About me
I am a Ph.D. candidate in the Graduate School of Artificial Intelligence at Pohang University of Science and Technology (POSTECH), advised by Prof. Jungseul Ok, Prof. Yunsu Kim, and Prof. Gary Geunbae Lee. Currently, I am a visiting researcher at Ludwig Maximilian University of Munich (LMU Munich), where I work with Prof. Hinrich Schütze. My research is supported by the Samsung Electronics Mobile eXperience (MX). Previously, I completed my B.S. in Software and Computer Engineering from Ajou University, with a micro in Artificial Intelligence.
My research interests lie in natural language processing, with a particular focus on text summarization, controllable text generation, and multilingual NLP. I am also interested in reinforcement learning, including multi-objective optimization, planning, and alignment.
I have also worked as a forklift driver, and served as a bus driver in the Auxiliary Police. In my free time, I enjoy combat sports, including weight lifting, MMA, BJJ, and grappling.
Feel free to contact me via email at ryusangwon@postech.ac.kr.
News 🗞️
[Mar, 2026] 👋 I have joined LMU Munich as a visiting researcher
[Jan, 2026] 🎉 One paper has been accepted at EACL 2026 (Findings)
[Sep, 2025] 🎉 One paper has been accepted at NLLP Workshop (EMNLP 2025)
[Jun, 2025] 🎊 I have been selected for the Samsung Electronics MX Scholarship
[May, 2025] 🎉 One paper has been accepted at ACL 2025
[Jan, 2025] 🎉 Two papers have been accepted at NAACL 2025 (one Oral, one Findings)
[Sep, 2024] 🎉 One paper has been accepted at EMNLP 2024
[Jun, 2024] 🎉 One paper has been accepted at INTERSPEECH 2024 (Oral)
[May, 2024] 🎉 One paper has been accepted at ACL 2024
Publications 📖
Conferences (C) / Journals (J) / Workshops (W) / Preprints (P)
*: Equal contributions
[P3] Adaptive Planning for Multi-Attribute Controllable Summarization with Monte Carlo Tree Search
Sangwon Ryu, Heejin Do, Yunsu Kim, Gary Geunbae Lee, Jungseul Ok
Preprint
[P2] Teach-to-Reason with Scoring: Rationale-Driven Automated Multi-Trait Essay Scoring
Heejin Do, Sangwon Ryu, Gary Geunbae Lee
Preprint
[P1] Ontology-Free General-Domain Knowledge Graph-to-Text Generation Dataset Synthesis using Large Language Model
Daehui Kim, Deokhyung Kang, Sangwon Ryu, Gary Geunbae Lee
Preprint
[C7] Exploring Iterative Controllable Summarization for Large Language Models
Sangwon Ryu, Heejin Do, Daehui Kim, Hwanjo Yu, Dongwoo Kim, Yunsu Kim, Gary Geunbae Lee, Jungseul Ok
EACL, Findings, 2026
[W1] GuRE:Generative Query REwriter for Legal Passage Retrieval
Daehui Kim, Deokhyung Kang, Jonghwi Kim, Sangwon Ryu, Gary Geunbae Lee
NLLP at EMNLP, 2025
[C6] Multi-facet Blending for Faceted Query-by-Example Retrieval
Heejin Do*, Sangwon Ryu*, Jonghwi Kim, Gary Geunbae Lee
ACL, 2025
[C5] Towards Prompt Generalization: Grammar-aware Cross-Prompt Automated Essay Scoring
Heejin Do, Taehee Park, Sangwon Ryu, Gary Geunbae Lee
NAACL, Short, Findings, 2025
[C4] Revisiting Early Detection of Sexual Predators via Turn-level Optimization
Jinmyeong An, Sangwon Ryu, Heejin Do, Yunsu Kim, Jungseul Ok, Gary Geunbae Lee
NAACL, 2025 (Oral presentation)
[C3] Autoregressive Multi-trait Essay Scoring via Reinforcement Learning with Scoring-aware Multiple Rewards
Heejin Do, Sangwon Ryu, Gary Geunbae Lee
EMNLP, 2024
[C2] Key-Element-Informed sLLM Tuning for Document Summarization
Sangwon Ryu*, Heejin Do*, Yunsu Kim, Gary Geunbae Lee, Jungseul Ok
INTERSPEECH, 2024 (Oral presentation)
[C1] Multi-Dimensional Optimization for Text Summarization via Reinforcement Learning
Sangwon Ryu*, Heejin Do*, Yunsu Kim, Gary Geunbae Lee, Jungseul Ok
ACL, 2024