Guillaume Lajoie
@glajoie.bsky.social
Professor at Université de Montréal & Mila -- Québec AI Institute
mathematics - neuroscience - artificial intelligence
mathematics - neuroscience - artificial intelligence
Reposted by Guillaume Lajoie
Excited to share that POSSM has been accepted to #NeurIPS2025! See you in San Diego 🏖️
New 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
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
September 20, 2025 at 3:40 PM
Excited to share that POSSM has been accepted to #NeurIPS2025! See you in San Diego 🏖️
Reposted by Guillaume Lajoie
The CTRL-Labs decoding model paper is out! Saw this presented at Cosyne this year, very cool to see it out.
I would say this is the clearest demonstration of scaling laws in neural decoding to-date.
www.nature.com/articles/s41...
🧠📈 🧪
I would say this is the clearest demonstration of scaling laws in neural decoding to-date.
www.nature.com/articles/s41...
🧠📈 🧪
A generic non-invasive neuromotor interface for human-computer interaction - Nature
A high-bandwidth neuromotor interface offers performant out-of-the-box generalization across people.
www.nature.com
September 18, 2025 at 1:34 PM
The CTRL-Labs decoding model paper is out! Saw this presented at Cosyne this year, very cool to see it out.
I would say this is the clearest demonstration of scaling laws in neural decoding to-date.
www.nature.com/articles/s41...
🧠📈 🧪
I would say this is the clearest demonstration of scaling laws in neural decoding to-date.
www.nature.com/articles/s41...
🧠📈 🧪
Reposted by Guillaume Lajoie
www.programmablemutter.com/p/large-lang... Gopnikism, interactionism, structuralism and role play.
Large language models are cultural technologies. What might that mean?
Four different perspectives
www.programmablemutter.com
August 18, 2025 at 1:00 PM
www.programmablemutter.com/p/large-lang... Gopnikism, interactionism, structuralism and role play.
Compositionality is a central desideratum for intelligent systems...but it's a fuzzy concept and difficult to quantify. In this blog post, lab member @ericelmoznino.bsky.social outlines ideas toward formalizing it & surveys recent work. A must-read for interested researchers in AI and Neuro
Very excited to release a new blog post that formalizes what it means for data to be compositional, and shows how compositionality can exist at multiple scales. Early days, but I think there may be significant implications for AI. Check it out! ericelmoznino.github.io/blog/2025/08...
Defining and quantifying compositional structure
What is compositionality? For those of us working in AI or cognitive neuroscience this question can appear easy at first, but becomes increasingly perplexing the more we think about it. We aren’t shor...
ericelmoznino.github.io
August 19, 2025 at 1:51 PM
Compositionality is a central desideratum for intelligent systems...but it's a fuzzy concept and difficult to quantify. In this blog post, lab member @ericelmoznino.bsky.social outlines ideas toward formalizing it & surveys recent work. A must-read for interested researchers in AI and Neuro
Reposted by Guillaume Lajoie
🎉 We’re featured by @mila-quebec.bsky.social for our work on immersive, real-world cognitive science. With LABO, researchers can run full XR experiments—no code needed, real behaviour captured. Special thanks to @tyrellturing.bsky.social for being with us from the start!
tinyurl.com/yc4wpp3t
tinyurl.com/yc4wpp3t
Modernizing Cognitive Health Research with SilicoLabs | Mila
Cognitive health research is a field dedicated to understanding how our brains work when we think, remember, and learn as we go through life. When combined with medical research and rehabilitation…
mila.quebec
July 17, 2025 at 4:52 PM
🎉 We’re featured by @mila-quebec.bsky.social for our work on immersive, real-world cognitive science. With LABO, researchers can run full XR experiments—no code needed, real behaviour captured. Special thanks to @tyrellturing.bsky.social for being with us from the start!
tinyurl.com/yc4wpp3t
tinyurl.com/yc4wpp3t
Excited to share recent progress on foundation-like models for neural data. As many use cases for generalizable models demand flexible online deployment, here we focus on a design enabling low latency real time use. We use hybrid SSM architecture & demonstrate various transfer learning capabilities
New 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
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
June 6, 2025 at 6:44 PM
Excited to share recent progress on foundation-like models for neural data. As many use cases for generalizable models demand flexible online deployment, here we focus on a design enabling low latency real time use. We use hybrid SSM architecture & demonstrate various transfer learning capabilities
Reposted by Guillaume Lajoie
New 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
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
June 6, 2025 at 5:40 PM
New 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
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
Reposted by Guillaume Lajoie
Reserve your free tickets to SFI's upcoming Community Lecture! lensic.org/events/blais...
