Blake Richards
@tyrellturing.bsky.social
Researcher at Google and CIFAR Fellow, working on the intersection of machine learning and neuroscience in Montréal (academic affiliations: @mcgill.ca and @mila-quebec.bsky.social).
Reposted by Blake Richards
Please repost: another kind of Black-Friday deal!
November 28, 2025 at 6:43 PM
Please repost: another kind of Black-Friday deal!
Reposted by Blake Richards
I always suggest that people think about what urban centres like New York or London were like 150 years ago — dangerous, unbelievably polluted air and water, desperately inequitable, few trees or green space.
And then imagine building the cities where we look back to *today* and see the same thing.
And then imagine building the cities where we look back to *today* and see the same thing.
At its peak, 100-200k NYC horses, 30 lbs of poop/day each. People would use these boot scrapers, that you can still see everywhere today built into the brownstone wrought iron fences, to scrape, 70%? of the poop off the bottom of their shoes before they went into the house. Horse poop everywhere.
November 28, 2025 at 5:53 PM
I always suggest that people think about what urban centres like New York or London were like 150 years ago — dangerous, unbelievably polluted air and water, desperately inequitable, few trees or green space.
And then imagine building the cities where we look back to *today* and see the same thing.
And then imagine building the cities where we look back to *today* and see the same thing.
Reposted by Blake Richards
The basal forebrain plays the cortex like a piano.
A cholinergic mechanism orchestrating task-dependent computation across the cortex
In an ever-changing environment, animals often need to switch between performing different tasks involving distinct sets of cognitive processes. Many such tasks involve neural activity distributed acr...
www.biorxiv.org
November 28, 2025 at 5:51 PM
The basal forebrain plays the cortex like a piano.
Reposted by Blake Richards
🧠👀
'These findings reveal high-dimensional aspects of cortical representation undetectable with conventional methods, such as RSA, & contradict previous theories suggesting that high-level visual cortex representations are low-dimensional.' #neuroskyence
journals.plos.org/ploscompbiol...
'These findings reveal high-dimensional aspects of cortical representation undetectable with conventional methods, such as RSA, & contradict previous theories suggesting that high-level visual cortex representations are low-dimensional.' #neuroskyence
journals.plos.org/ploscompbiol...
Universal scale-free representations in human visual cortex
Author summary The human cerebral cortex is thought to encode sensory information in population activity patterns, but the statistical structure of these population codes has yet to be characterized. ...
journals.plos.org
November 27, 2025 at 10:35 PM
🧠👀
'These findings reveal high-dimensional aspects of cortical representation undetectable with conventional methods, such as RSA, & contradict previous theories suggesting that high-level visual cortex representations are low-dimensional.' #neuroskyence
journals.plos.org/ploscompbiol...
'These findings reveal high-dimensional aspects of cortical representation undetectable with conventional methods, such as RSA, & contradict previous theories suggesting that high-level visual cortex representations are low-dimensional.' #neuroskyence
journals.plos.org/ploscompbiol...
Reposted by Blake Richards
Task learning is compositional, so would behavior be!
www.nature.com/articles/s41...
www.nature.com/articles/s41...
Building compositional tasks with shared neural subspaces - Nature
The brain can flexibly perform multiple tasks by compositionally combining task-relevant neural representations.
www.nature.com
November 27, 2025 at 5:22 PM
Task learning is compositional, so would behavior be!
www.nature.com/articles/s41...
www.nature.com/articles/s41...
Reposted by Blake Richards
🚨New Preprint!
How can we model natural scene representations in visual cortex? A solution is in active vision: predict the features of the next glimpse! arxiv.org/abs/2511.12715
+ @adriendoerig.bsky.social , @alexanderkroner.bsky.social , @carmenamme.bsky.social , @timkietzmann.bsky.social
🧵 1/14
How can we model natural scene representations in visual cortex? A solution is in active vision: predict the features of the next glimpse! arxiv.org/abs/2511.12715
+ @adriendoerig.bsky.social , @alexanderkroner.bsky.social , @carmenamme.bsky.social , @timkietzmann.bsky.social
🧵 1/14
Predicting upcoming visual features during eye movements yields scene representations aligned with human visual cortex
Scenes are complex, yet structured collections of parts, including objects and surfaces, that exhibit spatial and semantic relations to one another. An effective visual system therefore needs unified ...
arxiv.org
November 18, 2025 at 12:37 PM
🚨New Preprint!
