Very proud to have worked on this project with an incredible team!

I am pleased to announce the release of github.com/probml/sts-jax, which is a library for structural time series forecasting in JAX, built on top of dynamax. Thanks to Xinglong for doing most of the heavy lifting!

Come help us build the next generation of numerical computing and machine learning software! Join the JAX team at Nvidia to invent the future :) #computing #machinelearning #hiring lnkd.in/ePbhfVpD 🔥 🔥 🔥

The trilogy is complete! My "Advanced Topics" book is officially released today. Buy it on Amazon, or get it for free at probml.github.io/pml-book/book2….

Announcing a new #JAX and #Equinox nonlinear optimisation library: ⭐️ Optimistix ⭐️ (GitHub: github.com/patrick-kidger…) - Minimisation - Nonlinear least-squares - Root-finding - Fixed-points With blazing fast compile times and fast run times 🔥 1/7

Interested in working on Bayesian neural networks/ deep ensembles? Here's a reading list to get you started! I've taken away alot of the clutter and tried to include the main papers from most major groups and when the predictive task is classification. ⬇️ github.com/konstantinos-p…

(0/17) Grab your🍿 for a thread on some mysteries and explanations connecting flat minima, second order optimization, weight noise, gradient norm penalty, and activation functions😱 There is also a video presentation if you prefer: youtube.com/watch?v=HSwUqt…

If you watched my "Getting Started with CUDA for Python Programmers", and are ready to go even faster, then this new video is for you! Fast CUDA isn't just about having all the threads go brrrr in parallel, but also give them fast memory to play with. youtu.be/eUuGdh3nBGo

I've been wondering: can AI solve science? I just did some analysis... writings.stephenwolfram.com/2024/03/can-ai…

My friend Chenyang (twitterless) has written a nice tutorial on diffusion models, from the "projection onto manifold" perspective. My favorite part is the *extremely simple* pedagogical codebase, which I've been using myself for quick experiments. See: chenyang.co/diffusion.html

Can AI Solve Science? (podcast version with Q&A) now available on YouTube: youtu.be/goYaSkxG8LA?si…

If you know Torch, I think you can code for GPU now with OpenAI's Triton language. We made some puzzles to help you rewire your brain. Starts easy, but gets quickly to fun modern models like FlashAttention and GPT-Q. Good luck! github.com/srush/Triton-P…

This looks cool: Mathieu Blondel (Mathieu Blondel) and Vincent Roulet have posted a first draft of their book on arXiv: arxiv.org/abs/2403.14606

I was so lucky to be able to have Danny Kahneman as a best friend and collaborator for decades. He usually ended our conversations with "to be continued..." but I now have to simulate his part which is impossible. My favorite image of us "working".

Excited to share our latest story! We found disentangled memory representations in the hippocampus that generalized across time and environments, despite the seemingly random drift and remapping of single cells. This code enabled the transfer of prior knowledge to solve new tasks

& here are some of my favorite papers on the unification of flows and diffusion. What a decade!! (From my presentation here: bamos.github.io/presentations/…)

The first paper I’ve worked on as a PhD student is out! Very proud of this work.

Researchers from Harvard, Keyon Vafa (Keyon Vafa) and MIT, Peter Chang (ᴘᴇᴛᴇʀ ɢ. ᴄʜᴀɴɢ), Ashesh Rambachan (Ashesh Rambachan), and Sendhil Mullainathan (𝐒𝐞𝐧𝐝𝐡𝐢𝐥 𝐌𝐮𝐥𝐥𝐚𝐢𝐧𝐚𝐭𝐡𝐚𝐧) have published what I consider the most interesting study on the abilities of AI models in 2025. They wanted to address

If you’re at ICML, please come check out the World Models workshop I am co-organizing tomorrow!