David Klindt
@david-klindt.bsky.social
AI and Neuroscience, Assistant Professor at CSHL
Pinned
From superposition to sparse codes: interpretable representations in neural networks
Understanding how information is represented in neural networks is a fundamental challenge in both neuroscience and artificial intelligence. Despite their nonlinear architectures, recent evidence sugg...
arxiv.org
🔵 New paper! We explore sparse coding, superposition, and the Linear Representation Hypothesis (LRH) through identifiability theory, compressed sensing, and interpretability. If you’re curious about lifting neural reps out of superposition, this might interest you! 🤓
arxiv.org/abs/2503.01824
arxiv.org/abs/2503.01824
Reposted by David Klindt
Simultaneous detection and estimation in olfactory sensing https://www.biorxiv.org/content/10.1101/2025.11.01.686013v1
November 3, 2025 at 11:15 PM
Simultaneous detection and estimation in olfactory sensing https://www.biorxiv.org/content/10.1101/2025.11.01.686013v1
Reposted by David Klindt
Brown University Rejects White House Deal for Special Treatment
www.nytimes.com
October 15, 2025 at 9:58 PM
Reposted by David Klindt
So I get that a Neuroscientist Couldn’t Understand a Microprocessor, and TBH I’m ok with that. But could a neuroscientist understand a deep RNN? Because that seems like a more pressing issue.
*assuming you think the brain operates through the parallel activity of many connected input/output units
*assuming you think the brain operates through the parallel activity of many connected input/output units
October 10, 2025 at 11:02 AM
So I get that a Neuroscientist Couldn’t Understand a Microprocessor, and TBH I’m ok with that. But could a neuroscientist understand a deep RNN? Because that seems like a more pressing issue.
*assuming you think the brain operates through the parallel activity of many connected input/output units
*assuming you think the brain operates through the parallel activity of many connected input/output units
Reposted by David Klindt
A study led by Cina Aghamohammadi is now out in @natcomms.nature.com! We developed a mathematical framework for partitioning spiking variability, which revealed that spiking irregularity is nearly invariant for each neuron and decreases along the cortical hierarchy.
www.nature.com/articles/s41...
www.nature.com/articles/s41...
October 12, 2025 at 12:42 AM
A study led by Cina Aghamohammadi is now out in @natcomms.nature.com! We developed a mathematical framework for partitioning spiking variability, which revealed that spiking irregularity is nearly invariant for each neuron and decreases along the cortical hierarchy.
www.nature.com/articles/s41...
www.nature.com/articles/s41...
Reposted by David Klindt
Over the past year, my lab has been working on fleshing out theory + applications of the Platonic Representation Hypothesis.
Today I want to share two new works on this topic:
Eliciting higher alignment: arxiv.org/abs/2510.02425
Unpaired learning of unified reps: arxiv.org/abs/2510.08492
1/9
Today I want to share two new works on this topic:
Eliciting higher alignment: arxiv.org/abs/2510.02425
Unpaired learning of unified reps: arxiv.org/abs/2510.08492
1/9
October 10, 2025 at 10:13 PM
Over the past year, my lab has been working on fleshing out theory + applications of the Platonic Representation Hypothesis.
Today I want to share two new works on this topic:
Eliciting higher alignment: arxiv.org/abs/2510.02425
Unpaired learning of unified reps: arxiv.org/abs/2510.08492
1/9
Today I want to share two new works on this topic:
Eliciting higher alignment: arxiv.org/abs/2510.02425
Unpaired learning of unified reps: arxiv.org/abs/2510.08492
1/9
Reposted by David Klindt
Superposition has reshaped interpretability research. In our @unireps.bsky.social paper led by @andre-longon.bsky.social we show it also matters for measuring alignment! Two systems can represent the same features yet appear misaligned if those features are mixed differently across neurons.
