Taku Ito
@takuito.bsky.social
Computational Neuroscience + AI @ IBM Research | 📍NYC | https://ito-takuya.github.io
Pinned
Taku Ito
@takuito.bsky.social
· Aug 19
What complexity of algorithms can AI compute? In a new paper with colleagues at IBM Research, we explore how circuit complexity theory can help quantify the degree of algorithmic generalization in AI systems. www.nature.com/articles/s42...
@natmachintell.nature.com
#ML #AI #MLSky
1/n
@natmachintell.nature.com
#ML #AI #MLSky
1/n
Reposted by Taku Ito
Did you know that AI can figure out its own way to learn, and that its way is better than one designed by humans? Read more in a @nature.com N&V (and the original paper is in the comment) 🧪 www.nature.com/articles/d41...
AI discovers learning algorithm that outperforms those designed by humans
An artificial-intelligence algorithm that discovers its own way to learn achieves state-of-the-art performance, including on some tasks it had never encountered before.
www.nature.com
October 24, 2025 at 1:18 PM
Did you know that AI can figure out its own way to learn, and that its way is better than one designed by humans? Read more in a @nature.com N&V (and the original paper is in the comment) 🧪 www.nature.com/articles/d41...
Reposted by Taku Ito
Our work with @pawa-pawa.bsky.social is out in Nature Machine Intelligence! The choice of activation function affects the representations, dynamics, and circuit solutions that emerge in RNNs trained on cognitive tasks. Activation matters!
www.nature.com/articles/s42...
www.nature.com/articles/s42...
October 24, 2025 at 7:18 PM
Our work with @pawa-pawa.bsky.social is out in Nature Machine Intelligence! The choice of activation function affects the representations, dynamics, and circuit solutions that emerge in RNNs trained on cognitive tasks. Activation matters!
www.nature.com/articles/s42...
www.nature.com/articles/s42...
Reposted by Taku Ito
(repost welcome) The Generative Model Alignment team at IBM Research is looking for next summer interns! Two candidates for two topics
🍰Reinforcement Learning environments for LLMs
🐎Speculative and non-auto regressive generation for LLMs
interested/curious? DM or email ramon.astudillo@ibm.com
🍰Reinforcement Learning environments for LLMs
🐎Speculative and non-auto regressive generation for LLMs
interested/curious? DM or email ramon.astudillo@ibm.com
October 7, 2025 at 8:19 PM
(repost welcome) The Generative Model Alignment team at IBM Research is looking for next summer interns! Two candidates for two topics
🍰Reinforcement Learning environments for LLMs
🐎Speculative and non-auto regressive generation for LLMs
interested/curious? DM or email ramon.astudillo@ibm.com
🍰Reinforcement Learning environments for LLMs
🐎Speculative and non-auto regressive generation for LLMs
interested/curious? DM or email ramon.astudillo@ibm.com
Reposted by Taku Ito
Michael X Cohen on why he left academia/neuroscience.
mikexcohen.substack.com/p/why-i-left...
mikexcohen.substack.com/p/why-i-left...
Why I left academia and neuroscience
Don't worry, this isn't yet another story of rage-quitting.
mikexcohen.substack.com
October 6, 2025 at 5:05 PM
Michael X Cohen on why he left academia/neuroscience.
mikexcohen.substack.com/p/why-i-left...
mikexcohen.substack.com/p/why-i-left...
