Meta has released a model that predicts brain activation for visual and auditory inputs, and language. The trained model is available to download.
https://ai.meta.com/blog/tribe-v2-brain-predictive-foundation-model/
I'd love to chat with anyone about how they could use this in their research. I feel it could be very helpful for hypothesis generation -- and maybe for some kinds of projects, rather than a real replication, you could do a "virtual replication" :)
Cheers Beth