Blaise Agüera y Arcas’ presents 'Computing, Life, and Intelligence' at the Lensic on 🗓️ May 20, 7:30pm MT in-person or online.
Blaise Agüera y Arcas’ presents 'Computing, Life, and Intelligence' at the Lensic on 🗓️ May 20, 7:30pm MT in-person or online.
May 13, 2025 at 3:30 PM
Reserve your free tickets to SFI's upcoming Community Lecture! lensic.org/events/blais...
Blaise Agüera y Arcas’ presents 'Computing, Life, and Intelligence' at the Lensic on 🗓️ May 20, 7:30pm MT in-person or online.
Blaise Agüera y Arcas’ presents 'Computing, Life, and Intelligence' at the Lensic on 🗓️ May 20, 7:30pm MT in-person or online.
Reposted by Guillaume Lajoie
Check 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
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
Preprint Alert 🚀
Can we simultaneously learn transformation-invariant and transformation-equivariant representations with self-supervised learning?
TL;DR Yes! This is possible via simple predictive learning & architectural inductive biases – without extra loss terms and predictors!
🧵 (1/10)
Can we simultaneously learn transformation-invariant and transformation-equivariant representations with self-supervised learning?
TL;DR Yes! This is possible via simple predictive learning & architectural inductive biases – without extra loss terms and predictors!
🧵 (1/10)
May 14, 2025 at 12:57 PM
Check 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
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
Reposted by Guillaume Lajoie
come see @glajoie.bsky.social presenting our poster this week @iclr-conf.bsky.social ! It will be poster #56 in poster session #3. This work was a collaboration between a bunch of us from @mila-quebec.bsky.social and Luca Mazzucato @neuroai-uoregon.bsky.social :)
1/7: Super excited to share our new paper! This one should be of interest to neuroscientists and deep learning theory folks. This paper was a collaboration with Alexandre Payeur, @averyryoo.bsky.social, Thomas Jiralerspong, @mattperich.bsky.social, Luca Mazzucato, @glajoie.bsky.social
April 22, 2025 at 2:06 PM
come see @glajoie.bsky.social presenting our poster this week @iclr-conf.bsky.social ! It will be poster #56 in poster session #3. This work was a collaboration between a bunch of us from @mila-quebec.bsky.social and Luca Mazzucato @neuroai-uoregon.bsky.social :)
Reposted by Guillaume Lajoie
🚨 New Preprint! 🚨
We explore Amortized In-Context Bayesian Posterior Estimation with Niels, @glajoie.bsky.social, Priyank Jaini & @marcusabrubaker.bsky.social ! 🔥
Amortized Conditional Modeling = key to success in large-scale models! We use it to estimate posteriors 🔑
📄 arxiv.org/abs/2502.06601
We explore Amortized In-Context Bayesian Posterior Estimation with Niels, @glajoie.bsky.social, Priyank Jaini & @marcusabrubaker.bsky.social ! 🔥
Amortized Conditional Modeling = key to success in large-scale models! We use it to estimate posteriors 🔑
📄 arxiv.org/abs/2502.06601
Amortized In-Context Bayesian Posterior Estimation
Bayesian inference provides a natural way of incorporating prior beliefs and assigning a probability measure to the space of hypotheses. Current solutions rely on iterative routines like Markov Chain ...
arxiv.org
February 28, 2025 at 3:21 PM
🚨 New Preprint! 🚨
We explore Amortized In-Context Bayesian Posterior Estimation with Niels, @glajoie.bsky.social, Priyank Jaini & @marcusabrubaker.bsky.social ! 🔥
Amortized Conditional Modeling = key to success in large-scale models! We use it to estimate posteriors 🔑
📄 arxiv.org/abs/2502.06601
We explore Amortized In-Context Bayesian Posterior Estimation with Niels, @glajoie.bsky.social, Priyank Jaini & @marcusabrubaker.bsky.social ! 🔥
Amortized Conditional Modeling = key to success in large-scale models! We use it to estimate posteriors 🔑
📄 arxiv.org/abs/2502.06601
Reposted by Guillaume Lajoie
🚀 New Preprint! 🚀
In-Context Parametric Inference: Point or Distribution Estimators?
