Jiwon Kim

Hi! I'm a MS student at Korea University, Image Processing Algorithm Lab. advised by Prof. Kyong Hwan Jin. Currently, I am also working as a Research Intern at Naver Labs (Computer Vision & Deep Learning).

My ultimate goal is to bridge the gap between human imagination and digital reality, creating a world that is seamlessly modifiable according to user intention. To that end, my research focuses on Generative Models and 3D Computer Vision, enabling intelligent systems to perceive, reconstruct, and edit the world with high fidelity and controllability.

Feel free to send me an e-mail if you want to have a chat!
Contact: jwonkim@korea.ac.kr

Google Scholar / Linkedin / Github / CV

	Dual Recursive Feedback on Generation and Appearance Latents for Pose-Robust Text-to-Image Diffusion Jiwon Kim, Pureum Kim, SeonHwa Kim, Soobin Park, Eunju Cha^†, Kyong Hwan Jin^† International Conference on Computer Vision (ICCV), 2025. Paper / Website / Code We introduce DRF, a training-free dual recursive feedback system that recursively refines latents to robustly integrate structure and appearance for controllable text-to-image generation.
	iOS: 3D iterative Optimization Sampling Jiwon Kim, Hyunmin Cho, Pureum Kim, Kyong Hwan Jin^† IEIE summer, 2025. Paper We introduce iOS, a 3D iterative optimization sampling framework that utilizes Fixed-Point Iterative Regularization to preserve source identity and structural consistency in text-guided 3D editing.
	Identity-preserving Distillation Sampling by Fixed-Point Iterator SeonHwa Kim, Jiwon Kim, Soobin Park, Donghoon Ahn, Jiwon Kang, Seungryong Kim^†, Eunju Cha^†, Kyong Hwan Jin^† Conference on Computer Vision and Pattern Recognition (CVPR), 2025. Paper / Website / Code We introduce IDS that leverages a fixed-point iterator to self-correct gradient errors for preserving source identity and structural consistency in text-guided image editing.

Research Intern | NAVER LABS
2026 Jan - Current

On Road Intelligence team

M.S in Electrical Engineering | Korea University
Sep 2024 - Aug 2026 (Expected)

Research: Generative Model & 3D Vision
Advisor: Prof. Kyong Hwan Jin

B.A in Electrical and Computer Engineering | AJOU University
Mar 2020 - Feb 2024

Research: Healthcare AI
Advisor: Prof. Weduke Cho

Jiwon Kim, Ahyeon Kim, Weduke Cho^†,
"A Study on Aging Health Measurement Technology Using Image-Based Hand Function Test", CEIC, 2023
Weduke Cho^†, Kyuhyung Kim, Ahyeon Kim, Jiwon Kim,
"Research on Criteria for Selecting Videos that Elicit Happiness and Fear: Based on Heart Rate Measurement", KICS, 2023

Best Paper Award, Summer Annual Conference of IEIE, 2025
Gold Prize, Best Paper Award, 7th Workshop of Image Processing and Image Understanding (IPIU), 2025

Development of a Self-Learning World Model-Based AGI System for Hyperspectral Imaging, IITP (Institute of Information & Communications Technology Planning & Evaluation), 2025

Method and Apparatus for Lossless Implicit Neural Representation Based on Bipolar Vector Labeling and Recursive Single Weight Operation
Hyunmin Cho, Kyong Hwan Jin, Yongjun Lee, Jiwon Kim, Woo Kyoung Han
Korea Patent Application No. 10-2025-0150878

Website templates from Jon Barron.