnect, hosted by Dr. Gihun Lee!

One paper accepted to NeurIPS 2024 Workshop on Open-World Agents (OWA)!

One paper accepted to NeurIPS 2024!

Two papers accepted to CKAIA 2024 + one is selected as one of the best papers!

I'll be giving a talk at the DeLTA Seminar in Copenhagen, Denmark.

I'll be spending the next two weeks in Stockholm, attending Stochastic Networks Conference 2024 and visiting KTH!

I have successfully organized the 1st Korean AI Theory Community Workshop (Bandits)

Two papers accepted to two ICML workshops, one as **oral**!

I'll be giving a talk at a mini-workshop at Universitat Pompeu Fabra, hosted by Prof. Gergely Neu

I will be attending the "Summer School on Optimal Transport, Stochastic Analysis and Applications to Machine Learning" at Daejeon, South Korea!

One paper accepted to AISTATS 2024!

One paper accepted to ICLR 2024!

Our OPODIS 2023 paper has received best student paper award!!

Our preprint on improved confidence set construction for (multinomial) logistic bandits now available on arXiv!

One paper accepted to OPODIS 2023!

One paper accepted to NeurIPS 2023 Workshop on Mathematics of Modern Machine Learning (M3L) as an *oral presentation*!

Received NeurIPS 2023 Scholar Award!

One paper accepted to NeurIPS 2023!

Our arXiv paper on collaborative bandits over a network has been updated!

Two papers accepted to CKAIA 2023!

Our preprint on multi-agent heterogeneous bandits over a communication network now available on arXiv!

Best oral presentation for KSC 2022 + invitation to submit to KTCP

One invited paper and one poster accepted for presentation at the INFORMS APS 2023!

One paper accepted to AISTATS 2023!

I've successfully defended my MSc thesis!

I'm heading to Stockholm to attend the Nobel Prize Lectures!

One paper accepted to KSC 2022!

Our preprint on theoretical analysis of block MDP now available on arXiv!

One paper accepted to CKAIA 2022 + selected as one of the best papers!

One paper accepted to KCC 2022!

One paper accepted to AAAI 2022!

One paper accepted to JKAIA 2021 + selected as one of the best papers!

One paper accepted to SSBSE 2021!

I have been chosen as one of the best reviewers for AISTATS 2025

Two papers accepted to two ICML workshops, one as oral!

One paper accepted to NeurIPS 2023 Workshop on Mathematics of Modern Machine Learning (M3L) as an oral presentation!