Yujin Jeong

I am a PhD student at TU Darmstadt and a member of ELLIS program under the supervision of Anna Rohrbach (the Multimodal AI Lab, TU Darmstadt) and Iro Laina (VGG, University of Oxford). I completed my Master's degree in Computer Science at Korea University under the supervision of Jinkyu Kim. I had an amazing opportunity to complete an internship as part of the ML Research team at NAVER AI LAB, and I also visited the Scalable Trustworthy AI (STAI) group at the Tübingen AI Center as visiting researcher during my Master’s. Previously, I received my B.S. in Statistics at Ewha Womans University. My current research interest is 1. Compositional generative models (Diffusion mostly), 2. Analysis by Synthesis, and 3. Multimodal Generative models (Text-Vision-Audio).

Github  /  CV  /  Email  /  Linkedin  /  Twitter  /  Google Scholar

💡 Open Positions for HiWi / Thesis supervision

I am currently looking for motivated students to work with me on research topics related to my research interests. Students with a strong background in machine learning and Python are especially welcome. If you are interested, please feel free to contact me via email with a short introduction, and also apply through this page.

Publications

Diffusion Classifiers Understand Compositionality, but Conditions Apply

Read, Watch and Scream! Sound Generation from Text and Video

The Power of Sound (TPoS): Audio Reactive Video Generation with Stable Diffusion

Zero-shot Visual Commonsense Immorality Prediction

The webpage template is from this source code.