🌙 Lune Bellec
🏳️🌈 🏳️⚧️ 🌈♾️ Prof in psychology at Université de Montréal (she/her). Founder of the https://cneuromod.ca project: breeding 🤖 to mimic individual human 🧠. Delegate for digital health at the Montreal Geriatrics Institute criugm.qc.ca
- Reposted by 🌙 Lune BellecAttending the Montreal AI and Neuroscience (MAIN) Conference this week? #MontAIN2025 We have put together some exciting educational workshops on cognitive benchmarking large models, RL and video games and dynamical systems! More info and registration here: main-educational.github.io/program/
- Registration closes tonight!
- Interested in getting hands on with methods at the intersection of AI and neuroscience? Register to the Educational Workshop of the Montreal AI and Neuroscience (MAIN) Conference 2025! main-educational.github.io
- Reposted by 🌙 Lune BellecInterested in getting hands on with methods at the intersection of AI and neuroscience? Register to the Educational Workshop of the Montreal AI and Neuroscience (MAIN) Conference 2025! main-educational.github.io
- Reposted by 🌙 Lune BellecI've created a @gatsbyucl.bsky.social starter pack! Let me know if you’d like to be included, or just jump in to see what we're talking about. Either way, a retweet would be greatly appreciated! 🚀 go.bsky.app/4g6Ro4U go.bsky.app/AErHDonat://did:plc:zeeebjg74mhc6kshb552vg5a/app.bsky.graph.starterpack/3ljkhgnncqw2k
- Reposted by 🌙 Lune BellecHumans and animals can rapidly learn in new environments. What computations support this? We study the mechanisms of in-context reinforcement learning in transformers, and propose how episodic memory can support rapid learning. Work w/ @kanakarajanphd.bsky.social : arxiv.org/abs/2506.19686
- Reposted by 🌙 Lune BellecCNeuroMod is now on substack, and our first post highlights a new study showing that a tiny 2M-parameter audio model can be meaningfully fine-tuned on an individual brain with benefits for downstream AI tasks. open.substack.com/pub/cneuromo...
- Reposted by 🌙 Lune Belleca gross parliamentary overreach — article by @picardonhealth.bsky.social in the globe and mail; #academicsky #neuroskyence #psychscisky www.theglobeandmail.com/gift/91587b9...
- Reposted by 🌙 Lune BellecThe 2nd CogBases Workshop is this 4 & 5 Nov at Institut Pasteur! We'll discuss the latest in open science methods for analysing brain imaging data. Registration free, but mandatory neuroanatomy.github.io/cogbases-2025/ @k4tj4.bsky.social @cmaumet.bsky.social @bthirion.bsky.social @demw.bsky.social
- Reposted by 🌙 Lune BellecOpenNeuro @openneuro.bsky.social just hit a huge milestone: 1500 datasets! Congrats to the team on making this project so successful over the last 7 years.
- Reposted by 🌙 Lune BellecThe Biological Psychiatry family of journals is now officially on Bluesky! Follow us for the latest research in psychiatric neuroscience, cognitive neuroimaging, and global open science from our three leading journals.
- Many brain imaging “biomarkers” for autism have been proposed. Most aim for balanced accuracy (matching sensivity/specificity) on datasets where cases and controls are split 50/50. 1/🧵
- Real life isn’t balanced. Autism affects about 1% of the population. In that setting, a biomarker with 80% balanced accuracy would catch one true case for every twenty false alarms. 2/🧵
- We turned the problem on its head. Instead of trying to classify everyone, we built a brain signature that only makes predictions when it’s confident. 3/🧵
-
View full threadAnd to match their spirit of openness, we’ve released the code, containers, and data. Anyone can rerun the entire analysis. Co-lead authors: @clarken.bsky.social and @surchs.bsky.social Paper: doi.org/10.1093/giga... Github: github.com/SIMEXP/autis... Zenodo archive: doi.org/10.5281/zeno... End/🧵
- "A murder of butterflies" has a nice ring to it.
