ELLIS itself doesn’t give out money. But there are EU mobility programs associated with ELLIS. Planning the exchange is part of your supervision agreement. For example, my exchange to Helsinki was partially funded by ELISE+ELSA (8000 EUR total) 🇪🇺 More: ellis.eu/mobility-progr…

It’s clearly the Gaussian pdf.

Bit late to the latest #reasoning debate (yes, the Apple paper) but was busy doing my homework TLDR: 1) paper over-interprets normal statistical variation; 2) for 21/25 models, there isn’t evidence to reject the null that performance on GSM8K equals to that on GSM-Symbolic ⬇️

The One World ABI (née ABC) community is fantastic and the online seminar series is sublime. Make sure to follow their new account! 👇

My PhD thesis is printed and ready for submission. Title: Towards Trustworthy Amortized Bayesian Inference with Deep Learning I pondered about the title for a long time and decided that we’re not far enough to remove the word "towards" (yet). Exciting times ahead!

Apply to work with Antoine and team on high-impact topics in probabilistic machine learning! 👇

This is awkward, François Chollet.

Ullrich Köthe talks about generative modeling for inverse problems at tomorrow's Approximate Bayesian Inference seminar. ⏰ TOMORROW October 31, 11.00am UK time 📍 Online (MS Teams) 👇 Sign up to the mailing list below to get the link!

The ELLIS PhD program ELLIS is the best place for an AI/ML PhD in Europe 🇪🇺 👉 Apply by November 15, 2024! 👈 I compiled some resources on ELLIS and AI/ML PhD applications in this thread: x.com/MarvinSchmittM…

📣We're hiring! Join the Computational Behavior Lab (CBL) and the new ELLIS Institute Finland. We're looking for PhD students with cross-disciplinary mindsets. Be part of a push to develop better human models for better AI! Deadline Nov 15.

Why do you have a character limit on reviews AISTATS Conference? I just had to *shorten* my review to fit into the character limits. This meant removing suggestions for authors to address my concerns. That's a pity, especially for ECRs who would appreciate concrete pointers + tips.

Fantastic news for the global AI/ML landscape! 🇪🇺🇨🇦

My work just reached 100 citations on Google Scholar. It might be small for many others, but it means a lot to me. I started my PhD with no research experience, and I’ve learned so much ever since. Thank you to my mentors, collaborators, and everyone who engaged with my work 🧡

What’s obvious to you might be amazing to others.

Thank you Vincent Fortuin @vincefort.bsky.social Mark van der Wilk Emtiyaz Khan for organising this great Schloss Dagstuhl workshop! dagstuhl.de/24461

BayesFlow 2.0, a Python package for amortized Bayesian inference, is now powered by Keras 3, with support for JAX, PyTorch, and TF. Great tool for statistical inference fueled by recent advances in generative AI and Bayesian inference. (Links in next tweet)