Superposition disentanglement of neural representations reveals hidden alignment
The superposition hypothesis states that a single neuron within a population may participate in the representation of multiple features in order for the population to represent more features than the ...
arxiv.org
October 8, 2025 at 8:54 PM
Superposition has reshaped interpretability research. In our @unireps.bsky.social paper led by @andre-longon.bsky.social we show it also matters for measuring alignment! Two systems can represent the same features yet appear misaligned if those features are mixed differently across neurons.
retweeting because this needs a multiplier.
October 7, 2025 at 11:29 PM
retweeting because this needs a multiplier.
Reposted by David Klindt
🚨Big news!🚨
The lab is relocating to Lisbon, joining a great team of experimental and theoretical neuroscientists, and the Neurotechnology Warehouse, a new initiative to bridge basic and translational research.
I'll be sharing postdoc openings soon. Come join us in this new incarnation of the lab!
The lab is relocating to Lisbon, joining a great team of experimental and theoretical neuroscientists, and the Neurotechnology Warehouse, a new initiative to bridge basic and translational research.
I'll be sharing postdoc openings soon. Come join us in this new incarnation of the lab!
🧠🎼 What does it take to restore movement? Neuroscientist and engineer, @juangallego.bsky.social, joins the new Centre for Restorative Neurotechnology at the Champalimaud Foundation.
🔗 Find out more in this interview: www.fchampalimaud.org/news/juan-al...
🔗 Find out more in this interview: www.fchampalimaud.org/news/juan-al...
October 7, 2025 at 4:37 PM
🚨Big news!🚨
The lab is relocating to Lisbon, joining a great team of experimental and theoretical neuroscientists, and the Neurotechnology Warehouse, a new initiative to bridge basic and translational research.
I'll be sharing postdoc openings soon. Come join us in this new incarnation of the lab!
The lab is relocating to Lisbon, joining a great team of experimental and theoretical neuroscientists, and the Neurotechnology Warehouse, a new initiative to bridge basic and translational research.
I'll be sharing postdoc openings soon. Come join us in this new incarnation of the lab!
Reposted by David Klindt
Join us for the 3rd edition of the UniReps Workshop at #NeurIPS2025! 🧠🤖
We're bringing together researchers from #AI, #Neuroscience, and #CogSci to explore why different neural models learn similar representations.
📝 Call for Papers is OPEN on OpenReview!
🌐 Website: unireps.org/2025/
We're bringing together researchers from #AI, #Neuroscience, and #CogSci to explore why different neural models learn similar representations.
📝 Call for Papers is OPEN on OpenReview!
🌐 Website: unireps.org/2025/
UniReps Workshop
Unifying Representations in Neural Models
unireps.org
July 16, 2025 at 12:28 PM
Join us for the 3rd edition of the UniReps Workshop at #NeurIPS2025! 🧠🤖
We're bringing together researchers from #AI, #Neuroscience, and #CogSci to explore why different neural models learn similar representations.
📝 Call for Papers is OPEN on OpenReview!
🌐 Website: unireps.org/2025/
We're bringing together researchers from #AI, #Neuroscience, and #CogSci to explore why different neural models learn similar representations.
📝 Call for Papers is OPEN on OpenReview!
🌐 Website: unireps.org/2025/
Reposted by David Klindt
📢 We're thrilled to announce that the UniReps workshop will return to @NeurIPSConf 25 for its 3rd edition!
🔵Check our new Call for Papers at: unireps.org/2025/call-fo...
🔴Submit your work at: openreview.net/group?id=Neu...
See you in San Diego!🌴🇺🇸
🔵Check our new Call for Papers at: unireps.org/2025/call-fo...
🔴Submit your work at: openreview.net/group?id=Neu...
See you in San Diego!🌴🇺🇸
July 10, 2025 at 3:27 PM
📢 We're thrilled to announce that the UniReps workshop will return to @NeurIPSConf 25 for its 3rd edition!
🔵Check our new Call for Papers at: unireps.org/2025/call-fo...
🔴Submit your work at: openreview.net/group?id=Neu...
See you in San Diego!🌴🇺🇸
🔵Check our new Call for Papers at: unireps.org/2025/call-fo...
