@FrancescoLocat8 Profile picture

Francesco Locatello

@FrancescoLocat8

Assistant prof at ISTA. Prev: AWS, PhD at ETH Zürich/Max Planck Institute for Intelligent Systems.

Similar User
Taco Cohen photo

@TacoCohen

Max Welling photo

@wellingmax

Pavel Izmailov photo

@Pavel_Izmailov

Bernhard Schölkopf photo

@bschoelkopf

Greg Yang photo

@TheGregYang

Sham Kakade photo

@ShamKakade6

Zico Kolter photo

@zicokolter

Roger Grosse photo

@RogerGrosse

Emiel Hoogeboom photo

@emiel_hoogeboom

Jakub Tomczak photo

@jmtomczak

Olivier Bachem photo

@OlivierBachem

Aditya Grover photo

@adityagrover_

Thomas Kipf photo

@tkipf

Michael Bronstein photo

@mmbronstein

Sindy Löwe photo

@sindy_loewe

Pinned

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: arxiv.org/abs/2102.11107

Tweet Image 1

Francesco Locatello Reposted

✨ Meet #ResiDual, a novel perspective on the alignment of multimodal latent spaces! Think of it as a spectral "panning for gold" along the residual stream. It improves text-image alignment by simply amplifying task-related directions! 🌌🔍 arxiv.org/abs/2411.00246 [1/6]

Tweet Image 1

Francesco Locatello Reposted

@ISTAustria welcomes renowned scientist, inventor, and entrepreneur Alex Bronstein as a faculty member! After a year as a Visiting Professor, he joins us to advance machine vision, #MachineLearning in life sciences—and even #AI in music! Read more 🔗 bit.ly/48uOcgX

Tweet Image 1

Francesco Locatello Reposted

🚀 Thrilled to announce our new paper: “Cross-Entropy is All You Need: Classification for Provably Identifiable Representations” 📄 arxiv.org/abs/2410.21869 🎉 Why I’m excited 🧵: [0/n]

Tweet Image 1

Why training a linear probe on top of a pretrained representation can solve so many different tasks? We take an identifiability viewpoint and show when/why your pretrained model actually learned ground truth factors of variations in your data! arxiv.org/abs/2410.21869



Francesco Locatello Reposted

BREAKING NEWS The Royal Swedish Academy of Sciences has decided to award the 2024 #NobelPrize in Physics to John J. Hopfield and Geoffrey E. Hinton “for foundational discoveries and inventions that enable machine learning with artificial neural networks.”

Tweet Image 1

Francesco Locatello Reposted

⭐⭐⭐ Join the group ⭐⭐⭐ Postdoctoral positions are open as part of the ERC Grant Calcifer 🔥 ! Job advertisement and How to apply: aas.org/jobregister/ad… 🚩 Deadline October 25th


Francesco Locatello Reposted

The #ELLISPhD application portal is now open! Apply to top #AI labs & supervisors in Europe with a single application, and choose from different areas & tracks. The call for applications: ellis.eu/news/ellis-phd… Deadline: 15 November 2024 #PhD #PhDProgram #MachineLearning #ML

Tweet Image 1

Francesco Locatello Reposted

📢Submit by Nov 2 to CLeaR, if you are researching on Causal Discovery, Causal Inference, Intersections of Causality and Machine Learning, and many others! Check out our Call for Papers cclear.cc/2025/CallforPa…

Tweet Image 1

We are thrilled to announce the 4th Conference on Causal Learning and Reasoning (CLeaR), taking place in Lausanne, Switzerland, from May 7-9, 2025! Submission deadline: Nov 2, 2024, 11:59 PM AoE. For details, visit cclear.cc/2025/CallforPa… 😀😎



Francesco Locatello Reposted

We are delighted to announce that Dr Leena Chennuru Vankadara will join the Unit as Lecturer in Feb 2025, developing theoretical understandings of scaling and generalization in deep learning and causality. Welcome aboard @leenaCvankadara! Learn more at ucl.ac.uk/gatsby/news-an…

Tweet Image 1

Francesco Locatello Reposted

PhD applications at @GatsbyUCL now open! Fully funded regardless of nationality. See below for application details!

