Hyeon Hwang

AI Researcher · Ph.D Student @ Korea University, DMIS Lab

HHHyeon Hwang

About

I am a Ph.D student (MS–Ph.D integrated) in Computer Science & Engineering at Korea University (DMIS Lab), advised by Prof. Jaewoo Kang. My research focuses on improving the scientific reasoning capabilities of large language models, spanning pre-training, post-training, and evaluation. I am particularly interested in efficient reasoning, achieving stronger reasoning at smaller model scale and lower inference cost.

Recently, I worked on LLM mid-training for biological capability at Trillion Labs and LLM post-training for scientific reasoning at SK Telecom.

News

2026.08
📣 Two papers accepted at EMNLP 2026 (1 Main, 1 Findings)
2026.08
🎤 Invited talk on TheBioCollection at the Multiomics Reading Group, Mila
2026.07
🎁 TheBioCollection released on arXiv
2026.05
🎁 Teaching LMs to Think in Code released on arXiv
2026.01
📣 A.X K1 Technical Report released on arXiv
2025.12
🏅 Three Excellence Awards at CureBench @ NeurIPS 2025
2025.08
📣 Paper accepted at EMNLP 2025 Findings
2025.07
🏆 1st place at ArchEHR-QA 2025 (BioNLP Workshop @ ACL 2025)
2025.06
🏆 1st place at MedHopQA (BioCreative IX) @ IJCAI 2025
2025.05
📣 Meerkat published in npj Digital Medicine
2025.05
📣 Paper accepted at ACL 2025
2025.01
📣 Paper accepted at NAACL 2025
2024.09
📣 Paper accepted at EMNLP 2024
2024.06
🏅 4th place at MEDIQA-CORR @ NAACL Clinical NLP 2024
2023.09
🏅 2nd place at BioASQ 11B

