Locating and Editing Factual Associations in Generative Models

[Intro. animation from here]

This project aims to investigate how image generative models can be used to locate and edit factual associations within an image. Specifically, the project will explore how such models can identify and modify factual associations that are embedded within the relation information used in a given image (e.g., language captions or scene graphs). This project is particularly relevant in today's world, where there is an increasing demand for automated tools that can help users to manipulate, retrain, or personalize the heavy generative model. By developing a better understanding of how generative models can be used to locate and edit factual associations, this project has the potential to contribute to the development of more accurate and trustworthy generative models in the future.

This project is suitable for (but not limited to) students majoring in electrical engineering, computer science, industrial engineering, and mathematics. Ideally, students in their third year or higher are preferred. Basic English skills for reading and presenting papers and proficiency in Python programming are required. Otherwise, it will be very difficult to proceed with the project. Students who have experience with deep learning projects or have read papers on the topic are preferred. If they have experience working with generative models, it would be even better.

Supervisors


Feel like you want to explore other projects? Go and look for the list here: Student (Intern) projects