- Reposted by 🌙 Lune BellecThis year at #CCN25 we showed the importance of OOD evaluation to adjudicate between brain models. Our results demonstrate these trivial but key facts : - high encoding accuracy ≠ functional convergence - human brain ≠ NES console ≠ 4-layers CNN - videogames are cool w/ @lune-bellec.bsky.social 🙌
- Reposted by 🌙 Lune BellecMapping cerebral blood perfusion and its links to multi-scale brain organization across the human lifespan | doi.org/10.1371/jour... How does blood perfusion map onto canonical features of brain structure and function? @asafarahani.bsky.social investigates @plosbiology.org ⤵️
- Reposted by 🌙 Lune BellecIn 2019, the CNeuroMod team and 6 participants began a massive data collection journey: twice-weekly MRI scans for most of 5 years. Data collection is now complete! 1/🧵
- Reposted by 🌙 Lune BellecAutomated testing with GitHub Actions - the latest in my Better Code, Better Science series russpoldrack.substack.com/p/automated-...
- Reposted by 🌙 Lune Bellec🥁... we are SO happy to officially announce that registration is now OPEN for our OHBM Virtual Satellite Meeting, taking place September 10-12! This has been a major goal of the SEA-SIG for a while now and we're so excited to show you what we've been working on! 🌱🌎✨🧠
- 🌍🧠 Join us for the OHBM & SEA-SIG Virtual Satellite Meeting! 📅 Sept 10–12, 2025 | 🕛 12–15 UTC 💻 Online via Zoom 🔗 More info: humanbrainmapping.org/25SEASIG #OHBM #SEASIG
- Reposted by 🌙 Lune BellecNew CNeuroMod-THINGS open-access fMRI dataset: 4 participants · ~4 000 images (720 categories) each shown 3× (12k trials per subject)· individual functional localizers & NSD-inspired QC . Preprint: arxiv.org/abs/2507.09024 Congrats Marie St-Laurent and @martinhebart.bsky.social !!
- Reposted by 🌙 Lune Bellec1/11 Very excited to say that our preprint, Precision functional mapping reveals less inter-individual variability in the child vs. adult human brain, is up on biorxiv! www.biorxiv.org/content/10.1...
- Reposted by 🌙 Lune BellecGoogle’s Gemini 2.5 paper has 3295 authors arxiv.org/abs/2507.06261
- Reposted by 🌙 Lune BellecExcited to share our News&Views on Kamitani Lab's NatComputSci paper! Their neural code converter enables transformation of brain activity patterns across individuals, and it doesn't need shared stimuli or connectivity information! www.nature.com/articles/s43...
- Reposted by 🌙 Lune BellecExcited to co-organize our NeurIPS 2025 workshop on Foundation Models for the Brain and Body! We welcome work across ML, neuroscience, and biosignals — from new approaches to large-scale models. Submit your paper or demo! 🧠 🧪 🦾
- 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
- Reposted by 🌙 Lune BellecThis is why I think the platonic rep hypothesis doesn’t apply to brain-ANN alignment, since most existing (functional?) models are implicitly or explicitly trained to mimic humans. The assumption of PRH is that the networks are trained independently which doesn’t hold in brain-ANN comparisons.
- Using intracranial brain recordings to guide representations in a vision-action AI model leads to faster and better training arxiv.org/abs/2506.208...
- Reposted by 🌙 Lune BellecJust wrapped up my first real foray into analyzing brain data at Brainhack School 2025 a couple weeks ago 🧠💻 I focused on comparing fMRI techniques on a single subject, using fear as a case study. school-brainhack.github.io/project/many...
- Reposted by 🌙 Lune BellecBenchmarking methods for mapping functional connectivity in the brain | doi.org/10.1038/s415... What is the best measure of functional connectivity (FC)? led by @zhenqi.bsky.social in @natmethods.nature.com ⤵️
- Reposted by 🌙 Lune BellecResearch assistant job posting is live! Come join us in Calgary and be part of a supportive, interdisciplinary team. careers.ucalgary.ca/jobs/1631661...
- We will soon be hiring a research assistant in Calgary to work on projects related to brain imaging, prenatal alcohol exposure, and mental health. Please reach out if you're interested, and I will share the posting once it's live. @ucalgary.bsky.social @mathisoncentre.bsky.social
- Reposted by 🌙 Lune BellecFew originals available Anyone interested can DM me.
