Patrick Mineault
NeuroAI, vision, open science. NeuroAI researcher at Amaranth Foundation. Previously engineer @ Google, Meta, Mila. Updates from http://neuroai.science
- Reposted by Patrick MineaultDiscovered @patrickmineault.bsky.social's excellent Good Research Code Handbook today, which was always awesome, but is even more necessary as more scientists consider integrating coding agents into their workflows. goodresearch.dev
- Reposted by Patrick Mineaultwww.neuroai.science/p/claude-cod... Why yes this is very helpful for me as an undergrad. I like the way the methods that Patrick laid, how to aid research using AI and its pros vs cons
- Reposted by Patrick MineaultFrom @patrickmineault.bsky.social, on how scientists can use Claude Code to help with all the heavy data analysis coding that is a big part of our lives. use a make system, set up folder structures, write tests, use git, use package managers. Notes on notebooks and visualizations too. 🧪
- www.neuroai.science/p/claude-cod... Why yes this is very helpful for me as an undergrad. I like the way the methods that Patrick laid, how to aid research using AI and its pros vs cons
- Reposted by Patrick Mineault🚨📜+🧵🚨 Very excited about this work showing that people with no hand function following a spinal cord injury can control the activity of motor units from those muscles to perform 1D, 2D and 3D tasks, play video games, or navigate a virtual wheelchair By a wonderful team co-mentored w Dario Farina
- New preprint! We show that people with tetraplegic spinal cord injury can use their residual motor unit activity to achieve up to three dimensional control using non-invasive high-density surface EMG With my co-first authors Xingchen Yang and Ciara Gibbs www.medrxiv.org/content/10.6... 1/13
- Reposted by Patrick MineaultJust published my review of neuroscience in 2025, on The Spike. The 10th of these, would you believe? This year we have foundation models, breakthroughs in using light to understand the brain, a gene therapy, and more Enjoy! medium.com/the-spike/20...
- ✈️ Montreal AI and Neuroscience is over, off to Costa Rica. Great catching up all things NeuroAI with hometown friends. Thanks for the shirt and the bagels, folks!
- Reposted by Patrick Mineault🔴 Live: Panel discussion #1: @ MAIN2025 The future of Neuroscience - The role of AI ? with Andreas Tolias, Siva Reddy, Joao Sacramento, Ching Fang + Eva Portelance Moderated by Patrick Mineault @patrickmineault.bsky.social @andreastolias.bsky.social
- What I would have done for a dataset like this to exist in grad school! One day, we'll figure out the dorsal stream. openreview.net/forum?id=Ila...
- Headed to NeurIPS, looking forward to catching up with you about NeuroAI, foundation models of the brain, AI safety and AI for science
- This equivocation of oscillations and continual learning is a bit of stretch... I'm surprised they didn't get dinged by the reviewers for neuro-babble. openreview.net/forum?id=nbM...
- We're almost at the end of the year, and that means an end-of-year review! Send me your favorite NeuroAI papers of the year (preprints or published, late last year is fine too).
- Reposted by Patrick MineaultNew #NeuroAI #compneurosky preprint! To better understand how target-directed learning works in the brain, we sought to engineer an artificial neural network capable of solving complex image classification tasks that comprises only experimentally-supported biological building blocks. (1/15)
- I had way too much fun making these diagrams. Sure, it's not as legible as if I had typed out the text; but I feel like these have a bit more personality
- Reposted by Patrick Mineault🚨 New preprint alert! 🧠🤖 We propose a theory of how learning curriculum affects generalization through neural population dimensionality. Learning curriculum is a determining factor of neural dimensionality - where you start from determines where you end up. 🧠📈 A 🧵: tinyurl.com/yr8tawj3
- Reposted by Patrick MineaultThrilled to share that our work is now published in Science! ✨ We found a preference for visual objects in the mouse spatial navigation system where they dynamically refine head-direction coding. In short, objects boost our inner compass! 🧭 www.science.org/doi/10.1126/... 🧵1/
- Reposted by Patrick MineaultHaving fun facilitating this amazing group of young Profs at the #Neuro4Pros workshop with @kordinglab.bsky.social and @meganakpeters.bsky.social, @yaelniv.bsky.social, and Hannah Bayer. Watch out world: this is the next generation of leaders! compneurosci.com/Neuro4Pros/i...