How can we model natural scene representations in visual cortex? A solution is in active vision: predict the features of the next glimpse! arxiv.org/abs/2511.12715
+ @adriendoerig.bsky.social , @alexanderkroner.bsky.social , @carmenamme.bsky.social , @timkietzmann.bsky.social
🧵 1/14
How can we model natural scene representations in visual cortex? A solution is in active vision: predict the features of the next glimpse! arxiv.org/abs/2511.12715
+ @adriendoerig.bsky.social , @alexanderkroner.bsky.social , @carmenamme.bsky.social , @timkietzmann.bsky.social
🧵 1/14
Reposted by Blake Richards
1/6 New preprint 🚀 How does the cortex learn to represent things and how they move without reconstructing sensory stimuli? We developed a circuit-centric recurrent predictive learning (RPL) model based on JEPAs.
🔗 doi.org/10.1101/2025...
Led by @atenagm.bsky.social @mshalvagal.bsky.social
🔗 doi.org/10.1101/2025...
Led by @atenagm.bsky.social @mshalvagal.bsky.social
November 27, 2025 at 8:24 AM
1/6 New preprint 🚀 How does the cortex learn to represent things and how they move without reconstructing sensory stimuli? We developed a circuit-centric recurrent predictive learning (RPL) model based on JEPAs.
🔗 doi.org/10.1101/2025...
Led by @atenagm.bsky.social @mshalvagal.bsky.social
🔗 doi.org/10.1101/2025...
Led by @atenagm.bsky.social @mshalvagal.bsky.social
Reposted by Blake Richards
Ada, Countess of Lovelace, daughter of Lord Byron, mathematician & a pioneer of computing; born 1815, died #OTD 1852. #WomeninStem
Painted by Margaret Sarah Carpenter 1836
UK Government Art Collection
Painted by Margaret Sarah Carpenter 1836
UK Government Art Collection
November 27, 2025 at 6:07 AM
Ada, Countess of Lovelace, daughter of Lord Byron, mathematician & a pioneer of computing; born 1815, died #OTD 1852. #WomeninStem
Painted by Margaret Sarah Carpenter 1836
UK Government Art Collection
Painted by Margaret Sarah Carpenter 1836
UK Government Art Collection
Reposted by Blake Richards
People on BlueSky: AI is useless! A stochastic parrot!
Mathematicians/biologists/physicists: It is already helping us do frontier technical research and in some cases solve open problems arxiv.org/pdf/2511.16072
(There are of course, as always, many caveats, but the paper is genuinely remarkable)
Mathematicians/biologists/physicists: It is already helping us do frontier technical research and in some cases solve open problems arxiv.org/pdf/2511.16072
(There are of course, as always, many caveats, but the paper is genuinely remarkable)
arxiv.org
November 26, 2025 at 3:51 PM
People on BlueSky: AI is useless! A stochastic parrot!
Mathematicians/biologists/physicists: It is already helping us do frontier technical research and in some cases solve open problems arxiv.org/pdf/2511.16072
(There are of course, as always, many caveats, but the paper is genuinely remarkable)
Mathematicians/biologists/physicists: It is already helping us do frontier technical research and in some cases solve open problems arxiv.org/pdf/2511.16072
(There are of course, as always, many caveats, but the paper is genuinely remarkable)
Reposted by Blake Richards
Nature Sci Rep publishes incoherent AI slop. eLife publishes a paper which the reviewers didn't agree with, making all the comments and responses public with thoughtful commentary. One of these journals got delisted by Web of Science for quality concerns from not doing peer review. Guess which one?
