Vincent Fortuin

Fisher meets Feynman: score-based variational inference with a product of experts

Fisher meets Feynman! 🤝

We use score matching and a trick from quantum field theory to make a product-of-experts family both expressive and efficient for variational inference.

To appear as a spotlight @ NeurIPS 2025.
#NeurIPS2025 (link below)

The ELLIS Society welcomes its new Board. As the primary decision-making body, it will play a vital role in shaping the future of ELLIS and advancing #AI and #MachineLearning research across Europe in a time of global change.

Read the full article: ellis.eu/news/ellis-s...

🥲

Super cool stuff! And great to see that there's at least a small part of GDM left not doing Gemini...

Looks like an awesome workshop!

The #EurIPS Salon des Refusés poster session is now accepting submissions 📜

We welcome self-nomination of rejected submissions from all @neuripsconf.bsky.social tracks (Main, D&B, Position). The call for self-nominations will stay open until the session is filled

eurips.cc/salon-des-re...

Nice speech! And congrats 😊

✨ EurIPS registration is now open! Get one of the 1,500 tickets available. 500 tickets are discounted for students 🎓.

In Copenhagen 🇩🇰 on Dec 2-7, 2025.

❗ Entrance to the ELLIS UnConference is free with a #EurIPS ticket.

Get your ticket now: https://eurips.cc/

@euripsconf.bsky.social

ELLIS PhD Program: Call for Applications 2025 The ELLIS mission is to create a diverse European network that promotes research excellence and advances breakthroughs in AI, as well as a pan-European PhD program to educate the next generation of AI...

🎓 The application portal for the #ELLISPhD Program is open today! Info & link: https://bit.ly/45DSe75

EurIPS workshop on AmOrTIzED InfErENcE!!!1!

YouTube video by Machine Learning Street Talk The Real Reason Huge AI Models Actually Work

My full interview with MLStreetTalk has just been posted. I really enjoyed this conversation! We talk about the bitter lesson, scientific discovery, Bayesian inference, mysterious phenomena, and key principles for building intelligent systems. www.youtube.com/watch?v=M-jT...

Most of the #EurIPS workshops now have their websites online 🙌

A lot of them have active call for participation and/or papers, so if you see something relevant to your field of research please consider submitting!

Links for most workshops are available at: eurips.cc/workshops/

Looks like a good candidate paper for the Salon des Refusés at @euripsconf.bsky.social

And lastly, if @neuripsconf.bsky.social would choose to reverse the decisions on the papers affected by space constraints, we would be happy and able to accommodate their presentation

Fuck yeah

I love the Salon des Refusés idea!

Data Science at the Singularity A purported `AI Singularity' has been in the public eye recently. Mass media and US national political attention focused on `AI Doom' narratives hawked by social media influencers. The European Commis...

I reference data science at the singularity constantly as it's not just a model of why data science blew up, but also how any field or org can organize itself around data, code sharing, and benchmarks: arxiv.org/abs/2310.00865

Reevaluating Policy Gradient Methods for Imperfect-Information Games In the past decade, motivated by the putative failure of naive self-play deep reinforcement learning (DRL) in adversarial imperfect-information games, researchers have developed numerous DRL algorithm...

Our NeurIPS submission arxiv.org/abs/2502.08938 did not get in, but it's one of my favorite papers and I think one of the better papers we've ever put out so I want to highlight it

Post-hoc Probabilistic Vision-Language Models Vision-language models (VLMs), such as CLIP and SigLIP, have found remarkable success in classification, retrieval, and generative tasks. For this, VLMs deterministically map images and text descripti...

Unfortunately, our submission to #NeurIPS didn’t go through with (5,4,4,3). But because I think it’s an excellent paper, I decided to share it anyway.

We show how to efficiently apply Bayesian learning in VLMs, improve calibration, and do active learning. Cool stuff!

📝 arxiv.org/abs/2412.06014

For anyone who is spiraling, I definitely recommend www.positive.news for a nice palate cleanser and reminder that there are still things going right despite all the garbage fires

I wrote a response to Thomas Friedman's "magical thinking" on AI here: aiguide.substack.com/p/magical-th...

Martingale posterior distributions The prior distribution on parameters of a sampling distribution is the usual starting point for Bayesian uncertainty quantification. In this paper, we present a different perspective which focuses on ...

This is years old at this point. Still very underrated and little known. arxiv.org/abs/2103.15671

Reinforcement Learning: An Overview This manuscript gives a big-picture, up-to-date overview of the field of (deep) reinforcement learning and sequential decision making, covering value-based methods, policy-based methods, model-based m...

Reminded again of Kevin Murphy's excellent RL overview: arxiv.org/abs/2412.05265
A lot of the stuff covered here really is at the cutting edge and not compiled so nicely anywhere else

Possibly one of the best PhD programs in the world if you are passionate about machine learning and AI:

🚨AISTATS workshop proposals open!

Big News: For the first time, there will be a day of workshops at #AISTATS 2026, in Tangier, Morocco 🌴🇲🇦

Quentin Berthet @qberthet.bsky.social and I are workshop chairs.

virtual.aistats.org/Conferences/...
Deadline: Oct 17, AOE

Let's push for the obvious solution: Dear @neuripsconf.bsky.social ! Allow authors to present accepted papers at EurIPS instead of NeurIPS rather than just additionally. Likely, at least 500 papers would move to Copenhagen, problem solved.

Agustinus is hiring! A great place to start a research journey.

EurIPS is coming! 📣 Mark your calendar for Dec. 2-7, 2025 in Copenhagen 📅

EurIPS is a community-organized conference where you can present accepted NeurIPS 2025 papers, endorsed by @neuripsconf.bsky.social and @nordicair.bsky.social and is co-developed by @ellis.eu

eurips.cc

Ruining art with Gemini 2.5 Flash. (These are all the prompts, in their entirety)

"make this painting less gloomy"
"it is still pretty disturbing, make it less gloomy emotionally"
"even less gloomy"

We are excited to bring #EurIPS 2025 to Copenhagen in December.

Consider becoming a sponsor and support us in making this inaugural event a success! Sponsorship packages are available and can be further customized if necessary.

Reach out if you have any questions ❔
Info: eurips.cc/become-spons...