Excited about this line of work. Pretrained models are surprisingly resilient to architecture modification, opening up entirely new options for customization and optimization: operator swapping, rewiring depth into width, and more.

One of the best ways to reduce LLM latency is by fusing all computation and communication into a single GPU megakernel. But writing megakernels by hand is extremely hard. 🚀Introducing Mirage Persistent Kernel (MPK), a compiler that automatically transforms LLMs into optimized

Getting mem-bound kernels to speed-of-light isn't a dark art, it's just about getting the a couple of details right. We wrote a tutorial on how to do this, with code you can directly use. Thanks to the new CuTe-DSL, we can hit speed-of-light without a single line of CUDA C++.

It’s time for the American AI community to wake up, drop the "open is not safe" bullshit, and return to its roots: open science and open-source AI, powered by an unmatched community of frontier labs, big tech, startups, universities, and non‑profits. If we don’t, we’ll be forced

I am very excited to take up the role of chief scientist for meta super-intelligence labs. Looking forward to building asi and aligning it to empower people with the amazing team here. Let’s build!

Omar Sanseviero great release, tho you forgot to include the SoTA in the chart: LFM2-350M Liquid AI

I believe LLMs will inevitably surpass humans in coding. Let us think about how humans actually learn to code. Human learning of coding has two stages. First comes memorization and imitation: learning syntax and copying good projects. Then comes trial and error: writing code,

Welcome to the age of generative genome design! In 1977, Sanger et al. sequenced the first genome—of phage ΦX174. Today, led by Samuel King, we report the first AI-generated genomes. Using ΦX174 as a template, we made novel, high-fitness phages with genome language models. 🧵

A careful study of architecture transfer dynamics, to be presented as oral at NeurIPS 2025 (top 0.3% of all submissions). Advances in grafting methods significantly accelerate research on architecture design, scaling recipes, and even post-training.

Fun explainer about Evo2 and its architecture, StripedHyena 2. Hybrids are so 2023, multi-hybrids are the future!

We just released the largest open-source diffusion language model (RND1). RND1 is important to me on a personal level: it symbolizes our commitment to open-source exploration of radically different designs for AI at scale — training objectives, architectures, domains. There is

Sliding window attention (SWA) is powering frontier hybrid models for efficiency. Is there something better? Introducing Phalanx, a faster and better quality drop-in replacement for sliding window attention (SWA). Phalanx is a new family of hardware and numerics-aware windowed

Thank you for having me, Delta Institute! We touched on a few topics, including the story behind Radical Numerics