About

I’m a first-year Ph.D. student in the Graduate School of AI at KAIST, advised by Prof. Seongjoon Oh in the STAI Lab. I completed my M.S. in AI at KAIST in 2026, advised by Prof. Minjoon Seo, and my B.S. in Computer Science at KAIST in 2024.

My research focuses on language model reasoning and agentic AI. I develop general post-training methods driven by self-training and reinforcement learning, with the long-term goal of extracting richer learning signals from data.

Outside of research, I enjoy playing jazz piano :)

Feel free to reach out!

Publications

2026

PUBG Ally: A Conversational Embodied Agent as an AI Teammate

PUBG Ally Team: I Chen, Y Cho, S Chung, J Hong, H Hwang, ..., K Yoo
Tech ReportPaper

2026

Intrinsic Task Symmetry Drives Generalization in Algorithmic Tasks

H Hwang, Y Park
ICML 2026PaperCode

2026

Characterizing Pattern Matching and Its Limits on Compositional Task Structures

H Chang, J Park, H Cho, S Yang, M Ko, H Hwang, S Won, D Lee, Y Ahn, M Seo
ICLR 2026Paper

2026

The CoT Encyclopedia: Analyzing, Predicting, and Controlling how a Reasoning Model will Think

S Lee, S Kim, M Seo, Y Jo, D Go, H Hwang, J Park, X Yue, S Welleck, G Neubig, M Lee, M Seo
ICLR 2026Paper

2025

Latent Reasoning via Sentence Embedding Prediction

H Hwang, B Jeon, S Kim, J Kim, H Chang, S Yang, S Won, D Lee, Y Ahn, M Seo
COLM 2025 RAM 2 Workshop · OralPaperCode

2025

The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models

S Kim, J Suk, ..., H Hwang, ..., M Seo
NAACL 2025 · Best PaperPaperCode

2025

Knowledge Entropy Decay during Language Model Pretraining Hinders New Knowledge Acquisition

J Kim, H Lee, H Cho, J Jang, H Hwang, S Won, Y Ahn, D Lee, M Seo
ICLR 2025 · Oral; AAAI 2025 KnowFM Workshop · Best PaperPaperCode

2024

Self-Explore: Enhancing Mathematical Reasoning in Language Models with Fine-grained Rewards

H Hwang, D Kim, S Kim, S Ye, M Seo
Findings of EMNLP 2024; ACL 2024 NLRSE Workshop · OralPaperCode

2024

FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets

S Ye, D Kim, S Kim, H Hwang, S Kim, Y Jo, J Thorne, J Kim, M Seo
ICLR 2024 · SpotlightPaperCode

2024

Investigating the Effectiveness of Task-Agnostic Prefix Prompt for Instruction Following

S Ye, H Hwang, S Yang, H Yun, Y Kim, M Seo
AAAI 2024PaperCode

2022

MED-SE: Medical Entity Definition-based Sentence Embedding

H Hwang, H Yoo, Y Choi
Preprint (During Internship @ NAVER)Paper

2022

Vision Transformer Equipped with Neural Resizer on Facial Expression Recognition Task

H Hwang, S Kim, W.-J. Park, J Seo, K Ko, H Yeo
ICASSP 2022PaperCode

Experience

Internships

  1. Sep 2026 — Present
    LG AI Research

    Research Intern · SuperIntelligence Lab

    Credit assignment in long-horizon RL

  2. May 2025 — Nov 2025
    KRAFTON

    Research Intern · AI Companion Team

    Gameplay agent for PUBG in collaboration with NVIDIA

    Co-Playable Character — PUBG Ally

  3. Mar 2022 — Aug 2022
    NAVER CLOVA

    Research Intern · Healthcare AI

    Medical text summarization & domain-specific embeddings

Education

  1. Aug 2026 — Present
    KAIST AI

    Ph.D. · Graduate School of AI

    Advisor: Seongjoon Oh

  2. Feb 2024 — Aug 2026
    KAIST AI

    M.S. · Graduate School of AI

    Advisor: Minjoon Seo

  3. Sep 2019 — Feb 2024
    KAIST

    B.S. · School of Computing

    Advisor: Tae-Kyun Kim

Academic service

Academic Service

Conference Reviewer
  • NeurIPS2026
  • ICLR2026
  • ICML2026Gold Reviewer
Journal Reviewer
  • TMLR2026