Francesco Locatello
@FrancescoLocat8
Followers
5K
Following
1K
Media
52
Statuses
922
Assistant prof at ISTA. Prev: AWS, PhD at ETH Zürich/Max Planck Institute for Intelligent Systems.
Joined June 2018
Towards Causal Representation Learning: led by @bschoelkopf and myself, with amazing co-authors Stefan Bauer, @rosemary_ke, @NalKalchbrenner, @anirudhg9119, Yoshua Bengio, accepted in the Proceedings of the IEEE. Link:
6
123
598
RT @ClementineDomi6: 🎓Thrilled to share I’ve officially defended my PhD!🥳. At @GatsbyUCL, my research explored how prior knowledge shapes n….
0
8
0
RT @Dingling_Yao: 🚀 Got fresh ideas in causal discovery, inference, or reasoning for scientific problems? Share them at the @CauScien works….
sites.google.com
Call for Papers
0
7
0
RT @CauScien: 🚨 Call for Papers: #CauScien Workshop @ #NeurIPS2025 🚨.Short papers. Real impact. 📅 Submit by Aug 22.🧠 Let’s uncover causalit….
0
2
0
If this Adam is looking for a new job (PhD or PostDoc), we have many architectures to optimize in my lab!.
0
1
61
FOMO hitting hard 🥲.
0
0
22
RT @CauScien: 🚨 We’re thrilled to announce our NeurIPS 2025 workshop:.CausCien: Uncovering Causality in Science 🔍✨.We’re uniting ML + scien….
0
8
0
RT @NeurIPSConf: NeurIPS is seeking additional ethics reviewers this year. If you are able and willing to participate in the review process….
0
12
0
RT @torchcompiled: Modeling dolphin language is cool. Translating it into human speak is cooler. Somewhere you're gonna want to figure ou….
0
60
0
RT @GatsbyUCL: 🥳 Congratulations to Clementine Domine on passing her PhD viva with minor corrections! 🎉. 🔖 Balancing Learning Regimes: The….
0
9
0
0
1
0
New "representation" of what an autoencoder learns: repeated autoencoding describes a latent vector field, with the attractors containing information on generalization/memorization, inductive bias, and the input data distribution. Also has the coolest visualizations!.
Neural networks implicitly define a latent vector field on the data manifold, via autoencoding iterations🌀. This representation retains properties of the model, revealing memorization and generalization regimes, and characterizing distribution shifts. 📜:
4
0
36
RT @marco_fumero: Neural networks implicitly define a latent vector field on the data manifold, via autoencoding iterations🌀. This represen….
0
76
0
RT @MireloAI: 🚀 Mirelo's beta is live!. Creates perfectly synced sound and music for your videos!.✨ Try the beta at .
0
5
0
RT @gcpr_by_dagm: Announcing our amazing Keynote speakers for #GCPR2025!. Keynote Speakers: .Venkatesh Babu Radhakrishnan, IISc. Dima Damen….
0
3
0
RT @ELLISforEurope: New #ELLISPhD Reading Group: the ELLIS @unireps Speaker Series:. 💡 Deep dives into #DeepLearning, neuroscience, #Cognit….
0
5
0
0
0
3
New preprint: "The third pillar of causal analysis? A measurement perspective on causal representations". We offer a new practical viewpoint of causal representations, their conceptualization, downstream usefulness, and evaluation.
1
5
29
RT @gcpr_by_dagm: Continued. Announcing our Publicity Chairs and Local Organizer:.Publicity Chairs: Shashank Agnihotri and Adeel Pervez @….
0
1
0