Publications

Low-Resource Reasoning
Enhancing Low-Resource Language Reasoning via High-Resource Language Feature Transfer
Minju Song, Hyeon Hwang, Junhyun Lee, Jaewoo Kang
EMNLP 2026 Findings
conference paper
Latent Block Insertion
Adaptive Latent Block Insertion via Online Reward Optimization
Yewon Cho, Hyeongsoon Hwang, Yein Park, Hyeon Hwang, Jaewoo Kang
EMNLP 2026 Main Conference
conference
TheBioCollection
TheBioCollection: Unified Pre-Training Scale LLM Corpus for Biology
Hyunjin Seo*, Hyeon Hwang*, Gyubok Lee, Jay Shin, Jimin Park, Taesoo Kim, Sanghoon Lee, Hongjoon Ahn, Sungjun Han, Sangwon Jung (*: equal contribution)
arXiv preprint, 2026
tech report paper
Think in Code
Teaching Language Models to Think in Code
Hyeon Hwang, Jiwoo Lee, Jaewoo Kang
arXiv preprint, 2026 · under review
preprint paper
A.X K1
A.X K1 Technical Report
SK Telecom
arXiv preprint, 2026
tech report paper
Principal Knowledge
Assessing LLM Reasoning Steps via Principal Knowledge Grounding
Hyeon Hwang, Yewon Cho, Chanwoong Yoon, Yein Park, Minju Song, Kyungjae Lee, Gangwoo Kim, Jaewoo Kang
Findings of EMNLP 2025
conference paper
OSP
Outlier-Safe Pre-Training for Robust 4-Bit Quantization of Large Language Models
Jungwoo Park, Taewhoo Lee, Chanwoong Yoon, Hyeon Hwang, Jaewoo Kang
ACL 2025
conference paper code
ArchEHR-QA
DMIS Lab at ArchEHR-QA 2025: Evidence-Grounded Answer Generation for EHR-based QA via a Multi-Agent Framework
Hyeon Hwang et al.
24th BioNLP Workshop @ ACL 2025 · 🏆 1st place
workshop paper
MedHopQA
DMIS Lab at MedHopQA-2025: Ensemble Multi-Retrieval Methodologies with Reasoning Language Model Decision
Jongmyung Jung, Hyeongsoon Hwang, Yein Park, Minju Song, Jaehoon Yoon, Hyeon Hwang, Sanghoon Lee, Jiwoong Sohn, Jaewoo Kang
BioCreative IX Challenge @ IJCAI 2025 · 🏆 1st place
workshop paper
Meerkat
Small Language Models Learn Enhanced Reasoning Skills from Medical Textbooks
Hyunjae Kim, Hyeon Hwang, Jiwoo Lee, Sihyeon Park, Dain Kim, Taewhoo Lee, Chanwoong Yoon, Jiwoong Sohn, Donghee Choi, Jaewoo Kang
npj Digital Medicine 8, 240 (2025) · IF 15.1
journal paper hugging face
RAG²
Rationale-Guided Retrieval Augmented Generation for Medical Question Answering
Jiwoong Sohn, Yein Park, Chanwoong Yoon, Sihyeon Park, Hyeon Hwang, Mujeen Sung, Hyunjae Kim, Jaewoo Kang
NAACL 2025
conference paper code
CompAct
CompAct: Compressing Retrieved Documents Actively for Question Answering
Chanwoong Yoon, Taewhoo Lee, Hyeon Hwang, Minbyul Jeong, Jaewoo Kang
EMNLP 2024
conference paper code
Medical Error Correction
Exploring the Reasoning Capabilities of Small Language Models in Medical Error Correction
Hyeon Hwang, Taewhoo Lee, Hyunjae Kim, Jaewoo Kang
6th Clinical NLP Workshop @ NAACL 2024
workshop paper
OLAPH
OLAPH: Improving Factuality in Biomedical Long-form Question Answering
Minbyul Jeong, Hyeon Hwang, Chanwoong Yoon, Taewhoo Lee, Jaewoo Kang
arXiv preprint, 2024 · under review
preprint paper code
BioASQ
Exploring Approaches to Answer Biomedical Questions: From Pre-processing to GPT-4
Hyunjae Kim, Hyeon Hwang, Chaeeun Lee, Minju Seo, Wonjin Yoon, Jaewoo Kang
CLEF 2023 · 🥈 BioASQ 11B 2nd place
workshop paper

Experience

Trillion Labs · Research Intern
LLM mid-training to enhance biological capability (TheBioCollection)
2026.04 – 2026.07
SK Telecom · Research Intern
LLM post-training to enhance scientific reasoning (A.X K1)
2025.10 – 2025.12
NVIDIA DLI University Ambassador
Certified Instructor — NVIDIA DLI “Efficient LLM Customization”
2025.04 – present

Education

Korea University
Ph.D (MS Integrated) Student, Computer Science & Engineering · Advisor: Prof. Jaewoo Kang
2023.03 – present
Sogang University
B.S in Life Science & Artificial Intelligence (Double Major)
2016.03 – 2022.08

Awards & Honors

excellence
CureBench @ NeurIPS 2025
Three Excellence Awards among the four evaluation categories
2025
🏆 1st
ArchEHR-QA 2025 @ ACL BioNLP Workshop [paper]
Answering patient questions using clinical evidence from EHRs
2025
🏆 1st
MedHopQA (BioCreative IX) @ IJCAI 2025 [paper]
Complex multi-hop medical question answering
2025
4th
MEDIQA-CORR @ NAACL Clinical NLP 2024 [paper]
Medical error correction in clinical notes
2024
🥈 2nd
BioASQ 11B [paper]
Large-scale biomedical semantic indexing and question answering
2023
🏆 1st
SKT FlyAI Challenger
AI service development hackathon hosted by SK Telecom
2022

Academic Activities

Invited Talk — Multiomics Reading Group at Mila
“TheBioCollection: Unified Pre-Training Scale LLM Corpus for Biology”
2026.08.19
Conference Reviewer
ACL 2026, EMNLP 2026, NeurIPS 2026
2026