The University of Notre Dame is hiring 5 tenure or tenure-track professors in Neuroscience, including Computational Neuroscience, across 4 departments. Come join me at ND! Feel free to reach out with any questions. And please share! apply.interfolio.com/173031

I am very happy to finally share something I have been working on and off for the past year: "The Information Dynamics of Generative Diffusion" This paper connects entropy production, divergence of vector fields and spontaneous symmetry breaking link: arxiv.org/abs/2508.19897

Students using AI to write their reports is like me going to the gym and getting a robot to lift my weights

Generative decisions in diffusion models can be detected locally as symmetry breaking in the energy and globally as peaks in the conditional entropy rate. The both corresponds to a (local or global) suppression of the quadratic potential (Hessian trace).

🧠✨How do we rebuild our memories? In our new study, we show that hippocampal ripples kickstart a coordinated expansion of cortical activity that helps reconstruct past experiences. We recorded iEEG from patients during memory retrieval... and found something really cool 👇(thread)

In continuous generative diffusion, the conditional entropy rate is the constant term that separates the score matching and the denoising score matching loss This can be directly interpreted as the information transfer (bit rate) from the state x_t and the final generation x_0.

Decisions during generative diffusion are analogous to phase transitions in physics. They can be identified as peaks in the conditional entropy rate curve!

I'd put these on the NeuroAI vision board: @tyrellturing.bsky.social's Deep learning framework www.nature.com/articles/s41... @tonyzador.bsky.social's Next-gen AI through neuroAI www.nature.com/articles/s41... @adriendoerig.bsky.social's Neuroconnectionist framework www.nature.com/articles/s41...

Very excited that our work (together with my PhD student @gbarto.bsky.social and our collaborator Dmitry Vetrov) was recognized with a Best Paper Award at #AABI2025! #ML #SDE #Diffusion #GenAI 🤖🧠

I am very happy to share our latest work on the information theory of generative diffusion: "Entropic Time Schedulers for Generative Diffusion Models" We find that the conditional entropy offers a natural data-dependent notion of time during generation Link: arxiv.org/abs/2504.13612

Flow Matching in a nutshell.

I will be at #NeurIPS2024 in Vancouver. I’m looking for post-docs, and if you want to talk about post-doc opportunities, get in touch. 🤗 Here’s my current team at Aalto University: users.aalto.fi/~asolin/group/

Can language models transcend the limitations of training data? We train LMs on a formal grammar, then prompt them OUTSIDE of this grammar. We find that LMs often extrapolate logical rules and apply them OOD, too. Proof of a useful inductive bias. Check it out at NeurIPS: nips.cc/virtual/2024...

Excited to speak at the ELLIS ML4Molecules Workshop 2024 in Berlin! moleculediscovery.github.io/workshop2024/

Can we please stop sharing posts that legitimate murder? Please.

Our team at Google DeepMind is hiring Student Researchers for 2025! 🧑‍🔬 Interested in understanding reasoning capabilities of neural networks from first principles? 🧑‍🎓 Currently studying for a BS/MS/PhD? 🧑‍💻 Have solid engineering and research skills? 🌟 We want to hear from you! Details in thread.

Diffusion models create beautiful novel images, but they can also memorize samples from the training set. How does this blending of features allow creating novel patterns? Our new work in Sci4DL workshop #neurips2024 shows that diffusion models behave like Dense Associative Memory networks.

The naivete of these takes is always amusing They could be equally applied to human beings, and they would work as well

I have always been saying that diffusion = flow matching. Is it supposed to be some sort of news now??

I am very excited to share our new Neurips 2024 paper + package, Treeffuser! 🌳 We combine gradient-boosted trees with diffusion models for fast, flexible probabilistic predictions and well-calibrated uncertainty. paper: arxiv.org/abs/2406.07658 repo: github.com/blei-lab/tre... 🧵(1/8)

A common question nowadays: Which is better, diffusion or flow matching? 🤔 Our answer: They’re two sides of the same coin. We wrote a blog post to show how diffusion models and Gaussian flow matching are equivalent. That’s great: It means you can use them interchangeably.

I'm still cautiously optimistic that we'll find a way to leverage Bayesian ideas in "Modern" AI without retrofitting. However, I'm very much an agnostic when it comes the philosophy of uncertainty (Bayes vs frequentist vs imprecise etc.)

🌟 New Research Alert! 🌟 Excited to share our latest work (accepted to NeurIPS2024) on understanding working memory in multi-task RNN models using naturalistic stimuli!: with @takuito.bsky.social and @bashivan.bsky.social #tweeprint below:

Asking the following earnestly: what is the strongest case for GANs standing the "test of time"? Are they important 10 years later in modern ML research? How have they influenced the way we think about generative models today?