Thrilled to share our work on inferring probabilistic model parameters explicitly conditioned on data, in collab with @yoshuabengio.bsky.social, Nikolay Malkin & @glajoie.bsky.social!
🔗 arxiv.org/abs/2502.11617
In-Context Parametric Inference: Point or Distribution Estimators?
Thrilled to share our work on inferring probabilistic model parameters explicitly conditioned on data, in collab with @yoshuabengio.bsky.social, Nikolay Malkin & @glajoie.bsky.social!
🔗 arxiv.org/abs/2502.11617
In-Context Parametric Inference: Point or Distribution Estimators?
Bayesian and frequentist inference are two fundamental paradigms in statistical estimation. Bayesian methods treat hypotheses as random variables, incorporating priors and updating beliefs via Bayes' ...
arxiv.org
February 28, 2025 at 3:24 PM
🚀 New Preprint! 🚀
In-Context Parametric Inference: Point or Distribution Estimators?
Thrilled to share our work on inferring probabilistic model parameters explicitly conditioned on data, in collab with @yoshuabengio.bsky.social, Nikolay Malkin & @glajoie.bsky.social!
🔗 arxiv.org/abs/2502.11617
In-Context Parametric Inference: Point or Distribution Estimators?
Thrilled to share our work on inferring probabilistic model parameters explicitly conditioned on data, in collab with @yoshuabengio.bsky.social, Nikolay Malkin & @glajoie.bsky.social!
🔗 arxiv.org/abs/2502.11617
Reposted by Guillaume Lajoie
New preprint! Excited to share our latest work “Accelerated learning of a noninvasive human brain-computer interface via manifold geometry” ft. outstanding former undergraduate Chandra Fincke, @glajoie.bsky.social, @krishnaswamylab.bsky.social, and @wutsaiyale.bsky.social's Nick Turk-Browne 1/8
Accelerated learning of a noninvasive human brain-computer interface via manifold geometry
Brain-computer interfaces (BCIs) promise to restore and enhance a wide range of human capabilities. However, a barrier to the adoption of BCIs is how long it can take users to learn to control them. W...
doi.org
April 3, 2025 at 11:04 PM
New preprint! Excited to share our latest work “Accelerated learning of a noninvasive human brain-computer interface via manifold geometry” ft. outstanding former undergraduate Chandra Fincke, @glajoie.bsky.social, @krishnaswamylab.bsky.social, and @wutsaiyale.bsky.social's Nick Turk-Browne 1/8
Reposted by Guillaume Lajoie
Very late, but had a 🔥 time at my first Cosyne presenting my work with @nandahkrishna.bsky.social, Ximeng Mao, @mattperich.bsky.social, and @glajoie.bsky.social on real-time neural decoding with hybrid SSMs. Keep an eye out for a preprint (hopefully) soon 👀
#Cosyne2025 @cosynemeeting.bsky.social
#Cosyne2025 @cosynemeeting.bsky.social
April 4, 2025 at 5:21 AM
Very late, but had a 🔥 time at my first Cosyne presenting my work with @nandahkrishna.bsky.social, Ximeng Mao, @mattperich.bsky.social, and @glajoie.bsky.social on real-time neural decoding with hybrid SSMs. Keep an eye out for a preprint (hopefully) soon 👀
#Cosyne2025 @cosynemeeting.bsky.social
#Cosyne2025 @cosynemeeting.bsky.social
Fresh updates on our efforts to understand the effects of online error manipulation during learing. Turns out learning a task with assistive devices (think training wheels) changes how credit assignment mechanisms shapes neural representations in the brain.
Hot off the presses: big update to our work looking at how adaptive decoders influence neural representations.
We added heroic analyses to show in both experiments & models that the structure of what the brain learns is altered by adaptive decoders. Check it out: www.biorxiv.org/content/10.1...
We added heroic analyses to show in both experiments & models that the structure of what the brain learns is altered by adaptive decoders. Check it out: www.biorxiv.org/content/10.1...
April 3, 2025 at 10:16 PM
Fresh updates on our efforts to understand the effects of online error manipulation during learing. Turns out learning a task with assistive devices (think training wheels) changes how credit assignment mechanisms shapes neural representations in the brain.
