Hyukhun Koh (고혁훈)

13. ARR : Jailbreak

12. ARR : Story Visualizaiton

11. ARR : Differential Privacy

10. Generating Diverse Hypotheses for Inductive Reasoning

Kang-il Lee, Hyukhun Koh, Dongryeol Lee, Seunghyun Yoon, Minsung Kim, Kyomin Jung (2025 NAACL Main & Oral)

9. Conditional [MASK] Discrete Diffusion Language Model

Hyukhun Koh*, Minha Jhang*, Dohyung Kim, Sangmook Lee, Kyomin Jung

8. Intent Induction and Toxicity Mitigation for Reliable LM Agent

Hyukhun Koh (2024 Seoul National University IPAI Outstanding Dissertation Award)

7. VLind-Bench: Measuring Language Priors in Large Vision-Language Models

Kang-il Lee, Minbeom Kim, Seunghyun Yoon, Minsung Kim, Dongryeol Lee, Hyukhun Koh, Kyomin Jung (2025 NAACL Findings)

6. Can LLMs Recognize Toxicity? Definition-Based Toxicity Metric

Hyukhun Koh, Dohyung Kim, Minwoo Lee, Kyomin Jung (2024 EMNLP Findings)

5. Fine-grained Gender Control in Machine Translation with Large Language Models

Minwoo Lee, Hyukhun Koh, Minsung Kim, Kyomin Jung (2024 NAACL Main)

4. Diversifying prosodic features of speech via determinantal point processes

Seongho Joo, Hyukhun Koh, Kyomin Jung (2023 EMNLP Main)

3. Target-Agnostic Gender-Aware Contrastive Learning for Mitigating Bias in Multilingual Machine Translation

Minwoo Lee, Hyukhun Koh, Kang-il Lee, Dongdong Zhang, Minsung Kim, Kyomin Jung (2023 EMNLP Main)

2. Reflecting dialogue and pretrained information into Multi Modal Emotion Recognition: Focusing on Text and Audio

Hyukhun Koh, Seongho Joo, Kyomin Jung (2023 KCC)

1. Multi-View Zero-Shot Open Intent Induction from Dialogues: Multi Domain Batch and Proxy Gradient Transfer

Hyukhun Koh, Haesung Pyun, Nakyeong Yang, Kyomin Jung (2022 SigDial & INLG DSTC 11)

Development of AI Technologies for Open-ended Alignment with Changing Environments and Values [변화하는 환경과 가치에 부합하는 Open-ended Alignment 인공지능기술 개발]

Funded by ITRC

Fairness and Safety of Large Language Models

Funded by NRF

Process-Oriented Assessment AI for Customized Education [맞춤형 교육을 위한 과정 중심 평가 AI]

Funded by IITP

Research on Developing AI Technologies That Flexibly Evolve in Response to Strengthening Ethical Policies – Medical & Marketing [점차 강화되고 있는 윤리 정책에 발맞춰 유연하게 진화하는 인공지능 기술 개발 연구]

Funded by IITP

IITP Global Core Talent Development Support Program (Microsoft Research Asia)

MSRA program