Cornell University
Research Challenges and Opportunities for Open Generative Modeling
Abstract
dc:description.abstractThis dissertation develops methods to make generative modeling more accessible, reliable, and legally grounded across vision, biology, and language. I introduce CommonCanvas, an open latent diffusion pipeline trained solely on Creative-Commons-licensed images, using a lightweight “telephoning” caption synthesis step to reach competitive quality with vastly less data. I then present PlantCaduceus, a genomics foundation model that leverages domain structure to outperform much larger generic models on plant biology tasks. Finally, I apply a principled probabilistic framework to quantify memorization and the extraction of copyrighted training data from large language models, moving beyond coarse averages to surface per-work risk and inform safer curation and deployment. Together, these contributions fuse technical innovation with openness and risk-aware practice to lower barriers and challenge prevailing conventions in modern AI.
Degree
thesis:*- Name thesis:degree_name
- Ph. D., Computer Science
- Level thesis:degree_level
- Doctor of Philosophy
- Discipline thesis:degree_discipline
- Computer Science
- Grantor
- Cornell University
- Year dc:date.issued
- 2025
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Gokaslan, Aaron
- Chair dc:contributor.chair
-
- Kuleshov, Volodymyr
- Committee members dc:contributor.committeemember
-
- Grimmelmann, James
- Snavely, Keith
Subjects
dc:subject × 6Rights
dc:rights- Statement dc:rights
-
- Attribution-ShareAlike 4.0 International
- Licence dc:rights.uri
- Language dc:language.iso
- en
Identifiers
dc:identifier.*- Dc Identifier Bibid
- 17422578
- Dc Identifier Other
-
ProQuest Submission ID: 15170
ProQuest Publication ID: 32169092