Jungwon Choi 최중원

Multimodal intelligence for the real world

I am a Ph.D. student at KAIST AI, working in the Statistical Inference and Machine Learning Lab (SIML) under the supervision of Prof. Juho Lee.

My current research focuses on multimodal large language models, addressing real-world challenges such as efficient full-duplex interaction and learning with missing modalities. I also work on generative modeling and healthcare AI, with applications spanning brain imaging, computational pathology, and disease surveillance.

Multimodal LLMs Full-duplex Missing Modalities Self-supervised Healthcare AI

Open to research internships and collaborations.

News

Sep 2026 One paper accepted to NeurIPS 2026!
Jul 2026 One paper accepted to ICML 2026 SD4H Workshop!
Mar 2026 Two papers accepted to ICLR 2026 Workshops (Re-Align; Trustworthy AI)!
Jan 2026 Two papers accepted to ICLR 2026!
Dec 2025 One paper accepted to WACV 2026 LFMBio Workshop (Oral)!
Earlier news
Dec 2024 Excellence Award – First Place, Seoul AI Hub (AI+Healthcare)!
Sep 2024 One paper accepted to NeurIPS 2024!
Feb 2024 One paper accepted to ISBI 2024 (Oral)!
Oct 2023 Two papers accepted to NeurIPS 2023 TGL Workshop!
Dec 2022 One paper accepted to AAAI 2023 Bridge Program (Oral)!
Sep 2022 One paper accepted to NeurIPS 2022!

Publications

* Equal contribution

2026

  1. CEPA comparison with and without cross-modal information on chest X-rays
    Context-Aware Generative Imputation for Robust Multimodal Learning in Missing Modality Scenarios
    Jungwon Choi, Juho Lee
    NeurIPS 2026 (to appear)
  2. PROVISION-AF method: self-supervised ECG reconstruction followed by atrial fibrillation classification
    Impact of an AI algorithm for multi-day prediction of incident atrial fibrillation on clinical decision-making: PROVISION-AF study
    Yeji Kim, Bogeun Kim, Jaeung Yoon, Jeongmin Kang, Seung Woo Lee, Moon-Hyun Kim, Dong-Hyeok Kim, Hye Ah Lee, Jaemin Shim, Dae-In Lee, Seung-Young Roh, Seung Young Shin, Sung Hwa Choi, Yae Min Park, Ki Hong Lee, Yoo Ri Kim, Min Kim, Wei-Jin Park, Hyeon Yeo, Jungwon Choi, Tae Young Shin, Junbeom Park
    npj Digital Medicine, 2026
  3. Rhinovirus patient counts: ground truth and predictions from symptom search trends
    Can Symptom Search Trends Forecast Respiratory Virus Patient Counts? A Rhinovirus Case Study in Korean Syndromic Surveillance

    Exploring symptom search trends as signals for forecasting respiratory virus patient counts.

    Jungwon Choi*, Hyun Do Jung*, Soyeoun Kim
    ICML 2026 Workshop on Structured Data for Health (SD4H)
  4. ForestPersons
    ForestPersons: A Large-Scale Dataset for Under-Canopy Missing Person Detection
    Deokyun Kim*, Jeongjun Lee*, Jungwon Choi*, Jonggeon Park*, Giyoung Lee, Yookyung Kim, Myungseok Ki, Juho Lee, Jihun Cha
    ICLR 2026
  5. fMRI SOC
    Stochastic Optimal Control for Continuous-Time fMRI Representation Learning
    Joonhyeong Park*, Byoungwoo Park*, Chang-Bae Bang, Jungwon Choi, Hyungjin Chung, Byung-Hoon Kim, Juho Lee
    ICLR 2026
  6. CEPA: Context-Conditional Alignment
    Preventing Representation Collapse in Latent Prediction via Context-Conditional Alignment under Missing Modalities
    Jungwon Choi, Juho Lee
    ICLR 2026 Workshop on Representational Alignment (Re-Align)
  7. Bridging the Missing-Modality Gap
    Bridging the Missing-Modality Gap: Improving Text-Only Calibration of Vision Language Models
    Mingyeong Kim, Jungwon Choi, Chaeyun Jang, Juho Lee
    ICLR 2026 Workshop on Principled Design for Trustworthy AI
  8. ReaMIL overview
    ReaMIL: Reasoning- and Evidence-Aware Multiple Instance Learning for Whole-Slide Histopathology
    Hyundo Jung, Jungwon Choi, Hwiyoung Kim
    WACV 2026 Workshop on Large Foundation Models in Biology and Biomedicine (LFMBio) Oral Presentation

2024

  1. DBFS diffusion bridge
    Stochastic Optimal Control for Diffusion Bridges in Function Spaces
    Byoungwoo Park, Jungwon Choi, Sungbin Lim, Juho Lee
    NeurIPS 2024
  2. STJEMA overview
    Joint-Embedding Masked Autoencoder for Self-supervised Learning of Dynamic Functional Connectivity from the Human Brain
    Preprint
  3. TENET overview
    Learning Dynamic Brain Connectome with Graph Transformers for Psychiatric Diagnosis Classification
    Byung-Hoon Kim*, Jungwon Choi*, EungGu Yun, Kyungsang Kim, Xiang Li, Juho Lee
    ISBI 2024 Oral Presentation

2023

  1. STMAE overview
    A Generative Self-Supervised Framework using Functional Connectivity in fMRI Data
    Jungwon Choi, Seongho Keum, EungGu Yun, Byung-Hoon Kim, Juho Lee
    NeurIPS 2023 TGL Workshop
  2. TENET embedding
    Large-scale Graph Representation Learning of Dynamic Brain Connectome with Transformers
    Byung-Hoon Kim*, Jungwon Choi*, EungGu Yun, Kyungsang Kim, Xiang Li, Juho Lee
    NeurIPS 2023 TGL Workshop
  3. Uplift modeling
    Modeling Uplift from Observational Time-Series in Continual Scenarios
    Sanghyun Kim, Jungwon Choi, NamHee Kim, Jaesung Ryu, Juho Lee
    AAAI 2023 Bridge Program Oral Presentation

2022

  1. BPC divergences
    On Divergence Measures for Bayesian Pseudocoresets
    Balhae Kim, Jungwon Choi, Seanie Lee, Yoonho Lee, Jung-Woo Ha, Juho Lee
    NeurIPS 2022

2021

  1. MS thesis
    Robust Deepfake Detection via Invariant Feature Learning
    Jungwon Choi
    Master Thesis, KAIST, 2021

Honors & Awards

Academic Services

Journal Reviewer
  • Machine Learning (Springer Nature)
  • IEEE Transactions on Medical Imaging
  • Medical Image Analysis
  • IEEE Open Journal of the Computer Society
Conference Reviewer
  • ICLR2025–2027
  • AAAI2027
  • ICML2025–2026
  • NeurIPS2026
  • ECCV2026
  • ICLR2025–2027
  • AAAI2027
  • ICML2025–2026
  • NeurIPS · ECCV2026

Education