Reposted by Guillaume Lajoie
1/7: Super excited to share our new paper! This one should be of interest to neuroscientists and deep learning theory folks. This paper was a collaboration with Alexandre Payeur, @averyryoo.bsky.social, Thomas Jiralerspong, @mattperich.bsky.social, Luca Mazzucato, @glajoie.bsky.social
March 25, 2025 at 3:59 PM
1/7: Super excited to share our new paper! This one should be of interest to neuroscientists and deep learning theory folks. This paper was a collaboration with Alexandre Payeur, @averyryoo.bsky.social, Thomas Jiralerspong, @mattperich.bsky.social, Luca Mazzucato, @glajoie.bsky.social
If you'll be at COSYNE workshops, we got a capstone party planned !
Coming to the #Cosyne2025 workshops? Wanna dance on the final night? We got you covered.
@glajoie.bsky.social and I have organized a party in Tremblant. Come and get on the dance floor y'all. 🕺
April 1st
10PM-3AM
Location: Le P'tit Caribou
DJs Mat Moebius, Xanarelle, and Prosocial
Please share!
@glajoie.bsky.social and I have organized a party in Tremblant. Come and get on the dance floor y'all. 🕺
April 1st
10PM-3AM
Location: Le P'tit Caribou
DJs Mat Moebius, Xanarelle, and Prosocial
Please share!
March 25, 2025 at 1:06 AM
If you'll be at COSYNE workshops, we got a capstone party planned !
Reposted by Guillaume Lajoie
Coming to the #Cosyne2025 workshops? Wanna dance on the final night? We got you covered.
@glajoie.bsky.social and I have organized a party in Tremblant. Come and get on the dance floor y'all. 🕺
April 1st
10PM-3AM
Location: Le P'tit Caribou
DJs Mat Moebius, Xanarelle, and Prosocial
Please share!
@glajoie.bsky.social and I have organized a party in Tremblant. Come and get on the dance floor y'all. 🕺
April 1st
10PM-3AM
Location: Le P'tit Caribou
DJs Mat Moebius, Xanarelle, and Prosocial
Please share!
March 24, 2025 at 5:37 PM
Coming to the #Cosyne2025 workshops? Wanna dance on the final night? We got you covered.
@glajoie.bsky.social and I have organized a party in Tremblant. Come and get on the dance floor y'all. 🕺
April 1st
10PM-3AM
Location: Le P'tit Caribou
DJs Mat Moebius, Xanarelle, and Prosocial
Please share!
@glajoie.bsky.social and I have organized a party in Tremblant. Come and get on the dance floor y'all. 🕺
April 1st
10PM-3AM
Location: Le P'tit Caribou
DJs Mat Moebius, Xanarelle, and Prosocial
Please share!
As sequence models and in-context conditioning for inference are being developed to perform all kinds of ML tasks, we make systematic and tracktable evaluations to compare point v.s. distributional estimates . imo a key step to scale predictive modeling for general ML
🚀 New Preprint! 🚀
In-Context Parametric Inference: Point or Distribution Estimators?
Thrilled to share our work on inferring probabilistic model parameters explicitly conditioned on data, in collab with @yoshuabengio.bsky.social, Nikolay Malkin & @glajoie.bsky.social!
🔗 arxiv.org/abs/2502.11617
In-Context Parametric Inference: Point or Distribution Estimators?
Thrilled to share our work on inferring probabilistic model parameters explicitly conditioned on data, in collab with @yoshuabengio.bsky.social, Nikolay Malkin & @glajoie.bsky.social!
🔗 arxiv.org/abs/2502.11617
In-Context Parametric Inference: Point or Distribution Estimators?
Bayesian and frequentist inference are two fundamental paradigms in statistical estimation. Bayesian methods treat hypotheses as random variables, incorporating priors and updating beliefs via Bayes' ...
arxiv.org
February 28, 2025 at 9:17 PM
As sequence models and in-context conditioning for inference are being developed to perform all kinds of ML tasks, we make systematic and tracktable evaluations to compare point v.s. distributional estimates . imo a key step to scale predictive modeling for general ML
Reposted by Guillaume Lajoie
This week, we’re unveiling two members for the AI Insights for Policymakers program: @glajoie.bsky.social (Mila) and Laleh Seyyed-Kalantari (York University). Register here to partner with them and overcome your AI and policy-related challenges: mila.quebec/en/ai4humani...
February 20, 2025 at 3:46 PM
This week, we’re unveiling two members for the AI Insights for Policymakers program: @glajoie.bsky.social (Mila) and Laleh Seyyed-Kalantari (York University). Register here to partner with them and overcome your AI and policy-related challenges: mila.quebec/en/ai4humani...
