Filip RadenovicResearch Scientist · MetaResearcher↗
Researcher
MetaResearch Scientist
Romero-Soriano co-authored Graph Attention Networks, a widely used method for learning from connected data.[1] She also contributed to fastMRI research that reduces the time needed to capture MRI scans, and now develops image and video models that produce more diverse, physically plausible synthetic training data.
The authors show how a network can learn from a graph by assigning different weights to neighboring nodes.
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 10, 2026 · Checked for accuracy and new information.