🔴Submit your work at: openreview.net/group?id=Neu...
See you in San Diego!🌴🇺🇸
Reposted by David Klindt
Delighted to see our new collaboration on ecological neuroscience 🧩🌿🧠 announced today! A huge ❤️🙏🏼 to @simonsfoundation.org
I’m so excited by this theory-driven question. It’s core to our research on adaptive intelligence & sensorimotor systems 🙌 #SCENE
www.simonsfoundation.org/2025/04/24/s...
I’m so excited by this theory-driven question. It’s core to our research on adaptive intelligence & sensorimotor systems 🙌 #SCENE
www.simonsfoundation.org/2025/04/24/s...
Simons Collaboration on Ecological Neuroscience
The mission of the Simons Collaboration on Ecological NEuroscience (SCENE) is to understand how affordances offered by the world shape representations in the mind and the brain.
www.simonsfoundation.org
April 24, 2025 at 4:32 PM
Delighted to see our new collaboration on ecological neuroscience 🧩🌿🧠 announced today! A huge ❤️🙏🏼 to @simonsfoundation.org
I’m so excited by this theory-driven question. It’s core to our research on adaptive intelligence & sensorimotor systems 🙌 #SCENE
www.simonsfoundation.org/2025/04/24/s...
I’m so excited by this theory-driven question. It’s core to our research on adaptive intelligence & sensorimotor systems 🙌 #SCENE
www.simonsfoundation.org/2025/04/24/s...
🚨 New paper on the limits of identifiability theory!
Mathematical guarantees for neural representations are thrilling—especially in a field driven by trial and error.
But sometimes theory lives in "fairyland" ...
👉 arxiv.org/abs/2504.13101
Mathematical guarantees for neural representations are thrilling—especially in a field driven by trial and error.
But sometimes theory lives in "fairyland" ...
👉 arxiv.org/abs/2504.13101
An Empirically Grounded Identifiability Theory Will Accelerate Self-Supervised Learning Research
Self-Supervised Learning (SSL) powers many current AI systems. As research interest and investment grow, the SSL design space continues to expand. The Platonic view of SSL, following the Platonic Repr...
arxiv.org
April 18, 2025 at 2:15 PM
🚨 New paper on the limits of identifiability theory!
Mathematical guarantees for neural representations are thrilling—especially in a field driven by trial and error.
But sometimes theory lives in "fairyland" ...
👉 arxiv.org/abs/2504.13101
Mathematical guarantees for neural representations are thrilling—especially in a field driven by trial and error.
But sometimes theory lives in "fairyland" ...
👉 arxiv.org/abs/2504.13101
Wow this is really cool, especially since the sensors are so close; and awesome to see the downstream effect on head direction coding
🚨new paper alert
Blind mice use stereo olfaction, comparing smells between nostrils, to maintain a stable sense of direction. Blocking this ability disrupts their internal compass.
Kudos to @kasumbisa.bsky.social! Another cool chapter of the Trenholm-Peyrache collab😉
www.nature.com/articles/s41...
Blind mice use stereo olfaction, comparing smells between nostrils, to maintain a stable sense of direction. Blocking this ability disrupts their internal compass.
Kudos to @kasumbisa.bsky.social! Another cool chapter of the Trenholm-Peyrache collab😉
www.nature.com/articles/s41...
Stereo olfaction underlies stable coding of head direction in blind mice - Nature Communications
Stereo olfaction involves comparing odor differences between the two nostrils. Here, using neuronal recordings and a behavioral test, the authors demonstrate that blind mice use stereo olfaction to fo...
www.nature.com
April 16, 2025 at 4:49 PM
Wow this is really cool, especially since the sensors are so close; and awesome to see the downstream effect on head direction coding
Reposted by David Klindt
A Perspective from the Ecker lab discusses the progress and challenges of using computer vision approaches for behavior studies of primates in natural environments.
www.nature.com/articles/s41...
www.nature.com/articles/s41...
