MedARC
@MedARC_AI
Followers
6K
Following
112
Media
22
Statuses
121
Medical AI Research Center (MedARC) Unlocking new possibilities in medical AI research. Supported by @SophontAI Founded by @iScienceLuvr
Joined January 2023
We're excited to announce that we're officially re-launching MedARC! 🚀 MedARC is an open science research collective, aimed to accelerate medical AI via a collaborative science-in-the-open approach. (1/5)
2
15
99
Check out OpenMidnight, our SOTA pathology foundation model. Available on HuggingFace! This model can be fine-tuned for a variety of usecases: - classifying cancer type - segmenting cells and tissue - predicting genes activity from pathology image and so much more!
Excited to share our latest @SophontAI release 🥳 "How to Train a State-of-the-Art Pathology Foundation Model with $1.6k" We present OpenMidnight, our first pathology foundation model! It has SOTA perf. despite being only trained on 12k whole slide images w/ $1.6k compute!
6
32
159
Families of 4 in 2025 paid the following for their healthcare as members of CrowdHealth: Jan - $475 Feb - $460 March - $445 April - $460 May - $505 June - $505 July - $445 Aug - $475 Sept - $475 Oct - $475 Nov - $505 Dec - $490 Total - $5,715 Members pay the first $500 of any
42
52
502
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!
6
21
128
Excited to share our latest @SophontAI release 🥳 "How to Train a State-of-the-Art Pathology Foundation Model with $1.6k" We present OpenMidnight, our first pathology foundation model! It has SOTA perf. despite being only trained on 12k whole slide images w/ $1.6k compute!
28
78
455
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.
13
11
96
Sharing our work on training fMRI neuroimaging foundation models, to be presented at FMs for Brain & Body NeurIPS 2025 workshop Although this was an internal Sophont research project, we are now expanding this at MedARC If you're interested in contributing, join us in Discord!!
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!
0
3
11
Our team is working hard and doing great work, we have some cool research stuff to share this month, excited to release! Be sure to follow @SophontAI and @MedARC_AI if you want to stay up to date!
4
6
52
yes we are! https://t.co/oMtBl93jze we also have open-source RL medical LLM research in @MedARC_AI discord
@iScienceLuvr Are you guys hiring RL people? Would be awesome to be able to have some compute to do RL experiments on med data
2
5
57
At @MedARC_AI we are building a comprehensive suite of medical LLM evals, and we already have tons of volunteers and lots of great progress! The project started less than a week ago! Are there other medical LLM evals we should include?
10
9
88
Excited to announce that @SophontAI has raised $9.22M in combined pre-seed+seed rounds! 🚀🔥 Led by @KindredVentures, with participation from @delphi_ventures @upfrontvc @AICONIC_VC also @jeffdean, @logankilpatrick, @ClementDelangue (via Factorial Capital), @l2k & others
90
43
531
IMO a challenge limiting modern medical AI is that data + domain expertise are in hospitals & academia but they have no compute + AI talent. Industry can do large-scale AI training, but little domain expertise and medical data. With @MedARC_AI + @SophontAI, we hope to create a
6
6
52
To get involved, join our Discord server: https://t.co/2lLbN05h59 Learn more about how we work on our website:
medarc.notion.site
Open science research collective to support medical AI projects.
0
0
10
We currently have 3 projects open to collaboration: 1. Histopathology foundation model 2. fMRI foundation model 3. Real-time brain-to-image reconstruction More projects coming soon! (4/5)
1
1
13
Our science-in-the-open approach means anyone can follow our projects in real time, contribute code or ideas, & earn co-authorship on peer-reviewed papers and top-tier conference submissions. We provide compute to volunteers to accelerate our research. (3/5)
1
0
8
We are supported by @SophontAI, a public benefit corporation that operates MedARC and separately facilitates commercial projects with medtech, hospitals, and pharma R&D. (2/5)
1
0
11
Nice work by MedARC team!
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!
1
0
8
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!
5
17
134
Lovely summary of the incredible achievements from @MedARC_AI s/o to all my collaborators and MedARC volunteers who enabled this research
I want to say I'm really proud of the work we've done at @MedARC_AI over the past 2 years since its inception: • Published landmark papers on fMRI-to-image "mind-reading" (MindEye and MindEye2) • Published (in collaboration with Stanford) two landmark papers on chest X-ray
1
3
26
Extremely grateful to work with Paul and Tanishq on Brain fMRI decoding (MindEye2) and present it at Vienna last year. We are working on the Algonauts 2025 challenge, feel free to join!
I want to say I'm really proud of the work we've done at @MedARC_AI over the past 2 years since its inception: • Published landmark papers on fMRI-to-image "mind-reading" (MindEye and MindEye2) • Published (in collaboration with Stanford) two landmark papers on chest X-ray
1
4
6
I want to say I'm really proud of the work we've done at @MedARC_AI over the past 2 years since its inception: • Published landmark papers on fMRI-to-image "mind-reading" (MindEye and MindEye2) • Published (in collaboration with Stanford) two landmark papers on chest X-ray
12
19
158