- "Everyone agrees that emergence is important, but they don’t agree on what the word should mean" arxiv.org/abs/2410.15468
- Reposted by Patrick Mineault𝗖𝗼𝗴𝗻𝗶𝘁𝗶𝗼𝗻 𝗶𝘀 𝗲𝗺𝗲𝗿𝗴𝗲𝗻𝘁 𝗶𝗻 𝘁𝗵𝗲 𝗯𝗿𝗮𝗶𝗻 by Earl K Miller, Scott L Brincat, Jefferson E Roy This promises to be a must read One day we should create an online journal club to just read these kinds of papers! #neuroskyence doi.org/10.1016/j.co...
- Reposted by Patrick MineaultA few years ago, with @tyrellturing.bsky.social @patrickmineault.bsky.social and others, we showed one single objective (prediction) was sufficient for explaining specialized pathways of mouse visual cortex: tinyurl.com/2vsjbve7 Super cool to see the same observation now for human visual cortex.
- Reposted by Patrick Mineault1 To predict the behaviour of a primate, would you rather base your guess on a closely related species or one with a similar brain shape? We looked at brains & behaviours of 70 species, you’ll be surprised! 🧵Thread on our new preprint with @r3rt0.bsky.social , doi.org/10.1101/2025...
- RFI: How can brain science shape frontier-scale AGI? The Amaranth Foundation wants your 2-page ideas on how brain science can guide & govern frontier-scale AGI—incl. short-timeline (2025-2028) scenarios. Send ≤2-page ideas by 29 Aug. Link: blog.amaranth.foundation/p/rfi-neuros...
- Reposted by Patrick MineaultHow can we best use AI in science? Myself and 9 other research fellows from @imperial-ix.bsky.social use AI methods in domains from plant biology (🌱) to neuroscience (🧠) and particle physics (🎇). Together we suggest 10 simple rules @plos.org 🧵 doi.org/10.1371/jour...
- Curious what cognitive scientists think about this daydreaming proposal from Gwern: gwern.net/ai-daydreaming
- Reposted by Patrick MineaultThrilled to see our TinyRNN paper in @nature! We show how tiny RNNs predict choices of individual subjects accurately while staying fully interpretable. This approach can transform how we model cognitive processes in both healthy and disordered decisions. doi.org/10.1038/s415...
- Reposted by Patrick Mineault🚨Preprint Alert: Who Does What in Deep Learning? Multidimensional Contribution of Neural Units using Game Theory: arxiv.org/abs/2506.19732 The result of my MSc thesis is out with @kayson.bsky.social @fatemehhadaeghi.bsky.social @patrickmineault.bsky.social @kordinglab.bsky.social, Claus C. Hilgetag
- Reposted by Patrick MineaultThrilled to announce I'll be starting my own neuro-theory lab, as an Assistant Professor at @yaleneuro.bsky.social @wutsaiyale.bsky.social this Fall! My group will study offline learning in the sleeping brain: how neural activity self-organizes during sleep and the computations it performs. 🧵
- Does anybody have a good review or blog post on advances in neurosymbolic and program induction methods over the last 2 years? I'm looking for something technical that has the depth of explanation I would expect from, say, Lil' Log. My usual tools have failed me.
- A $50k essay competition about consciousness... Any takers? Via @erikhoel.blogsky.venki.dev berggruen.org/essay-compet...
- Woo! Thanks for subscribing, all!
- Reposted by Patrick Mineault🪰 A team of Janelia researchers & collaborators have created a new set of tools for studying motor control of wing movements in fruit flies, providing an important #openscience resource for future studies of fly flight & courtship 🧠 hhmi.news/3H3ohn8
- Reposted by Patrick MineaultExcited to share a new preprint w/ @michael-lepori.bsky.social & Michael Franke! A dominant approach in AI/cogsci uses *outputs* from AI models (eg logprobs) to predict human behavior. But how does model *processing* (across layers in a forward pass) relate to human real-time processing? 👇 (1/12)
- Reposted by Patrick MineaultWhen I realized how dangerous the current agency-driven AI trajectory could be for future generations, I knew I had to do all I could to make AI safer. I recently shared this personal experience, and outlined the scientific solution I envision @TEDTalks⤵️ www.ted.com/talks/yoshua...
- Reposted by Patrick MineaultApplications are now open for a special cohort of the Brains Accelerator targeting ambitious AI research programs, with a special focus on security and governance capabilities! spec.tech/ai-brains 1/
- Reposted by Patrick MineaultNew Paper: Continuous Thought Machines pub.sakana.ai/ctm/ Neurons in brains use timing and synchronization in the way that they compute, but this is largely ignored in modern neural nets. We believe neural timing is key for the flexibility and adaptability of biological intelligence. Thread ↓
- Reposted by Patrick MineaultI'm very pleased to share our latest study: ‘Emergence of Language in the Developing Brain’, by L Evanson, P Bourdillon et al: - Paper: ai.meta.com/research/pub... - Blog: ai.meta.com/blog/meta-fa... - Thread below 👇
- I just tried the Gemini features in Google Sheets. It's pretty good! You can ask it to perform a simple analysis, and it will do it. I asked it to do a logistic regression, and it imported statsmodels, ran it, printed the results and interpreted them.
