| dc.rights.license | CC-BY-NC-ND | |
| dc.contributor.advisor | Chen, G. | |
| dc.contributor.author | Lu, Zehao | |
| dc.date.accessioned | 2024-02-15T14:49:49Z | |
| dc.date.available | 2024-02-15T14:49:49Z | |
| dc.date.issued | 2024 | |
| dc.identifier.uri | https://studenttheses.uu.nl/handle/20.500.12932/45939 | |
| dc.description.abstract | Although presentations are an excellent medium for sharing academic opinions and ideas, there has been a scarcity of research into automating the "paper to slides" generation task, and a lack of publicly available datasets. In response, we propose an inventive optimization framework based on reconstruction loss, harnessing cutting-edge Large Language Models (LLMs) and unsupervised learning. This approach facilitates the creation of high-quality slide decks from scientific papers, offering heightened adaptability and flexibility. Our evaluation results provide empirical evidence of our model’s superior performance in comparison to baseline models. | |
| dc.description.sponsorship | Utrecht University | |
| dc.language.iso | EN | |
| dc.subject | This thesis project addresses automating the creation of presentation slides from academic papers. We introduce a novel framework that uses Large Language Models and unsupervised learning to generate adaptable and high-quality slide decks. Our evaluation shows that our approach outperforms baseline models, proving its effectiveness in this task. | |
| dc.title | Unsupervised Paper2Slides Generation | |
| dc.type.content | Master Thesis | |
| dc.rights.accessrights | Open Access | |
| dc.subject.courseuu | Artificial Intelligence | |
| dc.thesis.id | 23029 | |