📢 Applications for 2025 Gatsby Unit PhD programme are open! Submit by 11 Nov 2024. 💰 Fully funded regardless of nationality ℹ️ ucl.ac.uk/gatsby/study-a…

Tweet Image 1


Francesco Locatello Reposted

Now that every one of my collaborators got my handle wrong… I have to also share this! Happy to share our perspective piece on virtual cells with the team from @cziscience, @StephenQuake , our AI residents @Prof_Lundberg , @jure , Aviv, @_bunnech , @yusufroohani , @YanayRosen ,…

Together with AI/ML experts, we explored how virtual cell models can advance scientific discovery. Rooted in community discussions, this 🆕 preprint lays out a roadmap for a large-scale, collaborative research agenda on AI-driven virtual cells bit.ly/3MP3mnx



Francesco Locatello Reposted

#AITHYRA is born! 🎉 OeAW is founding a new institute at the intersection of #AI & #biomedicine – the AITHYRA Institute. Meet the new founding director and DeepMind Professor of Artificial Intelligence @mmbronstein Watch now ➡️youtu.be/pTA6DPQpxfo #boehringeringelheimstiftung

Tweet Image 1

Francesco Locatello Reposted

Welcome to Vienna BioCenter, AITHYRA - A new research institute focused on Artificial Intelligence (AI) and biomedicine is set to join the Vienna BioCenter Read more: lnkd.in/dHCpyBNn

Tweet Image 1

Francesco Locatello Reposted

I am very excited to start a new journey funded by @ERC_Research ! Postdoctoral positions will open very soon, reach out!

Three @ISTAustria scientists have won @erc_research Starting Grants #ERCStG! A combined 4.8 million euros will go to @MMondelli, @aliciakmichael, and @lisa_Bugnet Read more about the scientists and their projects 🔗 bit.ly/3XvfQXo

Tweet Image 1


Francesco Locatello Reposted

@Dingling_Yao, Dario Rancati, @marco_fumero , and @FrancescoLocat8 also have an awesome recent paper on unifying CRL from an invariance perspective; you should check that out, too! arxiv.org/abs/2409.02772


Francesco Locatello Reposted

Take your career to the next level: #FacultyCall @ISTAustria is open! We're seeking exceptional group leaders in #chemistry, #ComputerScience, #DataScience, #EarthScience, #LifeSciences, #mathematics, and #SoftMatterPhysics to join our institute. Apply 🔗 bit.ly/47mxEre

Tweet Image 1

Francesco Locatello Reposted

Grateful to @ERC_Research and excited to start the project. This would not have been possible without my group at @ISTAustria and my collaborators, thank you! Multiple open positions (postdocs, PhDs, interns), strong candidates encouraged to reach out. marcomondelli.com

Three @ISTAustria scientists have won @erc_research Starting Grants #ERCStG! A combined 4.8 million euros will go to @MMondelli, @aliciakmichael, and @lisa_Bugnet Read more about the scientists and their projects 🔗 bit.ly/3XvfQXo

Tweet Image 1


Francesco Locatello Reposted

to follow up my recent post on "the mech-int community would likely benefit from learning more about manifolds" -- the following "old" work by @FrancescoLocat8 is certainly worth revisiting as well: arxiv.org/abs/1811.12359


Francesco Locatello Reposted

We are thrilled to announce the 4th Conference on Causal Learning and Reasoning (CLeaR), taking place in Lausanne, Switzerland, from May 7-9, 2025! Submission deadline: Nov 2, 2024, 11:59 PM AoE. For details, visit cclear.cc/2025/CallforPa… 😀😎


Francesco Locatello Reposted

We have an amazing lineup of keynote speakers: @feishaAI @KaterinaFragiad @mmbronstein @StefanieJegelka @tkipf and Masashi Sugiyama! #fml2024 Join us as fml2024.ista.ac.at


Francesco Locatello Reposted

Are you planning to attend #ICML2024 in Vienna? Why not come two days earlier and attend the Symposium "The Future of Machine Learning" at @ISTAustria on July 19th? We'll have great speakers, free coffee, and enough space to meet and chat. Join now at fml2024.ista.ac.at


Loading...

Something went wrong.


Something went wrong.