- Reposted by 🌙 Lune Bellec#OSCAwards2025 | open access, data, materials & software: OpenMReye: camera-free magnetic resonance-based eye tracking for research and clinical applications 👀🩻 by @matthiasnau.bsky.social Find out more: github.com/DeepMReye/
- Reposted by 🌙 Lune BellecHi friends, I have news! Giga connectome, a BIDS app for post-fMRIPrep connectome extraction, is now in @joss-openjournals.bsky.social 🎉 Thanks to @remigau.bsky.social, @clarken.bsky.social, Quentin Dessain, and @lune-bellec.bsky.social for working on this together
- Reposted by 🌙 Lune BellecText-to-LoRA: Instant Transformer Adaption arxiv.org/abs/2506.06105 Generative models can now produce text, image, video. They should also be able to generate models! We trained a Hypernetwork to generate new task-specific LoRA models by simply giving it a description of the task as a text prompt.
- We’re excited to introduce Text-to-LoRA: a Hypernetwork that generates task-specific LLM adapters (LoRAs) based on a text description of the task. Catch our presentation at #ICML2025! Paper: arxiv.org/abs/2506.06105 Code: github.com/SakanaAI/Tex...
- Reposted by 🌙 Lune BellecAI may still need some neuroscience: "AI systems will not acquire the flexibility and adaptability of human intelligence until they can actually learn like humans do, shining brightly with their own light rather than observing a shadow from ours." 🧠🤖 sergeylevine.substack.com/p/language-m...
- Reposted by 🌙 Lune BellecDarwin Gödel Machine: A Commentary on Novelty and Implications. antomon.github.io/posts/darwin...
- Reposted by 🌙 Lune BellecWith Mila’s support, our Founder and Scientific Advisor @yoshuabengio.bsky.social is launching @law-zero.bsky.social, a nonprofit organization committed to advancing research and developing technical solutions for safe-by-design AI systems.
- Every frontier AI system should be grounded in a core commitment: to protect human joy and endeavour. Today, we launch LawZero, a nonprofit dedicated to advancing safe-by-design AI. lawzero.org
- Reposted by 🌙 Lune BellecTout système d'IA de pointe devrait reposer sur un engagement essentiel : celui de préserver la joie et les aspirations humaines. Aujourd’hui, nous lançons LoiZéro, une organisation à but non lucratif visant à concevoir des systèmes d'IA sécuritaires. loizero.org
- Reposted by 🌙 Lune BellecNew preprint! 🧠🤖 How do we build neural decoders that are: ⚡️ fast enough for real-time use 🎯 accurate across diverse tasks 🌍 generalizable to new sessions, subjects, and even species? We present POSSM, a hybrid SSM architecture that optimizes for all three of these axes! 🧵1/7
- More evidence on the fact the fact that fine tuning AI sound processing models reshapes representations in a meaningful way. Perhaps unsurprising- it's just distillation of a big model in a small model, but i often get a lot of skepticism on this idea. arxiv.org/abs/2506.038...
- new brain foundation model study, this time with a graph neural net architecture and fMRI, looking at a range of disorders and downstream tasks. arxiv.org/abs/2506.020... #neuroAI
- Reposted by 🌙 Lune BellecNew preprint from the Hasson Lab🪄Delineates coupling b/w regions within the language network AND shows the elements of language that connect them. Led by @ahmadsamara.bsky.social; thanks @samnastase.bsky.social Zaid Zada & Uri Hasson. 💥 www.biorxiv.org/content/10.1...
- Reposted by 🌙 Lune Bellec🚨Preprint!🚨 So excited to share my 1st major study as a postdoc at @holmeslab-bhi.bsky.social!🤘 www.biorxiv.org/content/10.1... Using a transdiagnostic framework, we found that brain network dynamics were able to discriminate individualized psychiatric symptom profiles with high accuracy 🧵1/9👇
- Reposted by 🌙 Lune Bellecjust watched a very great overview of the latest updates in Jupyterlab and Jupyterlite - Improved code consoles, RTC, - Support for R via xeus-R; consoles - Improvements with xeus-python with some pip magic - JupyterAI and Jupyterlite-AI, with options for in-browser LLMs - hybrid kernels 🤯 (cont ⬇️)
- Reposted by 🌙 Lune BellecExcited to announce that our paper (led by @hyejinjadelee.bsky.social & Derek Smith) is out in @nathumbehav.nature.com go.illinois.edu/Lee2025_NHB We use 36 days of testing in 4 inhibitory control tasks to examine the precision of inhibitory control measures in *individuals* and how they vary 🧵👇
- Reposted by 🌙 Lune Bellec
- Reposted by 🌙 Lune Bellec🧩 The dream: FAIR models and data. Only standards can solve the MxN problem, and this session is exactly about that. And we wrap up today’s workshops with a group reflection: Why are FAIR resources essential for scientific progress?
