Donghoon Ahn

I am an undergraduate researcher at CVLAB, KAIST, with a deep interest in artificial intelligence, computer vision, generative models, and diffusion models. I am particularly fascinated by the fundamental principles of how the world works and integrating the inductive biases derived from them into generative models. Additionally, I have a keen interest in generating images, videos, and 3D models for artistic or practical purposes. I enjoy creating beautiful artwork using generative models. Recently, I co-authored the Perturbed-Attention Guidance (PAG), which is increasingly used in diffusion models. If you are interested, please check out my publications below.

My hobbies include drawing, listening to music, playing the piano, cycling, and exploring new places. If you have any questions about me, feel free to reach out via email (suno.vivid@gmail.com), LinkedIn, or direct message on Twitter. I welcome your messages.

I’m currently exploring labs for PhD opportunities starting in Fall 2025. I’m also looking for internship positions this winter or next spring in the area of image, video, or 3D generation research. If you’re interested in my work or think we could be a good fit, I’d be happy to meet and chat, either online or in person.

If you are interested, feel free to read my CV.