November 27, 2025 at 1:35 PM
Nature Sci Rep publishes incoherent AI slop. eLife publishes a paper which the reviewers didn't agree with, making all the comments and responses public with thoughtful commentary. One of these journals got delisted by Web of Science for quality concerns from not doing peer review. Guess which one?
Reposted by Blake Richards
If you enjoyed The Verge essay, a new paper just dropped that further explores how our brains connect language to our broader understanding of the world. Shout out to @coltoncasto.bsky.social @neuranna.bsky.social @evfedorenko.bsky.social & @nancykanwisher.bsky.social for derailing my Wednesday.
November 26, 2025 at 5:46 PM
If you enjoyed The Verge essay, a new paper just dropped that further explores how our brains connect language to our broader understanding of the world. Shout out to @coltoncasto.bsky.social @neuranna.bsky.social @evfedorenko.bsky.social & @nancykanwisher.bsky.social for derailing my Wednesday.
Reposted by Blake Richards
@thetransmitter.bsky.social’s “New Lab Directory” features a list of new neuroscience labs that opened in 2024-2025, and some set to launch in 2026. Check out the list to learn about the work of more than 50 new neuroscience labs. www.thetransmitter.org/community/th...
#StateOfNeuroscience
#StateOfNeuroscience
The Transmitter’s New Lab Directory
Learn about neuroscience labs launched in the past two years, plus a few opening their doors in 2026.
www.thetransmitter.org
November 26, 2025 at 9:28 PM
@thetransmitter.bsky.social’s “New Lab Directory” features a list of new neuroscience labs that opened in 2024-2025, and some set to launch in 2026. Check out the list to learn about the work of more than 50 new neuroscience labs. www.thetransmitter.org/community/th...
#StateOfNeuroscience
#StateOfNeuroscience
Reposted by Blake Richards
New preprint alert!
Cognitive maps are flexible, dynamic, (re)constructed representations
#psychscisky #neuroskyence #cognition #philsky 🧪
Cognitive maps are flexible, dynamic, (re)constructed representations
#psychscisky #neuroskyence #cognition #philsky 🧪
OSF
osf.io
November 26, 2025 at 6:11 PM
New preprint alert!
Cognitive maps are flexible, dynamic, (re)constructed representations
#psychscisky #neuroskyence #cognition #philsky 🧪
Cognitive maps are flexible, dynamic, (re)constructed representations
#psychscisky #neuroskyence #cognition #philsky 🧪
A tale of the need for flexible cognition... 😂
In Tesco’s this afternoon: an elderly Polish man at the self-checkout, trying to buy a pint of milk and a white radish. There is no picture for the radish on the machine. The assistant doesn’t know what it is. She asks a colleague: “It’s a white radish.” There is no entry for it on the machine.
November 22, 2025 at 8:41 PM
A tale of the need for flexible cognition... 😂
Reposted by Blake Richards
AGI is just astrology for smart computer boys
November 21, 2025 at 3:12 AM
AGI is just astrology for smart computer boys
Reposted by Blake Richards
PSA to academics posting threads about your paper here: you can (and should) post the link to the paper in the first post. Your X/Twitter brain rot have have you thinking otherwise, but please free yourself of that. (Also you can call them 'blue-prints' if you want).
November 21, 2025 at 2:56 AM
PSA to academics posting threads about your paper here: you can (and should) post the link to the paper in the first post. Your X/Twitter brain rot have have you thinking otherwise, but please free yourself of that. (Also you can call them 'blue-prints' if you want).
Reposted by Blake Richards
I think almost all scientific projects should be planned carefully. And I think an app can dramatically improve that. So I wrote an app for that (free for now, if you can fund this let me know). I tested it quite a bit (>8000 users in beta so far). try it: planyourscience.com
November 20, 2025 at 3:33 PM
I think almost all scientific projects should be planned carefully. And I think an app can dramatically improve that. So I wrote an app for that (free for now, if you can fund this let me know). I tested it quite a bit (>8000 users in beta so far). try it: planyourscience.com
Reposted by Blake Richards
my little take on whole-brain neurophysiology and what it tells us about global coordination of neural activity on behavioural timescales
(I steered clear of tasteless analogies for this one...)
authors.elsevier.com/a/1m7H5_LsQS...
