Introducing the V-JEPA 2 world model and new benchmarks for physical reasoning Permalink
Meta Video Joint Embedding Predictive Architecture 2 (V-JEPA 2) is a world model that achieves state-of-the-art performance on visual understanding and predi...
Hello, I'm Matt, and I'm a research engineer on the Fundamental AI Research
(FAIR) team at Meta AI working on projects in computer vision, medical imaging,
and compression. On this site you'll find links to my publications, open-source
projects, and the occasional blog post.
Recent posts
Artificial Intelligence Reconstructs Missing Data from Rapid MRI Scans Permalink
Artificial intelligence (AI) can reconstruct coarsely-sampled, rapid magnetic resonance imaging (MRI) scans into high-quality images with similar diagnostic ...
Updating torchkbnufft to 1.0: Overview of Improvements
Today I am happy to announce the relase of version 1.0 of torchkbnufft. There are many changes: complex number support, an improved backend, a better density...
New AI research to help predict COVID-19 resource needs from a series of X-rays Permalink
Researchers, healthcare providers, and many others around the world are still grappling with COVID-19. Even a year into the pandemic, it remains challenging ...
Hello World
Website init. My goal for this website is mostly to host a collection of my academic and open-source work for those interested. On some occasions I may post ...