Sign in

Martin Schrimpf

@mschrimpf.bsky.social
2.9K followers 64 following 96 posts

NeuroAI Prof @EPFL & co-founder Dandelion. 🤖🧠 Brain Models to Understand + Treat the Mind. Brain-Score, MIRAGE, dysfunction. prev PhD @MIT, ML @Salesforce, Neuro @HarvardMed, co-founder @Integreat. 🇨🇭 www.mschrimpf.com

PostsRepliesMedia
Reposted by Martin Schrimpf
Rob Mok @robmok.bsky.social · 30/08/2026
📢 Announcing the 11th CiNet Conference: "From Biological to General Artificial Intelligence: Computational and Experimental Approaches to Understanding and Modeling the Brain" 5–7 October 2026, CiNet, Osaka, Japan Organized by yours truly & Shinji Nishimoto #neuroskyence #psychscisky #mlsky 🧠🤖 1/
43017
Martin Schrimpf @mschrimpf.bsky.social · 01/09/2026
Hiring postdocs @EPFL: please reach out and/or apply to the AI Center fellowship www.epfl.ch/research/fun.... My #NeuroAI group is excited about testing and building models of brain and behavior, from sensory through language to cognition, and from healthy to dysfunction (treatment)! 🧠🤖🧪
epfl.ch
EPFL AI Center and Swiss AI Initiative Postdoctoral Fellowships
The 3rd call is now open with a submission deadline on 9 November 2026 17:00 (CET).
0158
Reposted by Martin Schrimpf
Hannes Mehrer @CCN2026 @hannesmehrer.bsky.social · 04/08/2026
"So, you have a highly predictive model, now what?" At this #CCN2026 event on Wed, 5 Aug, 4pm at NYU Skirball Theatre I will present work on using ANN brain models for visual prostheses (tinyurl.com/modelguidedm...) and for dyslexia (tinyurl.com/neuroaidysle..., first author: Melika Honarmand).
0124
Martin Schrimpf @mschrimpf.bsky.social · 04/08/2026
Come say hi at #CCN2026! Scaling laws for visual cortex, topographic multimodal models, video generation for the lateral stream, model-enabled applications, and a GAC on whether #NeuroAI is asking the right questions
0234
Reposted by Martin Schrimpf
Badr AlKhamissi @bkhmsi.bsky.social · 03/08/2026
Excited to be at #CCN2026 in NYC! I'll be presenting our spotlight poster, Topo-Omni, with @hannesmehrer.bsky.social 🧠 📍 Poster F14 — Session F 🗓️ Thursday, Aug 6 Come by if you're around, we'd love to talk about how our multimodal model can discover functionally selective brain regions!
1256
Reposted by Martin Schrimpf
Minds, Machines, and Brains (MMB) @mmb-journal.bsky.social · 02/08/2026
Hello world! 👋 We’re Minds, Machines, and Brains (MMB) 👤🤖🧠 a new open access journal from @mitpress.bsky.social exploring the principles of intelligence and cognition across natural and artificial minds. Submissions open this Fall! 🔗 direct.mit.edu/mmb
direct.mit.edu
Minds, Machines, and Brains | MIT Press
223793
Martin Schrimpf @mschrimpf.bsky.social · 22/07/2026
Hi Monica, my group works on NeuroAI: www.mschrimpf.com/ could you please add me to the feed?
mschrimpf.com
Martin Schrimpf
100
Martin Schrimpf @mschrimpf.bsky.social · 07/07/2026
Bonus: the clearest view of Mont Blanc I've ever witnessed, during our lab retreat!
020
Martin Schrimpf @mschrimpf.bsky.social · 07/07/2026
What a treat to host @dyamins.bsky.social at EPFL this past month to dig into the most impactful future of #NeuroAI. A few conclusions we landed on: 1. Task optimization is a powerful starting point for most (all?) brain systems 2. Brain data is the bottleneck 3. Major opportunities in applications
1100
Reposted by Martin Schrimpf
Yingtian (David) Tang @davidtyt.bsky.social · 07/07/2026
🚨 NEW PREPRINT Videos strongly shape activity across the visual cortex. But can we design videos that maximally drive specific brain regions? We present NEvo 🧬🧠 — a neural-guided evolutionary framework that synthesizes videos to maximally activate target visual ROIs. (1/10)
13010
Martin Schrimpf @mschrimpf.bsky.social · 02/07/2026
Really proud of @akgokce.bsky.social's work, I think this is an important result for #NeuroAI: ML-style pretraining saturates for brain-aligned models, but hybrid task+data optimization keeps scaling. Modalities transfer: fine-tune on EEG and you improve electrophysiology, fMRI & MEG predictions!🧠🤖🧪
050
Martin Schrimpf @mschrimpf.bsky.social · 16/06/2026
Yea same underlying idea!