Reposted by Taku Ito
Nature research paper: Arousal as a universal embedding for spatiotemporal brain dynamics
go.nature.com/4nMUgYz
go.nature.com/4nMUgYz
Arousal as a universal embedding for spatiotemporal brain dynamics - Nature
Reframing of arousal as a latent dynamical system can reconstruct multidimensional measurements of large-scale spatiotemporal brain dynamics on the timescale of seconds in mice.
go.nature.com
September 26, 2025 at 10:26 AM
Nature research paper: Arousal as a universal embedding for spatiotemporal brain dynamics
go.nature.com/4nMUgYz
go.nature.com/4nMUgYz
Reposted by Taku Ito
Lab’s latest is out in Imaging Neuroscience, led by Kirsten Peterson: “Regularized partial correlation provides reliable functional connectivity estimates while correcting for widespread confounding”, where we demonstrate a major improvement to standard fMRI functional connectivity (correlation) 1/n
September 14, 2025 at 9:34 PM
Lab’s latest is out in Imaging Neuroscience, led by Kirsten Peterson: “Regularized partial correlation provides reliable functional connectivity estimates while correcting for widespread confounding”, where we demonstrate a major improvement to standard fMRI functional connectivity (correlation) 1/n
What complexity of algorithms can AI compute? In a new paper with colleagues at IBM Research, we explore how circuit complexity theory can help quantify the degree of algorithmic generalization in AI systems. www.nature.com/articles/s42...
@natmachintell.nature.com
#ML #AI #MLSky
1/n
@natmachintell.nature.com
#ML #AI #MLSky
1/n
August 19, 2025 at 10:38 PM
What complexity of algorithms can AI compute? In a new paper with colleagues at IBM Research, we explore how circuit complexity theory can help quantify the degree of algorithmic generalization in AI systems. www.nature.com/articles/s42...
@natmachintell.nature.com
#ML #AI #MLSky
1/n
@natmachintell.nature.com
#ML #AI #MLSky
1/n
Reposted by Taku Ito
Mental health research is at a turning point—breakthroughs can transform lives, but only with bold action, investment, and open collaboration. The time for action is now. Read our full statement here: childmind.org/blog/can-sci...
March 7, 2025 at 8:17 PM
Mental health research is at a turning point—breakthroughs can transform lives, but only with bold action, investment, and open collaboration. The time for action is now. Read our full statement here: childmind.org/blog/can-sci...
Reposted by Taku Ito
Out today in Nature Machine Intelligence!
From childhood on, people can create novel, playful, and creative goals. Models have yet to capture this ability. We propose a new way to represent goals and report a model that can generate human-like goals in a playful setting... 1/N
From childhood on, people can create novel, playful, and creative goals. Models have yet to capture this ability. We propose a new way to represent goals and report a model that can generate human-like goals in a playful setting... 1/N
February 21, 2025 at 4:29 PM
Out today in Nature Machine Intelligence!
From childhood on, people can create novel, playful, and creative goals. Models have yet to capture this ability. We propose a new way to represent goals and report a model that can generate human-like goals in a playful setting... 1/N
From childhood on, people can create novel, playful, and creative goals. Models have yet to capture this ability. We propose a new way to represent goals and report a model that can generate human-like goals in a playful setting... 1/N
Reposted by Taku Ito
New preprint! Ziyan and I explore how task order impacts continual learning in neural networks and how to optimize it. Our analysis highlights two key principles for better task sequencing.
Check it out: arxiv.org/pdf/2502.03350
Check it out: arxiv.org/pdf/2502.03350
arxiv.org
February 6, 2025 at 11:14 PM
New preprint! Ziyan and I explore how task order impacts continual learning in neural networks and how to optimize it. Our analysis highlights two key principles for better task sequencing.
Check it out: arxiv.org/pdf/2502.03350
Check it out: arxiv.org/pdf/2502.03350
Reposted by Taku Ito
The entire website for the NIH Office of Research on Women's Health (ORWH) is very nearly stripped bare. This is so, so devastating. orwh.od.nih.gov/research/fun...
orwh.od.nih.gov
January 31, 2025 at 6:25 PM
The entire website for the NIH Office of Research on Women's Health (ORWH) is very nearly stripped bare. This is so, so devastating. orwh.od.nih.gov/research/fun...