Reposted by Guillaume Lajoie
Voici deux nouveaux experts du programme Perspectives sur l’IA pour les responsables des politiques : @glajoie.bsky.social (Mila) et Laleh Seyyed-Kalantari (York Univ.) Échangez avec eux et relevez vos défis liés à l'IA et aux politiques. Inscrivez-vous ici mila.quebec/fr/ia-pour-l...
February 20, 2025 at 3:45 PM
Voici deux nouveaux experts du programme Perspectives sur l’IA pour les responsables des politiques : @glajoie.bsky.social (Mila) et Laleh Seyyed-Kalantari (York Univ.) Échangez avec eux et relevez vos défis liés à l'IA et aux politiques. Inscrivez-vous ici mila.quebec/fr/ia-pour-l...
Reposted by Guillaume Lajoie
The earliest studies on necessary and sufficient neural populations were performed on simple invertebrate circuits. In her latest column, @neurograce.bsky.social asks if this logic still serves us as we tackle more sophisticated outputs.
www.thetransmitter.org/systems-neur...
www.thetransmitter.org/systems-neur...
Claims of necessity, sufficiency don’t work well for studies of complex systems
Early studies on necessary and sufficient neural populations were done on simple invertebrate circuits. Does this logic work for complex outputs?
www.thetransmitter.org
February 7, 2025 at 2:24 PM
The earliest studies on necessary and sufficient neural populations were performed on simple invertebrate circuits. In her latest column, @neurograce.bsky.social asks if this logic still serves us as we tackle more sophisticated outputs.
www.thetransmitter.org/systems-neur...
www.thetransmitter.org/systems-neur...
Reposted by Guillaume Lajoie
@theguardian.com has produced an excellent recap of some of the key points of the International AI Safety Report. Full article below: www.theguardian.com/technology/2...
What International AI Safety report says on jobs, climate, cyberwar and more
Wide-ranging investigation says impact on work likely to be profound, but opinion on risk of human extinction varies
www.theguardian.com
February 4, 2025 at 3:12 PM
@theguardian.com has produced an excellent recap of some of the key points of the International AI Safety Report. Full article below: www.theguardian.com/technology/2...
Reposted by Guillaume Lajoie
Talk by Guillaume Lajoie at the Montreal AI and Neuroscience (MAIN) Conference on credit assignment in neural networks without plasticity.
#neuroscience #neuroAI #AI #compneuro @glajoie.bsky.social www.youtube.com/watch?v=CvCq...
#neuroscience #neuroAI #AI #compneuro @glajoie.bsky.social www.youtube.com/watch?v=CvCq...
Guillaume Lajoie - Credit assignment in neural networks without plasticity
YouTube video by MAIN Conference
www.youtube.com
January 13, 2025 at 1:42 PM
Talk by Guillaume Lajoie at the Montreal AI and Neuroscience (MAIN) Conference on credit assignment in neural networks without plasticity.
#neuroscience #neuroAI #AI #compneuro @glajoie.bsky.social www.youtube.com/watch?v=CvCq...
#neuroscience #neuroAI #AI #compneuro @glajoie.bsky.social www.youtube.com/watch?v=CvCq...
Long time coming. A very cool project that showcases the advantages of single neuron adaptation in RNNs.
#PLOSCompBio: Neural networks with optimized single-neuron adaptation uncover biologically plausible regulari ... dx.plos.org/10.1371/jour...
Props to V. Geadah and co-authors!
#PLOSCompBio: Neural networks with optimized single-neuron adaptation uncover biologically plausible regulari ... dx.plos.org/10.1371/jour...
Props to V. Geadah and co-authors!
Neural networks with optimized single-neuron adaptation uncover biologically plausible regularization
Author summary Evolution has shaped neural circuits in the brain to support complex tasks and behavior. In doing so, single neurons have developed intriguing coding properties such as heterogeneous an...
dx.plos.org
January 9, 2025 at 10:55 PM
Long time coming. A very cool project that showcases the advantages of single neuron adaptation in RNNs.
#PLOSCompBio: Neural networks with optimized single-neuron adaptation uncover biologically plausible regulari ... dx.plos.org/10.1371/jour...
Props to V. Geadah and co-authors!
#PLOSCompBio: Neural networks with optimized single-neuron adaptation uncover biologically plausible regulari ... dx.plos.org/10.1371/jour...
Props to V. Geadah and co-authors!