April 14, 2025 at 3:44 PM
A Perspective from the Ecker lab discusses the progress and challenges of using computer vision approaches for behavior studies of primates in natural environments.
www.nature.com/articles/s41...
www.nature.com/articles/s41...
Reposted by David Klindt
Come do cool BCI experiments with wellcome trust fellow Mostafa!
Job Alert (please repost)!
We are looking to hire a Research Assistant to join us in an exciting project looking into Brain-Computer Interfaces (BCIs) and how brains learn to control them.
We are looking to hire a Research Assistant to join us in an exciting project looking into Brain-Computer Interfaces (BCIs) and how brains learn to control them.
April 14, 2025 at 11:46 AM
Come do cool BCI experiments with wellcome trust fellow Mostafa!
Amazing work! I dreamt about getting this to work at such scale and predicting anatomical cell types from functional data ever since we wrote the what/where readout paper 🤩
After 7 years, thrilled to finally share our #MICrONS functional connectomics results!
We recorded activity from ~75K neurons in the visual cortex of a single mouse, then mapped its wiring using electron microscopy.
nature.com/immersive/d42859-025-00001-w/index.html
We recorded activity from ~75K neurons in the visual cortex of a single mouse, then mapped its wiring using electron microscopy.
nature.com/immersive/d42859-025-00001-w/index.html
The MICrONS Project
An unprecedented dataset of high resolution anatomical images of individual cells in mouse visual cortex, mapped on to their responses. This integrated view of function and structure lays a foundation...
nature.com
April 11, 2025 at 9:24 PM
Amazing work! I dreamt about getting this to work at such scale and predicting anatomical cell types from functional data ever since we wrote the what/where readout paper 🤩
Reposted by David Klindt
After 7 years, thrilled to finally share our #MICrONS functional connectomics results!
We recorded activity from ~75K neurons in the visual cortex of a single mouse, then mapped its wiring using electron microscopy.
nature.com/immersive/d42859-025-00001-w/index.html
We recorded activity from ~75K neurons in the visual cortex of a single mouse, then mapped its wiring using electron microscopy.
nature.com/immersive/d42859-025-00001-w/index.html
The MICrONS Project
An unprecedented dataset of high resolution anatomical images of individual cells in mouse visual cortex, mapped on to their responses. This integrated view of function and structure lays a foundation...
nature.com
April 10, 2025 at 11:46 PM
After 7 years, thrilled to finally share our #MICrONS functional connectomics results!
We recorded activity from ~75K neurons in the visual cortex of a single mouse, then mapped its wiring using electron microscopy.
nature.com/immersive/d42859-025-00001-w/index.html
We recorded activity from ~75K neurons in the visual cortex of a single mouse, then mapped its wiring using electron microscopy.
nature.com/immersive/d42859-025-00001-w/index.html
Reposted by David Klindt
📣 Grad students and postdocs in computational and theoretical neuroscience: please consider applying for the 2025 Flatiron Institute Junior Theoretical Neuroscience Workshop! All expenses are covered. Apply by April 14. jtnworkshop2025.flatironinstitute.org
April 9, 2025 at 4:11 PM
📣 Grad students and postdocs in computational and theoretical neuroscience: please consider applying for the 2025 Flatiron Institute Junior Theoretical Neuroscience Workshop! All expenses are covered. Apply by April 14. jtnworkshop2025.flatironinstitute.org
Reposted by David Klindt
Reposted by David Klindt
We're bringing together leading researchers from top institutions worldwide to Split, Croatia this summer. If you're passionate about brain-inspired AI, computational neuroscience, or fundamental mathematical principles driving intelligence, this conference is the place to be!
April 1, 2025 at 1:23 PM
We're bringing together leading researchers from top institutions worldwide to Split, Croatia this summer. If you're passionate about brain-inspired AI, computational neuroscience, or fundamental mathematical principles driving intelligence, this conference is the place to be!
Reposted by David Klindt
Going to #Cosyne2025?
Join us (w/ @mdiamantaki.bsky.social) for our exciting workshop
Object-centric Neuronal Representations
toliaslab.org/workshop/cos...
