Francesco Locatello
Francesco Locatello works on causal learning and representations. His research examines when learned internal variables can reflect the structure of the world. Locatello earned an ETH Zürich doctorate through the Max Planck–ETH program and worked as a senior applied scientist at AWS, where he led a causal representation learning team. Locatello coauthored research challenging assumptions in unsupervised disentangled representation learning. The original paper establishes that additional assumptions or supervision are needed to identify such representations. The paper appeared at ICML 2019. He is an ISTA assistant professor leading the Causal Learning and Artificial Intelligence lab. He received research recognition in 2023, 2024 and 2026 for joint work.
- Works
- 147
- Citations
- 3,306
- h-index
- 20
Publication numbers from OpenAlex, as of 14 October 2026.
Timeline
-
2018–2019
Limits of unsupervised disentanglement
Locatello coauthored research challenging assumptions in unsupervised disentangled representation learning. The original paper establishes that additional assumptions or supervision are needed to identify such representations. The paper appeared at ICML 2019.
-
As of October 2026
Research across academia and industry
Locatello’s career includes an ETH Zürich doctorate through the Max Planck–ETH program and a senior applied-scientist role at AWS, where he led a causal representation learning team.
-
As of October 2026
Causal learning at ISTA
He is an ISTA assistant professor leading the Causal Learning and Artificial Intelligence lab. He received research recognition in 2023, 2024 and 2026 for joint work.
Sources and credits
Photo: ellis.eu; Francesco Locatello profile photograph; creator not stated. License: Not stated by source. Source: ellis.eu. Cropped to a square and resized. Ask us to remove or replace this photo.