Exploring Generative Models' Latent Spaces: Investigating the Influence of UIs on Human-AI Collaboration

Problem Statement

The increased use of generative models has elevated human-AI collaboration to new heights. Although there has been extensive research on the evaluation metric of generative models, it has not yet been used for human exploration of the latent space of generative models. Exploring latent spaces of generative models remains a significant challenge, particularly in terms of how users explore and interact with these spaces through different user interfaces. This work investigates the influence of user interfaces on users’ exploration of latent spaces of generative models, aiming to develop more intuitive and effective exploration tools. By proposing a Python package with novel metrics and visualizations for quantifying exploration behavior and preferences, this work sheds light on user-centric exploration patterns and provides practical insights for designing user-friendly interfaces. The findings contribute to a deeper understanding of the user interaction with generative models and facilitate the broader adoption and application of these models in various domains.

Tasks

• Perform a literature review. Identify key challenges and gaps in current approaches to GAN's latent space Exploration
• Build a Python package for different metrics
• Do statistical evaluations
• Write a thesis and present your findings in the Disputationsseminar
• (Optional:) co-write a research paper