Jonghyun Park | Graduate School of AI, KAIST

About Me

I am a M.S. student at KAIST AI, advised by Prof. Jong Chul Ye. I am currently a research intern at the Vector Institute, working with Prof. Yaoliang Yu and Prof. Ricardo Baptista. I earned my B.S. in Naval Architecture and Ocean Engineering and Artificial Intelligence (Double Major) from Seoul National University (SNU) in Feb. 2025.

My research focuses on controllable and efficient image and video generation, editing, and restoration using diffusion and flow models. I also study how to train generative models from noisy or incomplete real-world observations when clean supervision is limited or unavailable. I am particularly interested in extending these methods to controllable world models.

News

[July 2026] I started a research internship at the Vector Institute, mentored by Prof. Yaoliang Yu and Prof. Ricardo Baptista.
[Feb 2025] I started my M.S. program at the KAIST Graduate School of AI, advised by Prof. Jong Chul Ye.

Publications

NeurIPS

[C4] Accelerating Video Inverse Problem Solvers with Autoregressive Diffusion Models

Taesung Kwon*, Jonghyun Park*, Hyungjin Chung†, Jong Chul Ye†

NeurIPS 2026.

PDF

[W1] FlowLPS: Langevin-Proximal Sampling for Flow-based Inverse Problem Solvers

Jonghyun Park, Jong Chul Ye

ICML 2026 workshop on RLxF.

PDF

ECCV

[C3] Tiled Prompts: Overcoming Prompt Underspecification in Image and Video Super-Resolution

Bryan Sangwoo Kim*, Jonghyun Park*, Jong Chul Ye

The 19th European Conference on Computer Vision (ECCV), 2026.

PDF

ICLR

[C2] FlowAlign: Trajectory-Regularized, Inversion-Free Flow-based Image Editing

Jeongsol Kim*, Yeobin Hong*, Jonghyun Park, Jong Chul Ye

International Conference on Learning Representations (ICLR), 2026.

PDF

ICCAS

[C1] Effective Exploration via Tsallis Actor-Critic on 6D Robot Grasping

Jaeyeon Jeong, Jonghyun Park, Songhwai Oh

The 24th International Conference on Control, Automation, and Systems (ICCAS), 2024.

PDF