Reposted by Taku Ito
New paper out! 🚨 📰 With @batuhanerkat.bsky.social, John McClure, @hussainyk1.bsky.social, @polacklab.bsky.social we reveal how discretized representations in V1 predict suboptimal orientation discrimination. 🧪🧠🐭 This work reconciles neuro and psychometric curves
www.nature.com/articles/s41...
www.nature.com/articles/s41...
Discretized representations in V1 predict suboptimal orientation discrimination - Nature Communications
How animals generate perceptual decisions remains poorly understood. Here, the authors show that during a discrimination task, the mouse visual cortex does not encode the orientations of the cues but ...
www.nature.com
January 8, 2025 at 9:43 PM
New paper out! 🚨 📰 With @batuhanerkat.bsky.social, John McClure, @hussainyk1.bsky.social, @polacklab.bsky.social we reveal how discretized representations in V1 predict suboptimal orientation discrimination. 🧪🧠🐭 This work reconciles neuro and psychometric curves
www.nature.com/articles/s41...
www.nature.com/articles/s41...
Reposted by Taku Ito
New paper in @brain1878.bsky.social: Healthy people under S-ketamine, an NMDAR antagonist, and people living with schizophrenia, a disorder associated with NMDAR hypofunction, spend more time in an external mode of perception - where noisy sensory signals override knowledge about the world.
January 19, 2025 at 9:18 PM
New paper in @brain1878.bsky.social: Healthy people under S-ketamine, an NMDAR antagonist, and people living with schizophrenia, a disorder associated with NMDAR hypofunction, spend more time in an external mode of perception - where noisy sensory signals override knowledge about the world.
Reposted by Taku Ito
The origin of color categories | PNAS www.pnas.org/doi/10.1073/...
The origin of color categories | PNAS
To what extent does concept formation require language? Here, we exploit color to
address this question and ask whether macaque monkeys have color ...
www.pnas.org
January 16, 2025 at 3:59 PM
The origin of color categories | PNAS www.pnas.org/doi/10.1073/...
Reposted by Taku Ito
Check our latest in which we leverage shape metrics to compare neural geometry across regions, sessions or subjects and how their differences predict behavior.
w/ Nejatbakhsh, Duong, @sarah-harvey.bsky.social, Brincat, @siegellab.bsky.social, @earlkmiller.bsky.social & @itsneuronal.bsky.social
w/ Nejatbakhsh, Duong, @sarah-harvey.bsky.social, Brincat, @siegellab.bsky.social, @earlkmiller.bsky.social & @itsneuronal.bsky.social
Quantifying Differences in Neural Population Activity With Shape Metrics https://www.biorxiv.org/content/10.1101/2025.01.10.632411v1
January 12, 2025 at 3:19 PM
Check our latest in which we leverage shape metrics to compare neural geometry across regions, sessions or subjects and how their differences predict behavior.
w/ Nejatbakhsh, Duong, @sarah-harvey.bsky.social, Brincat, @siegellab.bsky.social, @earlkmiller.bsky.social & @itsneuronal.bsky.social
w/ Nejatbakhsh, Duong, @sarah-harvey.bsky.social, Brincat, @siegellab.bsky.social, @earlkmiller.bsky.social & @itsneuronal.bsky.social
Reposted by Taku Ito
Paper shows very small LLMs can match or beat larger ones through 'deep thinking' - evaluating different solution paths - and other tricks. Their 7B model beats o1-preview on complex math by exploring 64 different solutions & picking the best one.
Test-time compute paradigm seems really fruitful.
Test-time compute paradigm seems really fruitful.
January 11, 2025 at 5:34 AM
Paper shows very small LLMs can match or beat larger ones through 'deep thinking' - evaluating different solution paths - and other tricks. Their 7B model beats o1-preview on complex math by exploring 64 different solutions & picking the best one.
Test-time compute paradigm seems really fruitful.
Test-time compute paradigm seems really fruitful.
