Jaemin Kim | KAIST

About Me

I am a Ph.D. student at Graduate School of AI, KAIST, where I also completed my master’s degree under the supervision of Prof. Jong Chul Ye.

I am interested in the controllability of advanced generative AI models, including diffusion models and large language models (LLMs). My recent research explores efficient guidance methods, such as training-free approaches and general-purpose strategies.

News

[2025.06] Our paper (Free²Guide) is accecpted to ICCV 2025.
[2025.03] Two papers (MotionPrompt, FreeMCG) are accepted to CVPR 2025.
[2025.03] I started Ph.D course in BIPSL, KAIST!
[2025.01] Our paper (GCTM) is accecpted to ICLR 2025.

Publications

ICCV

[C4] Free²Guide: Gradient-Free Path Integral Control for Enhancing Text-to-Video Generation with Large Vision-Language Models

Jaemin Kim, Bryan S Kim, Jong Chul Ye

IEEE/CVF International Conference on Computer Vision (ICCV), 2025

PDF Project Page Poster

[P2] Universal Reasoner: A Single, Composable Plug-and-Play Reasoner for Frozen LLMs

Jaemin Kim*, Hangeol Chang*, Hyunmin Hwang*, Choonghan Kim, Jong Chul Ye

arXiv preprint

PDF Preprint

CVPR

[C3] Optical-Flow Guided Prompt Optimization for Coherent Video Generation

Hyelin Nam*, Jaemin Kim*, Dohun Lee, Jong Chul Ye

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.

PDF Project Page Poster

CVPR

[C2] Derivative-Free Diffusion Manifold-Constrained Gradient for Unified XAI

Won Jun Kim*, Hyungjin Chung*, Jaemin Kim*, Sangmin Lee, Byeongsu Sim, Jong Chul Ye

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.

PDF Poster

ICLR

[C1] Generalized Consistency Trajectory Models for Image Manipulation

Beomsu Kim*, Jaemin Kim*, Jeongsol Kim, Jong Chul Ye

The Thirteenth International Conference on Learning Representations (ICLR), 2025.

PDF Project Page Poster

[P1] HiCBridge: Resolution Enhancement of Hi-C Data Using Direct Diffusion Bridge

Jaemin Kim, Jong Chul Ye

OpenReview

PDF Preprint