(I steered clear of tasteless analogies for this one...)
authors.elsevier.com/a/1m7H5_LsQS...
authors.elsevier.com
November 19, 2025 at 2:05 PM
my little take on whole-brain neurophysiology and what it tells us about global coordination of neural activity on behavioural timescales
(I steered clear of tasteless analogies for this one...)
authors.elsevier.com/a/1m7H5_LsQS...
(I steered clear of tasteless analogies for this one...)
authors.elsevier.com/a/1m7H5_LsQS...
Reposted by Blake Richards
We went back to the drawing board to think about what information is available to the visual system upon which it could build scene representations.
The outcome: a self-supervised training objective based on active vision that beats the SOTA on NSD representational alignment. 👇
The outcome: a self-supervised training objective based on active vision that beats the SOTA on NSD representational alignment. 👇
🚨New Preprint!
How can we model natural scene representations in visual cortex? A solution is in active vision: predict the features of the next glimpse! arxiv.org/abs/2511.12715
+ @adriendoerig.bsky.social , @alexanderkroner.bsky.social , @carmenamme.bsky.social , @timkietzmann.bsky.social
🧵 1/14
How can we model natural scene representations in visual cortex? A solution is in active vision: predict the features of the next glimpse! arxiv.org/abs/2511.12715
+ @adriendoerig.bsky.social , @alexanderkroner.bsky.social , @carmenamme.bsky.social , @timkietzmann.bsky.social
🧵 1/14
Predicting upcoming visual features during eye movements yields scene representations aligned with human visual cortex
Scenes are complex, yet structured collections of parts, including objects and surfaces, that exhibit spatial and semantic relations to one another. An effective visual system therefore needs unified ...
arxiv.org
November 18, 2025 at 2:14 PM
We went back to the drawing board to think about what information is available to the visual system upon which it could build scene representations.
The outcome: a self-supervised training objective based on active vision that beats the SOTA on NSD representational alignment. 👇
The outcome: a self-supervised training objective based on active vision that beats the SOTA on NSD representational alignment. 👇
Reposted by Blake Richards
Putting the figures at the end of your preprint is one thing, but separating the CAPTIONS from the figures (with both at the end of the paper) is just plain cruel
November 18, 2025 at 3:07 PM
Putting the figures at the end of your preprint is one thing, but separating the CAPTIONS from the figures (with both at the end of the paper) is just plain cruel
Reposted by Blake Richards
Coal isn't cost-effective anymore, and countries recognize it. Huge, since South Korea has been relying on coal for ~30% of their electricity.
www.theguardian.com/environment/...
www.theguardian.com/environment/...
South Korean decision to close all coal-fired power plants by 2040 sounds alarm for Australian exports
Decision announced at Cop30 climate conference signposts risks for Australia’s reliance on fossil fuel exports, analysts say
www.theguardian.com
November 17, 2025 at 2:51 PM
Coal isn't cost-effective anymore, and countries recognize it. Huge, since South Korea has been relying on coal for ~30% of their electricity.
www.theguardian.com/environment/...
www.theguardian.com/environment/...
Reposted by Blake Richards
This is an excellent blueprint on a very fascinating use of AI scientist! And the results and super cool and interesting! 🤩
I have been asked this when talking about our work on using powerlaws to study representation quality in deep neural networks, glad to have a more concrete answer now! 😃
I have been asked this when talking about our work on using powerlaws to study representation quality in deep neural networks, glad to have a more concrete answer now! 😃
1. New preprint resolving a conundrum in systems neuroscience with an AI scientist, and humans Reilly Tilbury, Dabin Kwon, @haydari.bsky.social, @jacobmratliff.bsky.social, @bio-emergent.bsky.social, @carandinilab.net, @kevinjmiller.bsky.social, @neurokim.bsky.social
www.biorxiv.org/content/10.1...
www.biorxiv.org/content/10.1...
