Cajal-1, a 218-million-parameter model trained on fMRI data from 2,000 people, beat TRIBE v2 by 25% accuracy and came closer to real brain activity in 27 of 32 recordings on Meta's held-out films.
Summaries like this, in your inbox every morning.
Pick your industry and the AI tools you use, and get news related to your work every day.
Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →
Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.
LSTC, Hokkaido University and Fujifilm said they will jointly develop an AI medical image-processing system, w…
AstraZeneca has partnered with Oracle to apply AI to its clinical trials, Reuters reported
Pfizer has introduced an internal program called Fluency aimed at building AI skills across its workforce
Dr. Stephen Hoge, President of Moderna, discussed AI and the future of healthcare in a conversation with Black…
LSTC, with Rapidus and the University of Tokyo, plus Hokkaido University and Fujifilm, said on the 20th it wil…
Lunit will present five abstracts at ESMO 2026 (Madrid, Oct 23–27) using its Lunit Scope platform, including f…
