Seongwoong Shim

✉: ssw030830@korea.ac.kr 🎓: Google Scholar 💼: LinkedIn

I'm a Ph.D. candidate in the Decision Making Lab at Korea University, advised by Prof. Byung-Jun Lee.

Research Interests

I push the boundaries of intelligent systems by leveraging reinforcement learning to enhance both the performance and efficiency of modern foundation models.

Enhancing Foundation Models: Language Models [C6], Multimodal Models [C5], Diffusion Models [C2]

Reinforcement Learning: Offline Learning [C1, C4], Skill Discovery [C3]

Selected Publications

(*: equal contribution / P: preprint / C: conference / J: journal / w: workshop)

[C6] Beyond RAG vs. Long-Context: Learning Distraction-Aware Retrieval for Efficient Knowledge Grounding

Seong-Woong Shim*, Myunsoo Kim*, Jae Hyeon Cho, Byung-Jun Lee
International Conference on Learning Representations (ICLR 2026)

[C5] FALCON: False-Negative Aware Learning of Contrastive Negatives in Vision-Language Alignment

Myunsoo Kim*, Seong-Woong Shim*, Byung-Jun Lee
Conference on Computer Vision and Pattern Recognition (CVPR 2026)

Other Publications

[C4] Prior-Guided Diffusion Planning for Offline Reinforcement Learning

Donghyeon Ki, JunHyeok Oh, Seongwoong Shim, Byung-Jun Lee
Neural Information Processing Systems (NeurIPS 2025)

[C3] NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic Demonstrations

Myunsoo Kim*, Hayeong Lee*, Seong-Woong Shim, JunHo Seo, Byung-Jun Lee
International Conference on Machine Learning (ICML 2025)

[C2] Adaptive Non-uniform Timestep Sampling for Accelerating Diffusion Model Training

Myunsoo Kim*, Donghyeon Ki*, Seong-Woong Shim, Byung-Jun Lee
Conference on Computer Vision and Pattern Recognition (CVPR 2025)

[C1] Offline Imitation Learning by Controlling the Effective Planning Horizon

Hee-Jun Ahn*, Seongwoong Shim*, Byung-Jun Lee
International Conference on Pattern Recognition and Artificial Intelligenc (ICPRAI 2024)

Educations

Korea University, Integrated MS. & Ph.D. (Mar. 2022 - Present)

Department of Artificial Intelligence (GPA: 4.25/4.5)
Advisor: Prof. Byung-Jun Lee

Academic Credit Bank System, B.S. (Oct. 2020 - Feb. 2022)

Department of Computer Engineering (GPA: 4.46/4.5)

Academic Services

Teaching

TA, XAI613 Reinforcement Learning (Fall 2022)
TA, XAI503 Optimization Theory (Fall 2022)
TA, AA109 Probabilistic Graphical Models (Fall 2022)
TA, Advanced Language AI (LG CNS) (Spring-Fall 2022)

Conference Reviewer

Conference on Computer Vision and Pattern Recognition (CVPR) 2026