Featuring diverse species💁♀️🐒🐁🐝🕷️🤖
Our goal: Discuss universal & species-specific principles of object-centric vision
See you in Montreal🥳
Join us (w/ @mdiamantaki.bsky.social) for our exciting workshop
Object-centric Neuronal Representations
toliaslab.org/workshop/cos...
Featuring diverse species💁♀️🐒🐁🐝🕷️🤖
Our goal: Discuss universal & species-specific principles of object-centric vision
See you in Montreal🥳
March 25, 2025 at 4:57 PM
Going to #Cosyne2025?
Join us (w/ @mdiamantaki.bsky.social) for our exciting workshop
Object-centric Neuronal Representations
toliaslab.org/workshop/cos...
Featuring diverse species💁♀️🐒🐁🐝🕷️🤖
Our goal: Discuss universal & species-specific principles of object-centric vision
See you in Montreal🥳
Join us (w/ @mdiamantaki.bsky.social) for our exciting workshop
Object-centric Neuronal Representations
toliaslab.org/workshop/cos...
Featuring diverse species💁♀️🐒🐁🐝🕷️🤖
Our goal: Discuss universal & species-specific principles of object-centric vision
See you in Montreal🥳
Reposted by David Klindt
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!
Reposted by David Klindt
Visa/ green card holders in the US who had planned to go to @cosynemeeting.bsky.social , what are your current thoughts about leaving and reentering the US / has your university issued any new directive? I'm happy to dm/ chat over Signal too. #cosyne25 #neuroskyence
March 22, 2025 at 4:46 PM
Visa/ green card holders in the US who had planned to go to @cosynemeeting.bsky.social , what are your current thoughts about leaving and reentering the US / has your university issued any new directive? I'm happy to dm/ chat over Signal too. #cosyne25 #neuroskyence
Reposted by David Klindt
Applications are open for the summer school 𝗠𝗮𝘁𝗵𝗲𝗺𝗮𝘁𝗶𝗰𝗮𝗹 𝗠𝗲𝘁𝗵𝗼𝗱𝘀 𝗶𝗻 𝗖𝗼𝗺𝗽𝘂𝘁𝗮𝘁𝗶𝗼𝗻𝗮𝗹 𝗡𝗲𝘂𝗿𝗼𝘀𝗰𝗶𝗲𝗻𝗰𝗲.
compneuronrsn.org
Application deadline: March 31, 2025
Located in beautiful Eresfjord, Norway 🇳🇴
#Neuroscience #ComputationalNeuroscience #KavliNeuro
@kavlintnu.bsky.social
compneuronrsn.org
Application deadline: March 31, 2025
Located in beautiful Eresfjord, Norway 🇳🇴
#Neuroscience #ComputationalNeuroscience #KavliNeuro
@kavlintnu.bsky.social
Mathematical Methods in Computational Neuroscience
Summer school in Eresfjord, Norway (July 8th - 26th, 2024)
compneuronrsn.org
March 19, 2025 at 5:06 PM
Applications are open for the summer school 𝗠𝗮𝘁𝗵𝗲𝗺𝗮𝘁𝗶𝗰𝗮𝗹 𝗠𝗲𝘁𝗵𝗼𝗱𝘀 𝗶𝗻 𝗖𝗼𝗺𝗽𝘂𝘁𝗮𝘁𝗶𝗼𝗻𝗮𝗹 𝗡𝗲𝘂𝗿𝗼𝘀𝗰𝗶𝗲𝗻𝗰𝗲.
compneuronrsn.org
Application deadline: March 31, 2025
Located in beautiful Eresfjord, Norway 🇳🇴
#Neuroscience #ComputationalNeuroscience #KavliNeuro
@kavlintnu.bsky.social
compneuronrsn.org
Application deadline: March 31, 2025
Located in beautiful Eresfjord, Norway 🇳🇴
#Neuroscience #ComputationalNeuroscience #KavliNeuro
@kavlintnu.bsky.social