Researching visual imagery? Consider submitting to this new cross-journal special issue on visual imagery at Nature Communications, Communications Psychology, and Scientific Reports! We welcome a broad range of topics and methods - more info below 👇 www.nature.com/collections/...

1/2) How do patterns form in diffusion models? Out-of-equilibrium phase transitions! Symmetry breaks → low-frequency modes destabilize → large-scale structure emerges. The peper offers a statistical field theory analysis of this process! Link: arxiv.org/abs/2603.20092

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 🤖🧠

Tim G. J. Rudner@timrudner.bsky.social · last yr.

Congratulations to the #AABI2025 Workshop Track Outstanding Paper Award recipients!

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.)

Desi R Ivanova@desirivanova.bsky.social · 2y ago

It’s hot takes Friday 😅 probapproxincorrect.substack.com/p/some-thoug...

🌟 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?

Jeff Clune@jeffclune.com · 2y ago

Ironically, while I love GANs, one could argue they did NOT stand the test of time....as they've mostly disappeared from modern ML. Also fun, I remember being in the room for Ilya's talk of this paper (right after our talk on How transferable are features in deep neural networks?").

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

sbi reloaded: a toolkit for simulation-based inference workflows

Scientists and engineers use simulators to model empirically observed phenomena. However, tuning the parameters of a simulator to ensure its outputs match observed data presents a significant challeng...

arxiv.org