back to list

Yujin Jeong M.Sc.

Multimodal Grounded Learning

Working area(s)

Compositionality

Contact

Work S4/23 207
Landwehrstr. 50A
64293 Darmstadt

Links

2024 ongoing Ph.D. student at the Multimodal AI group (supervised by Prof. Dr. Anna Rohrbach )
20203 2024 Research internship at NAVER AI LAB (South Korea)
20321 20203 M.Sc. in computer science at Korea University (supervised by Prof. Jinkyu Kim) (South Korea)
2016 2021 B.Sc in Statistics at Ewha Womans University (South Korea)

I’m interested in Compositionality in VLMs and Generative models (Audio-Text-Vision). Many vision-language models (VLMs) face significant challenges related to compositionality, a crucial aspect for their effectiveness in understanding and generating complex data. These challenges impact their ability to reason and perceive in many real-world. I am currently focusing on compositionality in generative-based models and plan to extend this work to encoder-based VLMs.