- #neuroAI preprint alert: studying the convergence of multimodal AI features with brain activity during movie watching. Notably identifies brain areas where multimodal features outperform unimodal stimuli representations. And it uses @cneuromod.ca 's movie10 dataset :) arxiv.org/abs/2505.20027
- Reposted by 🌙 Lune Bellec1/6 Why does the brain maintain such precise excitatory-inhibitory balance? Our new preprint explores a provocative idea: Small, targeted deviations from this balance may serve a purpose: to encode local error signals for learning. www.biorxiv.org/content/10.1... led by @jrbch.bsky.social
- Reposted by 🌙 Lune Bellec🌎 Rounding out our symposium from OHBM 2024 in Seoul 🇰🇷 is the wonderful @clarekelly.bsky.social "Rethinking academia in a time of climate crisis, or how to be a scientist in a world on fire." 🔬 🔥
- Please note: my main professional email address is now lune.bellec@umontreal.ca — my previous address has been deactivated. Many thanks to @umontreal.ca for making the transition smooth (once I actually read the instructions properly 😅).
- Reposted by 🌙 Lune BellecPsychological Science is looking for volunteers to join REPEAT—our new network of computational reproducibility checkers. Please join us if you have the time and skills! www.psychologicalscience.org/publications...
- New #neuroAI work incorporating human priors in training artificial vision models arxiv.org/abs/2505.142...
- Reposted by 🌙 Lune BellecOur lab is present at #VSS2025, so let me highlight some of the things we have been up to with a talk and three posters. Would love to see you around! 🧵
- Reposted by 🌙 Lune BellecBecause I have opened a BlueSky window and am procrastinating on reading final papers, let me also share what this spring has been like from my corner of the academic world.
- Reposted by 🌙 Lune BellecOur newest paper from a brilliant undergraduate researcher (now a PhD student at McGill!) Nate Roy. We use network control theory to show how dynamics shift after traumatic brain injury! A great collaborative team. doi.org/10.1016/j.ni...
- Reposted by 🌙 Lune BellecIf you haven't used Claude Code yet, you should - it's absolutely amazing! Yesterday I built an app that uses 4 LLM APIs (openai, anthropic, google, and together.ai) to perform an automated meta-review of a paper - using only the Claude interface, never touching code! github.com/poldrack/ai-...
- Reposted by 🌙 Lune BellecI love the work, not only because it speed up FIC models a lot, but also how it saves poor students from grad student descent 🤣🤣
- While the world burns, we cook up a new preprint! doi.org/10.1101/2025... Biophysical modeling is a key tool to derive mechanistic insights into the brain. These models are governed by biologically meaningful parameters (unlike artificial neural networks), but the dirty secret ... 1/N
- Reposted by 🌙 Lune BellecChronic #pain involves changes in multiple brain systems for nociception, threat, and reward. What self-management practices can help us live with or even reverse these changes? Cognitive, behavioral, and #digitalhealth strategies can help! New review in Lancet: authors.elsevier.com/a/1l5%7EfV-4...
- IMO one of the solution to the reproducibility crisis in science is to stop taking scientific articles too seriously. What matters is code, data, open protocols, pre-registration. Certainly not fact the article was endorsed by a publisher, especially predatory ones like Nature Publishing Co
- Reposted by 🌙 Lune BellecBetter Code, Better Science - Introducing a new open-source book project on scientific coding using AI tools russpoldrack.substack.com/p/better-cod...
- Reposted by 🌙 Lune Bellec🕟 It's Wednesday, so it's time for this week's Nilearn drop-in hour! Join us today on Jitsi at 4pm UTC to discuss anything #nilearn. 🧠🚀 Check your local time and grab the Jitsi meeting link here: tinyurl.com/nilearn-drop... Or check our google calendar shorturl.at/O9mCN
- Reposted by 🌙 Lune BellecCheck 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
