PhD student position at the School of Electrical Engineering and Computer Science at KTH Royal Institute of Technology.
Project description
Generative models will revolutionize many industries and professions, with applications like programming assistants already in use. This raises a need for reliable and automated metrics that measure, for example, method robustness and appropriateness. Understanding quality is particularly crucial in domains less intuitive to the average user than images and text, which might require expert evaluation of each generated sample. Currently, only a few automated metrics exist, and their correlation with human judgment is debatable.
This project aims to design and evaluate reliable and aligned automated metrics for generative models trained on content in domains relevant to the gaming industry. The development of computer and mobile games needs the creation content such as animations, sound effects, and dialogue. The growing demand for a continuous stream of new content, coupled with the availability of user-generated content, has raised the interest in machine learning-driven solutions for automatic content generation. Such domain-specific metrics are highly needed for model development in the gaming industry to enable more rigorous testing and comparison between models.
Supervision: Professor Hedvig Kjellström (co-supervisor from SEED)