000
Martin Schrimpf @mschrimpf.bsky.social · 16/06/2026
A wiring-cost-like loss has been shown to induce brain-like topography in vision (eg www.cell.com/neuron/fullt... and language (e.g. topolm.epfl.ch, toponets.github.io). The same spatial loss yields cognitive clusters in a multimodal model which even discovers new ones! topo-omni.epfl.ch #NeuroAI🤖🧠🧪
cell.com
A unifying framework for functional organization in early and higher ventral visual cortex
Margalit et al. develop a topographic artificial neural network that predicts both functional responses and spatial organization of multiple cortical areas of the primate visual system. In turn, the m...
2185
Reposted by Martin Schrimpf
Badr AlKhamissi @bkhmsi.bsky.social · 01/06/2026
🧠 When you watch a movie, your brain blends sight, sound, and speech into a single experience. Should models of the brain blend them too, or keep the senses separate until the very end? We built MIRAGE to find out. It sets a new SOTA for predicting whole-brain fMRI from movies. 🧵
1299
Martin Schrimpf @mschrimpf.bsky.social · 02/06/2026
Two simple ideas for building improved brain encoding models: 1. learn to use representations from all model layers via a gating mechanism + 2. start from natively multimodal features for multimodal predictions. State of the art performance; see mirage-brain.epfl.ch for details #NeuroAI 🧠🤖🧪
mirage-brain.epfl.ch
MIRAGE: Adaptive Multimodal Gating for Whole-Brain fMRI Encoding
0205
Reposted by Martin Schrimpf
Badr AlKhamissi @bkhmsi.bsky.social · 22/04/2026
Excited to be in Rio for #ICLR2026 🇧🇷 I'll be presenting our work, Mixture of Cognitive Reasoners (aka MiCRo), on Friday at Pavilion 3, 10:30 AM (#1610). Come say hi :D Happy to chat about NeuroAI, representational & cultural alignment, and/or test-time learning 🧠
171
Reposted by Martin Schrimpf
Hannes Mehrer @CCN2026 @hannesmehrer.bsky.social · 23/04/2026
I will be at #ICRL2026 in Rio to present our work on model-guided microstimulation. Poster session: Thursday, 23 April, 10.30am - 1pm at pavilion 3, poster nr. 1620 Initial BlueSkyPrint here: tinyurl.com/modelguidedmicrostim
1122
Martin Schrimpf @mschrimpf.bsky.social · 30/03/2026
My lab is hiring a software engineer to support our #NeuroAI research: careers.epfl.ch/job/Lausanne.... Please consider applying if you want to build out the infrastructure enabling models of the human brain & mind (e.g., www.Brain-Score.org). We will start screening applications this week 🧠🤖
careers.epfl.ch
Research Engineer, NeuroAI
Research Engineer, NeuroAI
12310
Reposted by Martin Schrimpf
Benjamin Cowley @benjocowley.bsky.social · 26/02/2026
DNN models of the brain are getting bigger. Are we replacing one complicated system in vivo with another in silico? In new work, we seek the *smallest* DNN models of visual cortex, balancing prediction with parsimony. It turns out these compact models are surprisingly small! rdcu.be/e5H8G
rdcu.be
Compact deep neural network models of the visual cortex
Nature - Parsimonious deep neural network models can be used for prediction of visual neuron responses.
412947
Martin Schrimpf @mschrimpf.bsky.social · 17/02/2026
I believe the results in your and Ebrahim's paper, but I do not understand why this particular configuration is so important. If you agree with point 2, then that is much more general than what we did in 2021 (more models & data) and with a more stringent metric -- and the core claim stands.
000
Martin Schrimpf @mschrimpf.bsky.social · 17/02/2026
2. NWP task performance is correlated with brain alignment in a larger set of models and datasets (going beyond our 2021 set). I understand your pushback to be that NWP-correlates-brainalignment does _not_ hold when using the *exact* 2021 models and datasets, *but* with a different metric.
110
Martin Schrimpf @mschrimpf.bsky.social · 17/02/2026
(maybe more as a personal summary from this, don't feel obliged to respond.) I believe we agree on two things: 1. The results from Schrimpf et al. 2021 with the exact same specifications (datasets, metrics, models) are perfectly reproducible from the open-source code.
100
Martin Schrimpf @mschrimpf.bsky.social · 17/02/2026
I personally see Brain-Score as an evolving set of benchmarks that is improved over time (and not as a static goalpost). Indeed our community is updating it with more rigorous alignment tests and better models. I hope you will consider contributing!