Reposted by Taku Ito
New results for a new year! “Linking neural population formatting to function” describes our modern take on an old question: how can we understand the contribution of a brain area to behavior?
www.biorxiv.org/content/10.1...
🧠👩🏻🔬🧪🧵
#neuroskyence
1/
www.biorxiv.org/content/10.1...
🧠👩🏻🔬🧪🧵
#neuroskyence
1/
Linking neural population formatting to function
Animals capable of complex behaviors tend to have more distinct brain areas than simpler organisms, and artificial networks that perform many tasks tend to self-organize into modules (1-3). This sugge...
www.biorxiv.org
January 4, 2025 at 4:25 PM
New results for a new year! “Linking neural population formatting to function” describes our modern take on an old question: how can we understand the contribution of a brain area to behavior?
www.biorxiv.org/content/10.1...
🧠👩🏻🔬🧪🧵
#neuroskyence
1/
www.biorxiv.org/content/10.1...
🧠👩🏻🔬🧪🧵
#neuroskyence
1/
Reposted by Taku Ito
And relatedly, Felix wrote a good piece on the stress and anxiety currently affecting many people who work in AI due to the current climate in the industry:
docs.google.com/document/d/1...
If only more folks in AI were gentle and introspective like this...
docs.google.com/document/d/1...
If only more folks in AI were gentle and introspective like this...
AI and Stress
200Bn Weights of Responsibility The Stress of Working in Modern AI Felix Hill, Oct 2024 The field of AI has changed irrevocably in the last 2 years. ChatGPT is approaching 200m monthly users. Gemin...
docs.google.com
January 3, 2025 at 8:05 PM
And relatedly, Felix wrote a good piece on the stress and anxiety currently affecting many people who work in AI due to the current climate in the industry:
docs.google.com/document/d/1...
If only more folks in AI were gentle and introspective like this...
docs.google.com/document/d/1...
If only more folks in AI were gentle and introspective like this...
Reposted by Taku Ito
What was the most important machine learning paper in 2024?
My Famous Deep Learning Papers list (that I use in teaching) does not include any new ideas from the last year.
papers.baulab.info
Which single new paper would you add?
My Famous Deep Learning Papers list (that I use in teaching) does not include any new ideas from the last year.
papers.baulab.info
Which single new paper would you add?
December 31, 2024 at 3:09 PM
What was the most important machine learning paper in 2024?
My Famous Deep Learning Papers list (that I use in teaching) does not include any new ideas from the last year.
papers.baulab.info
Which single new paper would you add?
My Famous Deep Learning Papers list (that I use in teaching) does not include any new ideas from the last year.
papers.baulab.info
Which single new paper would you add?
Reposted by Taku Ito
Reposted by Taku Ito
📌 Poster Session:
⏰ When: TODAY, Thu, Dec 12, 4:30 p.m. – 7:30 p.m. PST
📍 Where: East Exhibit Hall A-C, #3705
📄 What: Geometry of Naturalistic Object Representations in Recurrent Neural Network Models of Working Memory
Hope to see you there!
@bashivan.bsky.social @takuito.bsky.social
⏰ When: TODAY, Thu, Dec 12, 4:30 p.m. – 7:30 p.m. PST
📍 Where: East Exhibit Hall A-C, #3705
📄 What: Geometry of Naturalistic Object Representations in Recurrent Neural Network Models of Working Memory
Hope to see you there!
@bashivan.bsky.social @takuito.bsky.social
December 12, 2024 at 6:03 PM
📌 Poster Session:
⏰ When: TODAY, Thu, Dec 12, 4:30 p.m. – 7:30 p.m. PST
📍 Where: East Exhibit Hall A-C, #3705
📄 What: Geometry of Naturalistic Object Representations in Recurrent Neural Network Models of Working Memory
Hope to see you there!
