Byeongchan Kim

Byeongchan Kim is a Ph.D. candidate in the Graduate School of Data Science at Seoul National University, advised by Prof. Min-hwan Oh. He received his M.S. from the Graduate School of Data Science at Seoul National University, also under Prof. Oh's supervision, and his B.A. in Mathematics and Statistics from Sungkyunkwan University. His research focuses on offline reinforcement learning (RL), including model-free, model-based, goal-conditioned, and diffusion-based approaches, as well as kernel methods, optimization, and their applications.

Email / Google Scholar / Github

Recent News

Oct 2026	Recognized as a Top Reviewer at NeurIPS 2026
Sep 2026	2 papers accepted at NeurIPS 2026
Sep 2026	Received the YOULCHON AI Star Scholarship
May 2026	1 paper accepted at ICML 2026
Jan 2026	1 paper accepted at ICLR 2026
Sep 2025	1 paper accepted at NeurIPS 2025
Dec 2023	Received the Hanheum Ok Scholarship
Aug 2023	Received the NRF Ph.D. Fellowship
Apr 2023	1 paper accepted at ICML 2023

Publications
(*Equal contribution)

	RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings Byeongchan Kim, Arijit Sehanobish, Avinava Dubey, Min-hwan Oh, Krzysztof Choromanski NeurIPS, 2026 paper / code / project page
	Multi-Step Likelihood-Ratio Correction for Reinforcement Learning with Verifiable Rewards Deokgyu Yoon, Hyungkyu Kang, Joongkyu Lee, Byeongchan Kim, Gyungin Shin, Sungrae Park, Min-hwan Oh NeurIPS*, 2026 paper / code
	Latent Representation Alignment for Offline Goal-Conditioned Reinforcement Learning Hyungkyu Kang, Byeongchan Kim, Min-hwan Oh ICML, 2026 paper / code / project page
	Peng's Q(λ) for Conservative Value Estimation in Offline Reinforcement Learning Byeongchan Kim, Min-hwan Oh ICLR, 2026 paper / code
	EUGens: Efficient, Unified and General Dense Layers Sang Min Kim, Byeongchan Kim, Arijit Sehanobish, Somnath Basu Roy Chowdhury, Rahul Kidambi, Dongseok Shim, Avinava Dubey, Snigdha Chaturvedi, Min-hwan Oh, Krzysztof Choromanski* NeurIPS, 2025 paper / code
	Model-based Offline Reinforcement Learning with Count-based Conservatism Byeongchan Kim, Min-hwan Oh ICML, 2023 (M.S. Thesis) paper / code

This template is a modification to Jon Barron's website. Find the source code to my version here. Feel free to clone it for your own use while attributing the original author Jon Barron.