020
Martin Schrimpf @mschrimpf.bsky.social · 17/02/2026
In vision, Yamins & Hong et al 2014 first established a correspondence between object classification accuracy and ventral stream alignment on a dataset that is very easy by today's standards; which has now been extended to ImageNet, larger and more diverse neural data etc. See Brain-Score.org/vision
120
Martin Schrimpf @mschrimpf.bsky.social · 17/02/2026
I guess what you mean is whether we should move past the particular methodologies we used in the 2021 paper by testing alignment more stringently and building even better brain models -- I absolutely think so!
110
Martin Schrimpf @mschrimpf.bsky.social · 17/02/2026
The core claim you mean is "Models that perform better at predicting the next word in a sequence also better predict brain measurements" -- and yes, that indeed has been validated and extended by many follow-up studies. As you said yourself, the results can also be perfectly replicated.
210
Reposted by Martin Schrimpf
Badr AlKhamissi @bkhmsi.bsky.social · 16/02/2026
🚀 The Re-Align Challenge is now LIVE! We’re inviting you to explore what properties of vision models and data lead to convergences and divergences in representational alignment. 🔗 Get started: huggingface.co/spaces/repre... 🧵👇
huggingface.co
Re-Align Hackathon Leaderboard - a Hugging Face Space by representational-alignment
Submit Blue/Red hackathon JSON and rank by alignment scores.
181
Martin Schrimpf @mschrimpf.bsky.social · 16/02/2026
What's your sense as to why that is? Our intuition from the 2025 EMNLP paper is that more scaled models develop a lot more capabilities beyond formal "core" language processing; I'm curious if you agree
110
Martin Schrimpf @mschrimpf.bsky.social · 16/02/2026
correction: the original implementation was incorrect and @kartikpradeepan.bsky.social updated the model PR thanks to @ebrahimfeghhi.bsky.social linking the open source code. Updates here: bsky.app/profile/msch...
020
Martin Schrimpf @mschrimpf.bsky.social · 16/02/2026
hi Ebrahim, I responded in this thread: bsky.app/profile/msch.... Happy to discuss more
010
Martin Schrimpf @mschrimpf.bsky.social · 16/02/2026
Either way I'm glad the OASM model is now part of the open-source community platform, this will be a great reference point. With the new benchmarks soon on Brain-Score, we can encourage the development of models that generalize much better than what we did 5 years ago
000
Martin Schrimpf @mschrimpf.bsky.social · 16/02/2026
Regarding the original claims: Badr & others reproduced the correlation to NWP performance with the new benchmarks and newer models so I see no reason for the 2021 claims to be invalid. These new benchmarks are enforcing stronger generalization (great!) but that doesn't mean the old ones were wrong.
210
Martin Schrimpf @mschrimpf.bsky.social · 16/02/2026
The AlKhamissi et al 2025 benchmarks are most stringent afaict since they split on stories instead of contiguous k-folds, which prevents temporal autocorrelation within a story. (L)LMs indeed score much higher than OASM here. I'm glad OASM is now integrated in Brain-Score as a useful reference!
210
Martin Schrimpf @mschrimpf.bsky.social · 16/02/2026
Thanks @kartikpradeepan.bsky.social for confirming that this model indeed scores highly on the earlier benchmarks with part-of-sentence-splits! Building on Feghhi & Hadidi et al 2024, AlKhamissi et al 2025 had identified the most stringent benchmarks. We should have merged this PR sooner. 1/
110
Martin Schrimpf @mschrimpf.bsky.social · 11/02/2026
Some re-mapping is necessary even for predicting one brain's activity from another, esp. in higher areas. Linear regression is one of the more restrictive ways to achieve this between two brains so we use the same for models. @neuranna.bsky.social wrote about this here: arxiv.org/abs/2208.10668
arxiv.org
Beyond linear regression: mapping models in cognitive neuroscience should align with research goals
Many cognitive neuroscience studies use large feature sets to predict and interpret brain activity patterns. Feature sets take many forms, from human stimulus annotations to representations in deep ne...
010
Martin Schrimpf @mschrimpf.bsky.social · 11/02/2026
I'll continue in this thread where @ebrahimfeghhi.bsky.social has been helpful with linking the code. I would like to remind you that there is a human at the other end of the screen and that no information will be lost by keeping this friendly.
140
Martin Schrimpf @mschrimpf.bsky.social · 11/02/2026
Thanks Ebrahim! Would you be interested in submitting this model directly to Brain-Score? Alternatively I can let cursor attempt it again but as you pointed out, it doesn't necessarily get it right
100
Martin Schrimpf @mschrimpf.bsky.social · 11/02/2026
Nima you're very much welcome to update the PR. You are even more welcome to use the Brain-Score platform as we stated previously. I don't know how we can reach common ground if you don't either use the same benchmark implementation, or release your model code.