- Excited to dig into this, from @jeanremiking.bsky.social 's group. Compares neural representations of language across age. The stimulus? Le Petit Prince. ai.meta.com/research/pub...
- I think we're overdue for a rollup of the best papers of the past year in NeuroAI. Candidates?
- Reposted by Patrick MineaultCheck out our new paper! Vision models often struggle with learning both transformation-invariant and -equivariant representations at the same time. @hafezghm.bsky.social shows that self-supervised prediction with proper inductive biases achieves both simultaneously. (1/4) #MLSky #NeuroAI
- New post: things have been moving very fast in AI. But has safety caught up to capabilities? open.substack.com/pub/naix/p/w...
- Any good neuroscience/NeuroAI discord servers I should know about? I feel like the neuroscience town square on bsky is a bit of a ghost town
- Loving the new ICLR blogpost track. Here's a cool one on engrams in neuroscience vs mechanistic interpretability: d2jud02ci9yv69.cloudfront.net/2025-04-28-e...
- Can o3 curate your reading stack? I asked it about last week in NeuroAI, and while not great, it is much better than anticipated, highlighting 3 solid talks/papers and several other reasonable suggestions. I wouldn't be surprised if this was solved in a couple of gens chatgpt.com/share/680bae...
- Reposted by Patrick Mineault⚡️ Excited to introduce ZAPBench, our #ICLR2025 spotlight: The Zebrafish Activity Prediction Benchmark measures progress in predicting neural activity within an entire vertebrate brain (70k+ neurons!) Explore interactive visualizations, datasets, code + paper: google-research.github.io/zapbench 🧠🧪
- Excellent talk from Zico Kolter at ICLR on AI safety. Science of deep learning and AI safety are some of the most impactful ways academic AI researchers can bend the curve
- Some fantastic work on the virtual fly www.nature.com/articles/s41...
- Reposted by Patrick MineaultThrilled to share our state-of-the-art method for in vivo cell-type classification and brain region localization, NEMO, which is now now a spotlight at @iclr-conf.bsky.social ! We use NEMO to characterize the electrophysiological diversity of cell-types across the entire mouse brain. 🐭 🧪 🧠
- I asked o3 for help with LaTeX quote boxes. This is the example quote it used. The machines are on to us.
- Crowdsourcing this: what are the best examples of scaling laws in foundation models for neuroscience? My top 3 examples: Ctrl+Labs, Sato et al., Mineault et al. @colehurwitz.bsky.social , @mehdiazabou.bsky.social , @nandahkrishna.bsky.social , @averyryoo.bsky.social, @tyrellturing.bsky.social ?
- Reposted by Patrick MineaultIf GPT-4o walked into a neuro-opthalmology clinic, what would it be diagnosed with? Here we administered 51 tests from 6 clinical and experimental batteries to assess vision in commercial AI models. Very proud to share this first work from @genetang.bsky.social's PhD! arxiv.org/abs/2504.10786
- The Foundation Model crew at #COSYNE2025. With @josueortc.bsky.social , @colehurwitz.bsky.social , @averyryoo.bsky.social , @nandahkrishna.bsky.social , @auschulz.bsky.social
- Reposted by Patrick MineaultAnother step toward a foundation model of the mouse brain: "Neural Encoding and Decoding at Scale (NEDS)" Trained on neural and behavioral data from 70+ mice, NEDS achieves state-of-the-art prediction of behavior (decoding) and neural responses (encoding) on held-out animals. 🐀
- This is a really interesting (and heroic!) map of "dark matter" in the sciences that should be addressed with new tools and datasets. What's the dark matter of neuroscience?
- We (mostly @adammarblestone.bsky.social and Mary with the help of the amazing scientists in our network) made a map of “fundamental development” gaps in science and technology. Go explore gap-map.org.
- I am intrigued by recent discussions of neuropeptides and our inability to map them, @antihebbiann.bsky.social, @engeltatiana.bsky.social ?
- Scott Linderman and I ended up on the same panel at #ODIN2025 at the @alleninstitute.bsky.social , wearing the same J Crew shirt. Twins!
- Nice article on MICrONS in the NYTimes from @carlzimmer.com www.nytimes.com/2025/04/09/s...
- Headed to Seattle this week for ODIN workshop at the Allen Institute. Hit me up!
