@humanscotti: CortexMAE, our fMRI foundation model preprint is out (accepted to ICML)! we trained an image foundation model on flat m…
Summary
CortexMAE is a family of fMRI foundation models trained on 2.1K hours of open fMRI data, accepted to ICML. The release also includes Brainmarks, an open benchmark suite for evaluating such models.
View Cached Full Text
Cached at: 05/30/26, 06:30 AM
CortexMAE, our fMRI foundation model preprint is out (accepted to ICML)!
we trained an image foundation model on flat map brain scans instead of natural images
i believe this is the way forward to extract the most signal from fMRI, whereas traditional preprocessing just treats
Sophont (@SophontAI): NEW RELEASE:
Today we’re releasing CortexMAE: a family of fMRI foundation models trained on 2.1K hours of open fMRI data.
We’re also releasing Brainmarks: an open benchmark suite for evaluating fMRI foundation models.
Full paper is on arXiv (accepted to ICML 2026)
A thread:
Similar Articles
@iScienceLuvr: Learning Sparse Latent Predictive Foundation Model for Multimodal Neuroimaging This paper introduces Neuro-JEPA, a foun…
This paper introduces Neuro-JEPA, a foundation model that uses a latent predictive objective and Mixture-of-Experts architecture to encode brain MRI scans across T1w, T2w, and FLAIR sequences, pretrained on a large dataset of 1.55 million scans.
@mustafasuleyman: Super excited to announce seven new world-class MAI models today. They represent what we consider a new era in AI desig…
Microsoft announces seven new MAI models, including a strong reasoning model (MAI-Thinking-1) and coding model (MAI-Code-1-Flash), along with Frontier Tuning for enterprise customization.
@ClementDelangue: OpenAI dropped a new model on HF today!
OpenAI released a new model on Hugging Face today.
@adithya_s_k: Wake up ppl Huggingface just open sourced Genomic Foundational Models
Huggingface has open-sourced genomic foundational models, including Carbon, a DNA model that is 275x faster than the next best model and can process the entire human genome on a single GPU in under 2 days.
@eliebakouch: one of my favorite projects is Marin from the stanford folks, they have a scientific approach to training, are ready to…
Marin is an open-source framework from Stanford for reproducible foundation model research, covering data curation, tokenization, training, and evaluation; it was used to train an 8B parameter model that outperforms Llama 3.1 8B.