100
Martin Schrimpf @mschrimpf.bsky.social · 10/02/2026
I am of course happy to be proven wrong, but I find the framing of this preprint a bit frustrating. We gave similar feedback before, yet the manuscript doesn't seem to engage with the counter-evidence. I would appreciate clarification on the results discrepancy -- please feel free to update the PR!
3192
Martin Schrimpf @mschrimpf.bsky.social · 10/02/2026
This is significantly lower than the paper's reported number and far below gpt2-xl (which in the paper is outperformed by oasm). So something does not track here, either in the preprint's re-implementation of the benchmark or my reconstruction of the model.
1120
Martin Schrimpf @mschrimpf.bsky.social · 10/02/2026
3. I implemented and submitted the authors' model to Brain-Score (see PR#355 github.com/brain-score/...). The implementation follows the paper as I could not find a code release. It obtains a ceiling-normalized score of 0.34 on the criticized Pereira2018 benchmark.
github.com
add OASM model from Hadidi et al. 2025 by mschrimpf · Pull Request #355 · brain-score/language
Cursor-aided implementation based on the paper. Preliminary results from local run: 0.34 on Pereira2018-linear
2100
Martin Schrimpf @mschrimpf.bsky.social · 10/02/2026
-- this work includes null models such as randomly-assigned stimuli responses. Brain-Score language includes benchmarks that use this stronger form of generalization, which we flagged about a year ago.
160
Martin Schrimpf @mschrimpf.bsky.social · 10/02/2026
2. Splitting across larger temporal chunks (eg stories) is indeed a stronger form of generalization than smaller chunks (eg sentences). @bkhmsi.bsky.social tackled this in his EMNLP'25 where we identified the most stringent evaluation of brain alignment to be linear predictivity with story splits
190
Martin Schrimpf @mschrimpf.bsky.social · 10/02/2026
The perhaps strongest support for this point is that recent LLMs confirm the original prediction: as their task performance improved, their alignment to the human brain further increased (see e.g. Shen et al. 2025).
180
Martin Schrimpf @mschrimpf.bsky.social · 10/02/2026
Thank you Dan for the ping! As far as I can tell, all of the original claims hold, for the following reasons: 1. The relationship between next-word prediction performance and brain alignment has been replicated in several other studies (eg Caucheteux et al 2022; De Varda et al 2025; Mischler 2024).
2120
Martin Schrimpf @mschrimpf.bsky.social · 27/01/2026
Looking forward to presenting at the #AAAI #NeuroAI workshop; including 3 projects that were just accepted to ICLR! arxiv.org/abs/2509.24597, arxiv.org/abs/2510.03684, arxiv.org/abs/2506.13331 🧪🧠🤖
arxiv.org
Inducing Dyslexia in Vision Language Models
Dyslexia, a neurodevelopmental disorder characterized by persistent reading difficulties, is often linked to reduced activity of the visual word form area in the ventral occipito-temporal cortex. Trad...
0203
Reposted by Martin Schrimpf
Badr AlKhamissi @bkhmsi.bsky.social · 07/01/2026
🎉 Re-Align is back for its 4th edition at ICLR 2026! 📣 We invite submissions on representational alignment, spanning ML, Neuroscience, CogSci, and related fields. 📝 Tracks: Short (≤5p), Long (≤10p), Challenge (blog) ⏰ Deadline: Feb 5, 2026 for papers 🔗 representational-alignment.github.io/2026/
1169
Martin Schrimpf @mschrimpf.bsky.social · 08/12/2025
One week left to apply to the EPFL computer science PhD program www.epfl.ch/education/ph.... It's an amazing environment to do impactful research 🧪 (with unparalleled compute)! My NeuroAI group is hiring 🧠🤖. Consider this review service by our fantastic PhD students: www.linkedin.com/posts/spnesh...
144
Reposted by Martin Schrimpf
UCL NeuroAI @ucl-neuroai.bsky.social · 17/11/2025
For our next UCL #NeuroAI online seminar, we are happy to welcome Dr Martin Schrimpf @mschrimpf.bsky.social (EPFL) 🗓️Wed 19 Nov 2025 ⏰2-3pm GMT Neuro -> AI and Back Again: Integrative Models of the Human Brain in Health and Disease ℹ️ Details / registration: www.eventbrite.co.uk/e/ucl-neuroa...
eventbrite.co.uk
UCL NeuroAI Talk Series
A series of NeuroAI themed talks organised by the UCL NeuroAI community. Talks will continue on a monthly basis.
0104
Martin Schrimpf @mschrimpf.bsky.social · 06/11/2025
Thrilled to be among this fantastic cohort of AI2050 Fellows. This is a great recognition of the transformative potential of #NeuroAI and our lab’s work in this space 🧪🧠🤖. Many thanks to @schmidtsciences.bsky.social for the support!
4282