I'm at New York for the meeting on Physics of Learning. You can join us online. (And if you are interested in collaborating on WM/control, pls DM me.)

We are having our first @SimonsFdn yearly meeting on the Physics of Learning and Neural Computation Sept 24th-25th and all are welcome to join on this zoom: simonsfoundation.zoom.us/j/9… We have an excellent set of speakers. Here is the agenda: simonsfoundation.org/event/s… Join our webinar starting Sept 24th 9:30am ET to learn how the structure of data, architectures, and learning dynamics conspire to empower AI to learn, scale, compute, imagine, reason and collaborate! See physicsoflearning.org/ for more about our collaboration.

Cool, but future prediction ≠ world modelling

RT @shervin: Media should refer to the Islamic Republic and not Iran. Iran and the Iranian people are different than the terrorist Islamic…

Are frontier LLMs trained across datacenters? One thing is certain: if the pre-training optimizer’s critical batch size is too small, they are NOT! Excited to announce MuLoCo, a pre-training optimizer that can efficiently pre-train across datacenters while having large enough batch sizes to warrant doing so. 🧵1/N

Dear partners in Europe, it is time to act.

I've spent the past week anxiously following the news in Iran. Protests in the last few days have escalated and taken a dark turn. Thousands have been killed or arrested, and the government has cut off phone and internet access, leaving tens of millions of people unable to communicate.  My heart goes out to the innocent people who are affected by all this, including Iranians who live in the US and elsewhere. ❤️ Many are attempting to continue their studies or work and get through their daily lives under the immense pressure of wondering what's happening in Iran. Some who are financially supported by their families in Iran are in need now. Some may have lost friends or family members. Many can’t even contact their family members to know if they’re safe. There are others who might have traveled home to Iran for Xmas and are now stuck, unable to get a flight back.   Even those who aren't directly impacted are silently carrying an emotional burden. I've spent much of the past week feeling helpless and longing for some way to help or be involved. I miss the city of my birth and feel the suffering of the people there.  If you're reading this and you work with anybody from Iran, be mindful of what they might be going through. Consider giving them space and understanding, extending deadlines, offering tuition relief.... or just a hug. Much love and hope. ❤️

Glad to be at @Stanford for the kick off event of the @SimonsFdn Collaboration on the Physics of Learning and Neural Computation.

1/ Today with my colleagues @PolymathicAI, I'm excited to release our latest project, Walrus, a cross-domain foundation model for physical dynamics, into the world. polymathic-ai.org/blog/walru… Paper: arxiv.org/abs/2511.15684 Git: github.com/PolymathicAI/walr… HF: huggingface.co/polymathic-ai…

We have 14 survey lectures for our @SimonsFdn Collaboration on the Physics of Learning and Neural Computation! All videos available at: physicsoflearning.org/webina… Here is the list: @zdeborova: Attention-based models and how to solve them using tools from quadratic networks and matrix denoising @KempeLab: Recent lessons from LLM reasoning @MBarkeshli: Sharpness dynamics in neural network training @KrzakalaF: How Do Neural Networks Learn Simple Functions with Gradient Descent? Michael Douglas: Mathematics, Economics and AI Yuhai Tu: Towards a Physics-based Theoretical Foundation for Deep Learning: Stochastic Learning Dynamics and Generalization @SuryaGanguli: An analytic theory of creativity for convolutional diffusion models Eva Silverstein: Hamiltonian dynamics for stabilizing neural simulation-based inference @adnarim066: Generation with Unified Diffusion Bernd Rosenow: Random matrix analysis of neural networks: distinguishing noise from learned information @jhhalverson Nerual networks and conformal field theory @KempeLab Synthetic data: friend or foe in the age of scaling @WyartMatthieu Learning hierarchical representations with deep architectures @CPehlevan Mean-field theory of deep network learning dynamics and applications to neural scaling laws

I’m excited to announce that @PolymathicAI new astrophysics model, AION-1, has been accepted to #neurips2025 ! 🎉 Come see our poster on Dec 5 (Friday) at 1-4pm PT, poster session 5 OR hear our talk from @liamhparker and Francois Lanusse at #AI4Science workshop It’s the first large-scale multimodal foundation model for astronomy!

I gave a talk on LLM zero-sum learning dynamics last week at MSR Montreal. I went over a few things that were not in the paper but that I'm particularly excited about; one of those is the connection between generalization and zero-sum learning. youtu.be/UyK3DgWY7yw

(1/n) Until recently, even strong LLMs struggled with USAMO/IMO problems. This year, specific model variants from Google and OpenAI’s were reported to solve 5/6 IMO problems. In our recent work, we asked a relevant question: Can we grade proofs fairly with partial credit using LLMs?

Introducing nanoAhaMoment: Karpathy-style, single file RL for LLM library (<700 lines) - super hackable - no TRL / Verl, no abstraction💆‍♂️ - Single GPU, full param tuning, 3B LLM - Efficient (R1-zero countdown < 10h) comes with a from-scratch, fully spelled out YT video [1/n]

How can we design human-interpretable AI models to explain why neurons behave as they do? Excited to share our recent work, a collaboration between three research groups from @Harvard. @SaraM306 @fullerene12 @temereanca @naoshigeuchida @VMurthyLab @paul_masset @dunbar_ba 1/21

How does #AI compare to the nuanced reasoning of clinicians in #Psychiatry? Our latest #Review revisits Meehl’s factors, bridging the human and machine reasoning gap to advance interdisciplinary collaboration doi.org/10.1016/j.psychres.2…🧠🤖 Big kudos to @ChristopheGauld & dream team!

Brains as dynamical systems! 💯