Characterizing neuronal population geometry with AI equation discovery
The visual cortex contains millions of neurons, whose combined activity forms a population code representing visual stimuli. There is, however, a discrepancy between our understanding of this code at ...
www.biorxiv.org
November 16, 2025 at 10:29 PM
This is an excellent blueprint on a very fascinating use of AI scientist! And the results and super cool and interesting! 🤩
I have been asked this when talking about our work on using powerlaws to study representation quality in deep neural networks, glad to have a more concrete answer now! 😃
I have been asked this when talking about our work on using powerlaws to study representation quality in deep neural networks, glad to have a more concrete answer now! 😃
Reposted by Blake Richards
1. New preprint resolving a conundrum in systems neuroscience with an AI scientist, and humans Reilly Tilbury, Dabin Kwon, @haydari.bsky.social, @jacobmratliff.bsky.social, @bio-emergent.bsky.social, @carandinilab.net, @kevinjmiller.bsky.social, @neurokim.bsky.social
www.biorxiv.org/content/10.1...
www.biorxiv.org/content/10.1...
Characterizing neuronal population geometry with AI equation discovery
The visual cortex contains millions of neurons, whose combined activity forms a population code representing visual stimuli. There is, however, a discrepancy between our understanding of this code at ...
www.biorxiv.org
November 14, 2025 at 6:07 PM
1. New preprint resolving a conundrum in systems neuroscience with an AI scientist, and humans Reilly Tilbury, Dabin Kwon, @haydari.bsky.social, @jacobmratliff.bsky.social, @bio-emergent.bsky.social, @carandinilab.net, @kevinjmiller.bsky.social, @neurokim.bsky.social
www.biorxiv.org/content/10.1...
www.biorxiv.org/content/10.1...
Reposted by Blake Richards
GDM WeatherNext 2
8x faster than v1, it can compute extreme situations and game out scenarios in one minute flat on a single TPU (as opposed to hours of supercomputer time for traditional algorithms)
will be available in all of Google’s weather apps
blog.google/technology/g...
8x faster than v1, it can compute extreme situations and game out scenarios in one minute flat on a single TPU (as opposed to hours of supercomputer time for traditional algorithms)
will be available in all of Google’s weather apps
blog.google/technology/g...
WeatherNext 2: Our most advanced weather forecasting model
The new AI model delivers more efficient, more accurate and higher-resolution global weather predictions.
blog.google
November 17, 2025 at 6:39 PM
GDM WeatherNext 2
8x faster than v1, it can compute extreme situations and game out scenarios in one minute flat on a single TPU (as opposed to hours of supercomputer time for traditional algorithms)
will be available in all of Google’s weather apps
blog.google/technology/g...
8x faster than v1, it can compute extreme situations and game out scenarios in one minute flat on a single TPU (as opposed to hours of supercomputer time for traditional algorithms)
will be available in all of Google’s weather apps
blog.google/technology/g...
I largely agree with this, with one caveat:
Algorithms/AI *are* a key barrier to progress in neuro-engineering and neuro-tech.
But, for actually *understanding* the brain, indeed, our major barrier is the inability to measure the things we could use to test our computational theories.
Algorithms/AI *are* a key barrier to progress in neuro-engineering and neuro-tech.
But, for actually *understanding* the brain, indeed, our major barrier is the inability to measure the things we could use to test our computational theories.
Same for neuroscience. The lack of ability to measure many neurons’ activity, perturb them, and measure intracellular processes and connections is what limits understanding the brain.
The key barriers are not algorithms or AI.
🧪#neuroscience 🧠🤖 #MLSky
The key barriers are not algorithms or AI.
🧪#neuroscience 🧠🤖 #MLSky
November 17, 2025 at 6:14 PM
I largely agree with this, with one caveat:
Algorithms/AI *are* a key barrier to progress in neuro-engineering and neuro-tech.
But, for actually *understanding* the brain, indeed, our major barrier is the inability to measure the things we could use to test our computational theories.
Algorithms/AI *are* a key barrier to progress in neuro-engineering and neuro-tech.
But, for actually *understanding* the brain, indeed, our major barrier is the inability to measure the things we could use to test our computational theories.