About Me

I am an assistant professor at POSTECH GSAI/CSE, leading Language & Intelligence Lab (LIL) under POSTECH NLP Group. Before joining POSTECH, I was an assistant professor at UNIST AIGS/CSE. I earned my PhD from UNC Chapel Hill, where I was advised by Prof. Mohit Bansal. I also worked with Prof. Henry Fuchs on AR applications.

Publications

• Mixture-of-Experts with Intermediate CTC Supervision for Accented Speech Recognition
  Wonjun Lee, Hyounghun Kim, and Gary Lee.
  Proceedings of ACL 2026.

• Can LLMs Estimate Cognitive Complexity of Reading Comprehension Items?
  Seonjeong Hwang, Hyounghun Kim, and Gary Lee
  Proceedings of ACL 2026.

• A Multi-Agent Framework for Feature-Constrained Difficulty Control in Reading Comprehension Item Generation
  Seonjeong Hwang, Jun Seo, Hyounghun Kim, Gary Lee
  Proceedings of ACL 2026.

• Why Do Multilingual Reasoning Gaps Emerge in Reasoning Language Models?
  Deokhyung Kang, Seonjeong Hwang, Daehui Kim, Hyounghun Kim, and Gary Lee
  Findings of ACL 2026.

• Behavior-Aware Item Modeling via Dynamic Procedural Solution Representations for Knowledge Tracing
  Jun Seo*, Sangwon Ryu*, Heejin Do†, Hyounghun Kim, and Gary Lee†
  Findings of ACL 2026.

• AQuA: Toward Strategic Response Generation for Ambiguous Visual Questions
  Jihyoung Jang and Hyounghun Kim
  Proceedings of ICLR 2026. [pdf]

• PanicToCalm: A Proactive Counseling Agent for Panic Attacks
  Jihyun Lee, Yejin Min, San Kim, Yejin Jeon, SungJun Yang, Hyounghun Kim, Gary Lee
  Proceedings of EMNLP 2025. [pdf]

• KoBLEX: Open Legal Question Answering with Multi-hop Reasoning
  Jihyung Lee*, DaeHee Kim*, Seonjeong Hwang, Hyounghun Kim, and Gary Lee
  Proceedings of EMNLP 2025. [pdf]

• Revealing the Inherent Instructability of Pre-Trained Language Models
  Seokhyun An, Minji Kim, and Hyounghun Kim
  Findings of EMNLP 2025. [pdf]

• Self-Correcting Code Generation Using Small Language Models
  Jeonghun Cho, Deokhyung Kang, Hyounghun Kim, and Gary Lee
  Findings of EMNLP 2025. [pdf]

• Progressive Facial Granularity Aggregation with Bilateral Attribute-based Reinforcement for Face-to-Speech Generation
  Yejin Jeon, Youngjae Kim, Jihyun Lee, Hyounghun Kim, and Gary Lee
  Findings of EMNLP 2025. [pdf]

• ChronoBias: A Benchmark for Evaluating Temporal Group Bias in Retrieval-augmented Language Models
  Kyungmin Kim, Youngbin Choi, Hyounghun Kim, Dongwoo Kim, and Sangdon Park
  Findings of EMNLP 2025. [pdf]

• Enabling Chatbots with Eyes and Ears: An Immersive Multimodal Conversation System for Dynamic Interactions
  Jihyoung Jang*, Minwook Bae*, Minji Kim, Dilek Hakkani-Tur, and Hyounghun Kim
  Proceedings of ACL 2025. [pdf]

• Collective Critics for Creative Story Generation
  Minwook Bae, and Hyounghun Kim
  Proceedings of EMNLP 2024. [pdf]

• Mixed-Session Conversation with Egocentric Memory
  Jihyoung Jang, Taeyoung Kim, and Hyounghun Kim
  Findings of EMNLP 2024. [pdf] [website]

• Conversation Chronicles: Towards Diverse Temporal and Relational Dynamics in Multi-Session Conversations
  Jihyoung Jang, MinSeong Boo, and Hyounghun Kim
  Proceedings of EMNLP 2023. [pdf] [website]

• Sound of Story: Multi-modal Storytelling with Audio
  Jaeyeon Bae*, Seokhoon Jeong*, Seokun Kang, Namgi Han, Jae-Yon Lee, Hyounghun Kim, and Taehwan Kim
  Findings of EMNLP 2023. [pdf]

• CoSIm: Commonsense Reasoning for Counterfactual Scene Imagination
  Hyounghun Kim*, Abhay Zala*, and Mohit Bansal
  Proceedings of NAACL 2022. [pdf]

• On the Limits of Evaluating Embodied Agent Model Generalization Using Validation Sets
  Hyounghun Kim, Aishwarya Padmakumar, Di Jin, Mohit Bansal, and Dilek Hakkani-Tur
  Insights Workshop, ACL 2022. [pdf]

• CAISE: Conversational Agent for Image Search and Editing
  Hyounghun Kim, Doo Soon Kim, Seunghyun Yoon, Franck Dernoncourt, Trung Bui, and Mohit Bansal
  Proceedings of AAAI 2022. [pdf][code]

• NDH-Full: Learning and Evaluating Navigational Agents on Full-Length Dialogue
  Hyounghun Kim, Jialu Li, and Mohit Bansal
  Proceedings of EMNLP 2021. [pdf][code]

• Continuous Language Generative Flow
  Zineng Tang, Shiyue Zhang, Hyounghun Kim, and Mohit Bansal
  Proceedings of ACL 2021. [pdf][code]

• FixMyPose: Pose Correctional Captioning and Retrieval
  Hyounghun Kim*, Abhaysinh Zala*, Graham Burri, and Mohit Bansal
  Proceedings of AAAI 2021. [pdf][code]

• ArraMon: A Joint Navigation-Assembly Instruction Interpretation Task in Dynamic Environments
  Hyounghun Kim, Abhaysinh Zala, Graham Burri, Hao Tan, and Mohit Bansal
  Findings of EMNLP 2020. [pdf][code]

• Dense-Caption Matching and Frame-Selection Gating for Temporal Localization in VideoQA
  Hyounghun Kim, Zineng Tang, and Mohit Bansal
  Proceedings of ACL 2020, Seattle, WA. [pdf][code]

• Modality-Balanced Models for Visual Dialogue
  Hyounghun Kim, Hao Tan, and Mohit Bansal
  Proceedings of AAAI 2020, New York, NY. [pdf]

• Improving Visual Question Answering by Referring to Generated Paragraph Captions
  Hyounghun Kim and Mohit Bansal
  Proceedings of ACL 2019, Florence, Italy (short paper). [pdf]
  (ACL Best Short Paper Nomination)

• Development of Augmented Reality Applications in Otolaryngology-Head and Neck Surgery
  Austin S. Rose, Hyounghun Kim, Henry Fuchs, and Jan-Michael Frahm
  The Laryngoscope, Jul. 2019. [pdf]

• Towards Fully Mobile 3D Face, Body, and Environment Capture Using Only Head-worn Cameras
  Young-Woon Cha, True Price, Zhen Wei, Xinran Lu, Nicholas Rewkowski, Rohan Chabra, Zihe Qin, Hyounghun Kim, Zhaoqi Su, Yebin Liu, Adrian Ilie, Andrei State, Zhenlin Xu, Jan-Michael Frahm, and Henry Fuchs
  IEEE Transactions on Visualization and Computer Graphics (TVCG), Vol. 24, November, 2018. [pdf]