Oscar Davis

Oscar Davis

Doctoral Student

Themes:

• Artificial Intelligence and Machine Learning

Biography

I study Machine Learning, and am most interested in generative modelling; see, for instance, my first paper, where we explored Riemannian Flow Matching for discrete data generation. My previous work concerned primarily Graph Neural Networks.

Selected Publications

View AllManage publications

• Fisher Flow Matching for Generative Modeling over Discrete Data

  Oscar Davis‚ Samuel Kessler‚ Mircea Petrache‚ İsmail İlkan Ceylan‚ Michael Bronstein and Avishek Joey Bose

  In Proceedings of the 38th Annual Conference on Neural Information Processing Systems (NeurIPS). 2024.

  Details about Fisher Flow Matching for Generative Modeling over Discrete Data | BibTeX data for Fisher Flow Matching for Generative Modeling over Discrete Data | Link to Fisher Flow Matching for Generative Modeling over Discrete Data

Supervisors