Pinned
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.
Sophont
142 posts
Sophont
@SophontAI
Open medical superintelligence.
WE'RE HIRING! (see website)
Joined March 2025
- 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!
- Sophont will build the future of medical AI and healthcare
- Our CEO will be speaking on Sun at the Nous Research hackathon, be sure to check it out!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:
- Glad to be sponsoring this workshop! If you are working in this space, be sure to submit a paper!Excited to announce the Foundation Models for the Brain and Body workshop at #NeurIPS2025!🧠 We invite short papers or interactive demos on AI for neural, physiological or behavioral data. Submit by Aug 22 👉 brainbodyfm-workshop.github.io
- Replying to @SophontAIWe'll be presenting this work at the NeurIPS 2025 Foundation Models for the Brain and Body Workshop! code: github.com/MedARC-AI/fmri… discord: discord.com/invite/tVR4TWn… abs: arxiv.org/abs/2510.13768
- 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 have some exciting company news to share tomorrow! (in several hours) 😊
- Congrats to Paul and Connor at Sophont and the rest of the team! Great work!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!
- Replying to @SophontAISpecial thanks to @fal for providing compute. Also thanks to all the other collaborators in @MedARC_AI
- Replying to @SophontAITo 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
- WE'RE HIRING !!Announcement 📢 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)
- We're glad to have you join us! 🔥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.
- Replying to @SophontAIWe 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.
