Research
Generative Models / Interpretability
† Equal contribution (co-first authors)
Your browser does not support the video tag.
Derivative-Free Diffusion Manifold-Constrained Gradients for Unified XAI
Won Jun Kim† ,
Hyungjin Chung† ,
Jaemin Kim† ,
Sangmin Lee,
Byeongsu Sim,
Jong Chul Ye
arXiv preprint , 2024
Counterfactual generation and feature attribution without any access to the model or its gradients using diffusion models and the theory of ensemble Kalman filters.
LLM-CXR: Instruction-Finetuned LLM for CXR Image Understanding and Generation
Suhyeon Lee† ,
Won Jun Kim † ,
Jinho Chang,
Jong Chul Ye
ICLR , 2024
Leveraging an LLM's language-based reasoning ability for multimodal alignment using a pretrained LLM and image tokenization with a VQ-GAN.
Association between adiposity and cardiovascular outcomes: an umbrella review and meta-analysis of observational and Mendelian randomization studies
Min Seo Kim,
Won Jun Kim ,
Amit V Khera,
Jong Yeob Kim,
Dong Keon Yon,
Seung Won Lee,
Jae Il Shin,
Hong-Hee Won
Eur Heart J , 2021
Systematic review of the relationship between adiposity (obesity) and cardiovascular illness.
Comprehensive Learning Curve of Robotic Surgery: Discovery From a Multicenter Prospective Trial of Robotic Gastrectomy
Min Seo Kim,
Won Jun Kim ,
Woo Jin Hyung,
Hyoung-Il Kim,
Sang-Uk Han,
Young-Woo Kim,
Keun Won Ryu,
Sungsoo Park
Ann Surg , 2021
Tracking of operation times and complication rates in robotic gastrectomy as the surgeons' experience grows.
Comparative efficacy and safety of pharmacological interventions for the treatment of COVID-19: A systematic review and network meta-analysis
Min Seo Kim,
Min Ho An,
Won Jun Kim ,
Tae-Ho Hwang
PLoS Medicine , 2020
Systematic review of the evidence behind COVID-19 treatments in the first wave of the pandemic.