News

Aug 2025: Three papers (CLEANMOL, MT-MOL, CORE-PO) got accepted to EMNLP 2025 (1 Main, 2 Findings).

Jul 2025: I've started my internship at Valence Labs — looking forward to connecting in Montreal!

May 2025: A paper (MSR) got accepted to ACL 2025 (Main).

Dec 2024: HGGT got honored to be the winner at Qualcomm Innovation Fellowship.

Sep 2024: A paper (PBP-GFN) got accepted to NeurIPS 2024.

Apr 2024: A paper (HNeR-S) got accepted to ICML 2024.

Apr 2024: I became a recipient of the Presidential Science Scholarship.

Jan 2024: HGGT won the Bronze prize in Samsung Humantech Paper Awards.

Jan 2024: Two papers (HGGT, GEEL) got accepted to ICLR 2024.

Education

  1. KAIST, Graduate school of AI, Ph.D.

    Mar. 2025 - Present

    Supervised by Sungsoo Ahn

  2. POSTECH, Graduate school of AI, M.S.

    Sep. 2022 - Feb. 2025

    Supervised by Sungsoo Ahn

    A member of Machine Learning Lab

  3. RWTH, Computer sciences, exchange student

    Mar. 2019 - Feb. 2020
  4. POSTECH, Industrial & management enginerring, B.S

    Mar. 2015 - Aug. 2020

Work Experience

  1. Valence Labs (Recursion pharmaceuticals)

    Jul. 2025 - Dec. 2025

    Research Intern

    Conducted research on constructing LLM agent for reasoning and developing reasoning models for virtual cells

  2. Netmarble

    Jul. 2018 - Aug. 2018

    Intern, AI research center

    Project: User Activity Sequence Representation Learning and Classification using LSTM

  3. Joycity

    Jun. 2017 - Aug. 2017

    Intern, BT Team

Publications

|
Boltz

Boltz is a Strong Baseline for Atom-level Representation Learning

Hyosoon Jang, Hyunjin Seo, Yunhui Jang, Seonghyun Park, Sungsoo Ahn

Under review

INDIBATOR

INDIBATOR: Diverse and Fact-Grounded Individuality for Multi-Agent Debate in Molecular Discovery

Yunhui Jang, Seonghyun Park, Jaehyung Kim, Sungsoo Ahn

Under review

Diverse Molecules

Can LLMs Generate Diverse Molecules? Towards Alignment with Structural Diversity

Hyosoon Jang, Yunhui Jang, Minsu Kim, Jinkyoo Park, Sungsoo Ahn

Under review

CLEANMOL

Improving Chemical Understanding of LLMs via SMILES parsing

Yunhui Jang, Jaehyung Kim, Sungsoo Ahn

EMNLP 2025 (Main)

CORE-PO

Self-Training Large Language Models with Confident Reasoning

Hyosoon Jang, Yunhui Jang, Sungjae Lee, Jungseul Ok, Sungsoo Ahn

EMNLP 2025 (Findings)

MT-MOL

MT-MOL: Multi Agent System with Tool-based Reasoning for Molecular Optimization

Hyomin Kim, Yunhui Jang, Sungsoo Ahn

EMNLP 2025 (Findings)

MSR

Structural Reasoning Improves Molecular Understanding of LLM

Yunhui Jang, Jaehyung Kim, Sungsoo Ahn

ACL 2025 (Main)

PBP-GFN

Pessimistic Backward Policy for GFlowNets

Hyosoon Jang, Yunhui Jang, Minsu Kim, Jinkyoo Park, Sungsoo Ahn

NeurIPS 2024

HNeR-S

Hybrid Neural Representations for Spherical Data

Hyomin Kim, Yunhui Jang, Jaeho Lee, Sungsoo Ahn

ICML 2024

GEEL

A Simple and Scalable Representation for Graph Generation

Yunhui Jang, Seul Lee, Sungsoo Ahn

ICLR 2024

HGGT

Hierarchical Graph Generation with K2-trees

Yunhui Jang, Dongwoo Kim, Sungsoo Ahn

ICLR 2024

Honors and Awards

  1. Winner, Qualcomm Innovation Fellowship Korea, 2024

  2. Recipient, Preseidential Sceince Scholarship for Graduate Students, 2024 - Present

  3. Recipient, ICLR Travel Awards, 2024

  4. Bronze Prize, Samsung Humantech Paper Awards, 2023

  5. Recipient, POSTECHIAN Fellowship, 2022-2023

  6. Recipient, Chun Sin-il Sejung Group Fellowship, 2020-2022

  7. Cum Laude Honor, POSTECH, 2020

  8. Recipient, Presidential Science Scholarship for Undergraduate Students, 2015-2020

  9. Recipient, RWTH Aachen University Exchange Scholarship, 2019

  10. Recipient, Realize Your Dream Scholarship by Blizzard Entertainment, 2018

Academic Services

Reviewer: NeurIPS 2023-2025, ICLR 2024-2026, ICML 2024-2025, AAAI 2025-2026