Technion - Israel Institute of Technology
Yang SongResearch Principal, MSL · MetaResearcher↗
Researcher
Itai Gat
MetaResearcher
Gat develops generative models for information represented as discrete units, such as words and compressed audio. His work on discrete flow matching adapts a powerful image-generation approach to language and other sequences,[1] while projects such as MAGNeT explore controllable music and audio generation.
Career & education
Current roleMeta2022-presentResearcher
Meta2022-presentWork and education history is primarily focused on AI-relevant roles and may not be comprehensive.
Citation Trend
Total citations to scholarly work, including research papers, technical reports, books and theses, as recorded by Google Scholar. Each point is a dated snapshot.
citations32,816As of Nov 11, '26
citations+6,669Since last snapshot, Jun 15, '26
References
- Discrete Flow Matchingarxiv.org
Gat and colleagues extend flow matching to discrete data such as text tokens and evaluate the method on language generation.
Based on public sources. If accuracy is important, verify details using the links or references.
For corrections, updates, or requests to remove information, contact us.
Reviewed August 8, 2026 · Checked for accuracy and new information.