@bashivan.bsky.social @takuito.bsky.social
⏰ When: TODAY, Thu, Dec 12, 4:30 p.m. – 7:30 p.m. PST
📍 Where: East Exhibit Hall A-C, #3705
📄 What: Geometry of Naturalistic Object Representations in Recurrent Neural Network Models of Working Memory
Hope to see you there!
@bashivan.bsky.social @takuito.bsky.social
Reposted by Taku Ito
🚨We're very excited to share our latest study, by Pablo Diego and team:
"A polar coordinate system represents syntax in large language models",
📄: Paper arxiv.org/abs/2412.05571
🪧: Poster tomorrow: neurips.cc/virtual/2024...
🧵: Thread 👇
"A polar coordinate system represents syntax in large language models",
📄: Paper arxiv.org/abs/2412.05571
🪧: Poster tomorrow: neurips.cc/virtual/2024...
🧵: Thread 👇
December 12, 2024 at 2:25 PM
🚨We're very excited to share our latest study, by Pablo Diego and team:
"A polar coordinate system represents syntax in large language models",
📄: Paper arxiv.org/abs/2412.05571
🪧: Poster tomorrow: neurips.cc/virtual/2024...
🧵: Thread 👇
"A polar coordinate system represents syntax in large language models",
📄: Paper arxiv.org/abs/2412.05571
🪧: Poster tomorrow: neurips.cc/virtual/2024...
🧵: Thread 👇
Reposted by Taku Ito
Just published🔈
"Structurally informed models of directed brain connectivity"
Read: rdcu.be/d3dC4
We review how structural connectivity constrains directed connectivity models 🧠
Lead by @matthewdgreaves.bsky.social w/ @novelli-leo.bsky.social, @sinamansourl.bsky.social and Andrew Zalesky
"Structurally informed models of directed brain connectivity"
Read: rdcu.be/d3dC4
We review how structural connectivity constrains directed connectivity models 🧠
Lead by @matthewdgreaves.bsky.social w/ @novelli-leo.bsky.social, @sinamansourl.bsky.social and Andrew Zalesky
December 11, 2024 at 5:53 PM
Just published🔈
"Structurally informed models of directed brain connectivity"
Read: rdcu.be/d3dC4
We review how structural connectivity constrains directed connectivity models 🧠
Lead by @matthewdgreaves.bsky.social w/ @novelli-leo.bsky.social, @sinamansourl.bsky.social and Andrew Zalesky
"Structurally informed models of directed brain connectivity"
Read: rdcu.be/d3dC4
We review how structural connectivity constrains directed connectivity models 🧠
Lead by @matthewdgreaves.bsky.social w/ @novelli-leo.bsky.social, @sinamansourl.bsky.social and Andrew Zalesky
Reposted by Taku Ito
hey -- i'm hiring a postdoc! the ad will be up shortly, but looking for someone with network neuroscience experience (very broadly). the position isn't tied to any specific project/grant, so lots of flexibility in terms of what you'd actually *do*. hmu if you might be interested/want to learn more!
December 3, 2024 at 3:39 PM
hey -- i'm hiring a postdoc! the ad will be up shortly, but looking for someone with network neuroscience experience (very broadly). the position isn't tied to any specific project/grant, so lots of flexibility in terms of what you'd actually *do*. hmu if you might be interested/want to learn more!
Reposted by Taku Ito
“Cognitive flexibility as the shifting of brain network flows by flexible neural representations”, a solo paper by yours truly, making the case that brain activity flow shifts are essential to mental flexibility (and quite interesting too!)
Open access: www.sciencedirect.com/science/arti...
Open access: www.sciencedirect.com/science/arti...
December 3, 2024 at 6:12 PM
“Cognitive flexibility as the shifting of brain network flows by flexible neural representations”, a solo paper by yours truly, making the case that brain activity flow shifts are essential to mental flexibility (and quite interesting too!)
Open access: www.sciencedirect.com/science/arti...
Open access: www.sciencedirect.com/science/arti...