I'm happy to announce that v2 of my RL tutorial is now online. I added a new chapter on multi-agent RL, and improved the sections on 'RL as inference' and 'RL+LLMs' (although latter is still WIP), fixed some typos, etc. arxiv.org/abs/2412.05265…

🚨 As a 𝗡𝗲𝘂𝗿𝗜𝗣𝗦 𝟮𝟬𝟮𝟱 𝗖𝗼𝗺𝗽𝗲𝘁𝗶𝘁𝗶𝗼𝗻𝘀 𝗖𝗵𝗮𝗶𝗿 with Qin Tao and Kun Zhang-in pursuit of Causality with ML, I want to highlight that the 𝗰𝗼𝗺𝗽𝗲𝘁𝗶𝘁𝗶𝗼𝗻 𝗽𝗿𝗼𝗽𝗼𝘀𝗮𝗹 𝗱𝗲𝗮𝗱𝗹𝗶𝗻𝗲 is coming up! 📅 𝗔𝗽𝗿𝗶𝗹 𝟭𝟯, 𝟮𝟬𝟮𝟱 🔗 neurips.cc/Conferences/20… Excited to see creative

This is flying a bit under the radar. But in terms of damage to America’s innovation and knowledge supremacy, the chilling effect of these revocations on the country’s ability to attract and retain scientific talent likely dwarfs the impact of tariffs or other policies.

One of my PhD students got their visa revoked. I know of other cases amongst my AI colleagues. This is not what investing in US leadership in AI looks like.

x.com/i/article/1915…

Many recent posts on free energy. Here is a summary from my class “Statistical mechanics of learning and computation” on the many relations between free energy, KL divergence, large deviation theory, entropy, Boltzmann distribution, cumulants, Legendre duality, saddle points,

We’re thrilled to announce the launch of the MolSS Reading Group! 🚀 🔬 MolSS = Machine Learning for Molecular Simulations and Sampling 🔥 First session: June 3rd, 3 PM (UK time) by Jose Miguel Hernández-Lobato 🗓️ Regular sessions: Every other Tuesday at 4 PM (UK time), 45–60 minutes

Superposition means that models represent more features than dimensions they have, which is true for LLMs since there are too many things to represent in language. We find that superposition leads to a power-law loss with width, leading to the observed neural scaling law. (1/n)

We REALLY REALLY need a "Findings" for NeurIPS, ICLR, and ICML. 25,000 submissions at this year's NeurIPS represents extreme excess pressure. It takes valuable time away from legitimate new research. One question is how to administer it. I suggest that Findings go through a

What is the probability of an image? What do the highest and lowest probability images look like? Do natural images lie on a low-dimensional manifold? In a new preprint with Zahra Kadkhodaie Eero Simoncelli, we develop a novel energy-based model in order to answer these questions: 🧵

I'm fortunate to be able to devote my career to researching AI and building reasoning models like o3 for the world to use. If you want to join us in pushing forward the intelligence frontier, we're hiring at OpenAI.

This new work generalizes the recent Adjoint Sampling approach from Stochastic Control to Schrodinger Bridges, enabling measure transport between data and unnormalized densities. Achieves SOTA on large-scale energy-driven conformer generation. See thread by Guan-Horng Liu

🧵generative models are sweet, but navigating existing repositories can be overwhelming, particularly when starting a new research project so i built jax-interpolants, a clean & flexible implementation of the stochastic interpolant framework in jax github.com/nmboffi/jax-in…

In an hour, François and I are presenting at ICML our paper on crystalline material generation using diffusion models, where the key innovation is a diffusion process for the fractional coordinates that is inspired by kinetic Langevin dynamics. Paper: arxiv.org/abs/2507.03602

Lucky to be part of this incredible piece with summary of progress on many hot AI for Science areas!

🔬 Interested in AI4Science? 📢 2 Funded PhD positions at TU Wien in Learning on Graphs & Geometry with AITHYRA! 🗓 Apply by Sept 4, 2025 📍 Vienna, Austria 🔗 jobs.tuwien.ac.at/Job/256399 #PhD #AI4Science #MachineLearning #GeometricDeepLearning #TUWien #AITHYRA

Made by Google Oh yea! Forgot to mention - it's also a one-step diffusion model 😉

GDM is growing in APAC, this time in Singapore🇸🇬 Come join us to build AI responsibly to benefit users in APAC & beyond! Research Lead & Director: job-boards.greenhouse.io/deepmind/jobs/… Research Scientist & Engineer (Multimodal GenAI): job-boards.greenhouse.io/deepmind/jobs/… job-boards.greenhouse.io/deepmind/jobs/…

Consistency models, CTMs, shortcut models, align your flow, mean flow... What's the connection, and how should you learn them in practice? We show they're all different sides of the same coin connected by one central object: the flow map. arxiv.org/abs/2505.18825 🧵(1/n)

Looking forward to this workshop on ML4molecules at the ELLIS unconference (followed by EurIPS). Please submit your abstracts! The deadline will be extended to 15 October 2025.