publications

ICLR * 1, EMNLP * 4, NAACL * 1, AAAI * 1, EACL * 1, IEEE Series * 1, Q1 Journal * 4.

First and co-first author (refereed) * 6.

The asterisk (*) indicates co-first authorship.

2026

  1. New Success and Failure of Human–AI Collaboration in Clinical Reasoning: An Experimental Study on Challenging Real-world Cases
    Kai Tzu-iunn Ong*, Junwon Seo*, Hyojun Kim, Jiwoo Kim, and 4 more authors
    International Journal of Medical Informatics 2026 (Q1)
    [PDF]

2025

  1. New PRINCIPLES: Synthetic Strategy Memory for Proactive Dialogue Agents
    Namyoung Kim, Kai Tzu-iunn Ong, Yeonjun Hwang, Minseok Kang, and 4 more authors
    EMNLP 2025 (Findings)
    [PDF]
  2. New Age-Related Scattered Hypofluorescent Spots as an Adverse Prognostic Factor for Polypoidal Choroidal Vasculopathy​
    Seo Hee Kim*, Kai Tzu-iunn Ong*, Seonghee Choi, Eun Jee Chung, and 4 more authors
    Ophthalmology Science 2025 (Q1)
    [PDF]
  3. Towards Lifelong Dialogue Agents via Timeline-based Memory Management
    Kai Tzu-iunn Ong*, Namyoung Kim*, Minju Gwak, Hyungjoo Chae, and 5 more authors
    NAACL 2025  Oral Presentation 
    [PDF]
  4. Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation
    Hyungjoo Chae, Namyoung Kim, Kai Tzu-iunn Ong, Minju Gwak, and 5 more authors
    ICLR 2025
    [PDF]
  5. Evidence-guided Transfer Learning to Overcome Data limitations in Optical Coherence Tomography-based Retinal Detachment Differentiation
    Kai Tzu-iunn Ong, Tae Keun Yoo, Jung Dong Kim, Min Kim, and 3 more authors
    under review 2025
  6. Noise Analysis of Chemical Reactions from US Patents via Large Language Models
    Chaewon Lee, Shuan Chen, Kai Tzu-iunn Ong, Jinyoung Yeo, and 1 more author
    under review 2025

2024

  1. Coffee-gym: An Environment for Evaluating and Improving Natural Language Feedback on Erroneous Code
    Hyungjoo Chae, Taeyoon Kwon, Seungjun Moon, Yongho Song, and 6 more authors
    EMNLP 2024
    [PDF]
  2. Language Models as Compilers: Simulating Pseudocode Execution Improves Algorithmic Reasoning in Language Models
    Hyungjoo Chae, Yeonghyeon Kim, Seungone Kim, Kai Tzu-iunn Ong, and 7 more authors
    EMNLP 2024 (Featured in AK Daily Papers)
    [PDF]
  3. Commonsense-augmented Memory Construction and Management in Long-term Conversations via Context-aware Persona Refinement
    Hana Kim, Kai Tzu-iunn Ong, Seoyeon Kim, Dongha Lee, and 1 more author
    EACL 2024 (Conceptualized and wrote the paper)  Oral Presentation 
    [PDF]
  4. Multitask Deep Learning for Joint Detection of Necrotizing Viral and Noninfectious Retinitis from Common Blood and Serology Test Data
    Kai Tzu-iunn Ong*, Taeyoon Kwon*, Harok Jang, Min Kim, and 5 more authors
    Investigative Ophthalmology & Visual Science 2024 (Q1; IF = 5.0)
    [PDF]
  5. Large Language Models Are Clinical Reasoners: Reasoning-aware Diagnosis Framework with Prompt-generated Rationales
    Taeyoon Kwon*, Kai Tzu-iunn Ong*, Dongjin Kang, Seungjun Moon, and 6 more authors
    AAAI 2024
    [PDF]
  6. Large Language Models Are Self-Taught Reasoners: Enhancing LLM Applications via Tailored Problem-Solving Demonstrations
    Kai Tzu-iunn Ong, Taeyoon Kwon, and Jinyoung Yeo
    preprint 2024

2023

  1. Dialogue Chain-of-Thought Distillation for Commonsense-aware Conversational Agents
    Hyungjoo Chae, Yongho Song, Kai Tzu-iunn Ong, Taeyoon Kwon, and 5 more authors
    EMNLP 2023
    [PDF]
  2. Natural Language Processing to Predict Isocitrate Dehydrogenase Genotype in Diffuse Glioma Using MR Radiology Reports
    Minjae Kim, Kai Tzu-iunn Ong, Seonah Choi, Jinyoung Yeo, and 9 more authors
    European Radiology 2023 (Q1; IF = 7.03​)
    [PDF]
  3. Evidence-empowered Transfer Learning for Alzheimer’s Disease
    Kai Tzu-iunn Ong, Hana Kim, Minjin Kim, Jinseong Jang, and 5 more authors
    IEEE ISBI 2023  Oral Presentation 
    [PDF] [Video]