The sbi package is growing into a community project 🌍 To reflect this and the many algorithms, neural nets, and diagnostics that have been added since its initial release, we have written a new software paper 📝 Check it out, and reach out if you want to get involved: arxiv.org/abs/2411.17337

The HPV vaccine has been recommended in the US since 2006. New study out today shows that cervical cancer deaths in young women in the years that followed have plummeted, decreasing 15% per year from 2013-2015. jamanetwork.com/journals/jam...

congratulations, @ian-goodfellow.bsky.social, for the test-of-time award at @neuripsconf.bsky.social! this award reminds me of how GAN started with this one email ian sent to the Mila (then Lisa) lab mailing list in May 2014. super insightful and amazing execution!

Anne Gagneux, Ségolène Martin, @quentinbertrand.bsky.social Remi Emonet and I wrote a tutorial blog post on flow matching: dl.heeere.com/conditional-... with lots of illustrations and intuition! We got this idea after their cool work on improving Plug and Play with FM: arxiv.org/abs/2410.02423

I made a starter pack for machine learning researchers working on Bayesian optimization and Gaussian processes! It's *very* sparse ATM since the migration is still in progress. Please reply to make me aware of people - potentially yourself - who should be added to it! go.bsky.app/QYMEQ52

Flow Matching in a nutshell.

Imagine that double Spiderman meme, but with generative AI pointing back at statistical mechanics. A neat paper in #JPCL on performing thermodynamic integration using denoising diffusion models #CompChem #CompChemSky pubs.acs.org/doi/10.1021/...

Hello world! Excited to (re)share from X our new paper on "Diffusion Model Predictive Control" (D-MPC). Key idea: leverage diffusion models to learn a trajectory-level (not just single-step) world model to mitigate compounding errors when doing rollouts. arxiv.org/abs/2410.05364 🧵 1/4

Topological & geometrical machine learning starter pack go.bsky.app/HnBdLJU

Prior specification is one of the hardest tasks in Bayesian modeling. In our new paper, we (Florence Bockting, @stefanradev.bsky.social and me) develop a method for expert prior elicitation using generative neural networks and simulation-based learning. arxiv.org/abs/2411.15826

Our group at Google DeepMind is now accepting intern applications for summer 2025. Attached is the official "call for interns" email; the links and email aliases that got lost in the screenshot are below.

The PCP theorem, a jewel of theoretical computer science, establishes that any NP statement can be assessed by a randomized verifier who only checks a vanishing fraction of the proof (indeed, a constant # of characters!) This has had incredible impact, most notably on how ML reviews are conducted

Welcome to the Crazy Rich Bayesian Starter Pack, folk who are/were vaguely into Bayesian reasoning but - with a few exceptions - don't shun the non-Bayesian. go.bsky.app/JYH5Z6M

1 of 4 linked commentaries on dynamic connectivity in Imaging Neuroscience, by Diego Vidaurre: Dynamic functional connectivity: Why the controversy? doi.org/10.1162/imag...

Just made a quick starter pack for those who create #neuroart and #brainart! Anyone who enjoys their art - please follow & share! 😊 And if I missed anyone, please post! 🧠🎨 go.bsky.app/PusdEwN

I have seen some anti-peer-review takes on here, and, believe me, I understand the frustrations, but I would urge caution before doing or publicly saying anything too drastic. We live in age rife with misinformation and anti-intellectualism—not everyone wants academia to survive

Generative decisions in diffusion models are made at special critical time points. Missing these points with a fast sampler results in loss of diversity. It's like missing an exit in the highway! Paper: openreview.net/forum?id=lxG...

Applications are now open for the Warwick Centre for Doctoral Training in Statistics. Follow the links below to apply, or to register for our open day on Wednesday. warwick.ac.uk/fac/sc... warwick.ac.uk/fac/sc...

Some of us care about GPs!

Huge congrats to @karyna-mi.bsky.social for her paper published today in Science! She found that the hippocampus is really important for a key strategy we use to make decisions called hidden state inference! 🧪 🧠https://www.science.org/doi/10.1126/science.adq5874 1/7

I know that you guys do not care much about GPs, but I am very proud of this solo paper where I defined smooth non-mean reverting kernels! openreview.net/forum?id=6CV...

Not to believe in some form of afterlife violates several scientific principles: 1) the human mind is an arbitrarely defined object and 2) information is always preserved. The prevaling belief among scientists results from 19th century naive materialism and an anti-religious sentiment.

By demand, I've created the final starter pack in my ML Personality Starter Pack Series. I'm uncertain who belongs in this starter pack and so if you think you better fit in the Grumpy ML or Unreasonably Upbeat ML starter packs, let me know. (Self) nominations welcome go.bsky.app/5Suyk58

4/ I think the proper definition is that #NeuroAI is the realization of the original promise of cybernetics and connectionism! en.wikipedia.org/wiki/Cyberne... en.wikipedia.org/wiki/Connect... It is a general science of intelligence focussed on parallel distributed systems, control, and learning.