Sophont will be at CVPR 2026!
We will be cohosting a social on June 4th, come join us! (link in reply)
Additionally, our CEO @iScienceLuvr will be speaking at the Med-Reasoner workshop.
Excited to share our first paper:
Scaling Vision Transformers for Functional MRI with Flat Maps
We introduce a new approach to training fMRI neuroimaging foundation models and demonstrate a strict dataset power scaling law!
Our RL Environments Hackathon in San Francisco is this coming Sunday, May 18th, and today we are announcing our speakers and judges - be sure to sign up if you haven't!
Speakers from:
@MistralAI, @SophontAI, @haizelabs, @EdgeAGI, @NousResearch, and @axolotl_ai
Judges from:
Excited to announce the Foundation Models for the Brain and Body workshop at #NeurIPS2025!๐ง
We invite short papers or interactive demos on AI for neural, physiological or behavioral data.
Submit by Aug 22 ๐ brainbodyfm-workshop.github.io
NEW RELEASE:
"How to Train a State-of-the-Art Pathology Foundation Model with $1.6k"
We present OpenMidnight, a our first pathology foundation model, trained on just whole-slide images for only $1.6K!
We open-source model weights and reproducible training code!
We came in 4th place in the @AlgonautsProj 2025 challenge! Goal was to predict brain activity to movie watching.
Incredibly lucky to work w/ @MedARC_AI team where we got very competitive results despite the simplest model arch (no transformers, just conv + linear)
Paper below!
To train ViTs on sequences of fMRI flat maps, we adopt the spatiotemporal masked autoencoder (MAE) framework.
We pretrain our flat map MAE (fm-MAE) using 2.3K hours of publicly available preprocessed fMRI data from the Human Connectome Project (HCP). We also validate on the
Announcement ๐ข
We're hiring at @SophontAI for a variety of positions!
We're looking for exceptional, high-agency ML research scientists/engineers who are passionate about using AI to build the future of healthcare.
Check our website for more details (link in 2nd tweet)
Some personal news: I've joined @SophontAI to help build the next generation of open medical foundation models.
We've relaunched @MedARC_AI, our open science research community. Join us if you want to help advance open medical AI.
And we are hiring.
We also evaluate performance on cognitive state decoding, sex classification, and image label classification. We observe how performance is impacted by dataset size, model size, and temporal patch size.