Pinned
🧠👁️Our MindEye2 preprint is out!
We reconstruct seen images from fMRI brain activity using only 1 hour of training data.
This is possible by first pretraining a shared-subject model using other people's data, then fine-tuning on a held-out subject with only 1 hour of data.🧵
![Blind men (unimodal models) incorrectly diagnosing an elephant (patient) because they are only concerned with a specific body part (medical modality)
[posted to Elon Musk's X]](https://pbs.twimg.com/media/GnZL4GuawAAmtVO?format=webp&name=medium)
