Scholar
LightNews

Taku Ito

Videos
H-index: 25
Neuroscience 41%
Engineering 35%
more

Reposted by Taku Ito, Larry W. Hunter

ramon-astudillo.bsky.social
(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 [email protected]
1 13 19

Reposted by Taku Ito

pessoabrain.bsky.social
Michael X Cohen on why he left academia/neuroscience.
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
6 34 92

Reposted by Taku Ito

nature.com
Nature research paper: Arousal as a universal embedding for spatiotemporal brain dynamics

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
12 29

Reposted by Taku Ito, Alessandro Gozzi

mwcole.bsky.social
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
5 30 74

by Taku Ito

takuito.bsky.social
Formalizing AI computation in terms of algorithmic complexity can offer a formal way to quantify AI systems while offering a principled foundation to build more algorithmically capable systems in the future.
Blog: research.ibm.com/blog/ai-algo...
arXiv: arxiv.org/abs/2411.05943
Can AI generate truly novel algorithms?
A decades-old approach to measuring algorithmic complexity could provide a window into better understanding how AI systems compute.
research.ibm.com

by Taku Ito

takuito.bsky.social
While using AI models to generate code is commonplace these days, we still do not fully understand the limits of the complexity of the code these models can formulate.
3/n
1

by Taku Ito

takuito.bsky.social
Using circuits to formalize algorithmic problems for AI models (e.g., depth as time complexity, size as space complexity), we can quantify the complexity of circuit computations (algorithmic complexity) an AI model can perform.
2/n
1

by Taku Ito

takuito.bsky.social
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
1 5 16

Reposted by Taku Ito

milhammichael.bsky.social
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...
7 15

Reposted by Taku Ito, Todd M. Gureckis

guydav.bsky.social
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
5 40 140

Reposted by Taku Ito

nhiratani.bsky.social
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
arxiv.org
3 7

Reposted by Taku Ito, Sarah Mitchell

docbecca.bsky.social
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
44 620 980

Reposted by Taku Ito

veithweilnhammer.bsky.social
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.
1 8 26

Reposted by Taku Ito

jsaito25.bsky.social
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
2 13 53

Reposted by Taku Ito

biorxiv-neursci.bsky.social
Quantifying Differences in Neural Population Activity With Shape Metrics https://www.biorxiv.org/content/10.1101/2025.01.10.632411v1
3 12

Reposted by Taku Ito

emollick.bsky.social
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.
3 20 160

Reposted by Taku Ito

juliencorbo.bsky.social
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...
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
3 8 26

Reposted by Taku Ito

marlenecohen.bsky.social
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/
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
2 81 230

Reposted by Taku Ito

tyrellturing.bsky.social
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...
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
5 17

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?
10 12 55

Reposted by Taku Ito, Arvind Narayanan, Sendhil Mullainathan , and 1 more

melaniemitchell.bsky.social
Some of my thoughts on OpenAI's o3 and the ARC-AGI benchmark

aiguide.substack.com/p/did-openai...
Did OpenAI Just Solve Abstract Reasoning?
OpenAI’s o3 model aces the "Abstraction and Reasoning Corpus" — but what does it mean?
aiguide.substack.com
17 99 340

Reposted by Taku Ito

xiaoxuanlei.bsky.social
📌 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
1 3

Reposted by Taku Ito, Stanislas Dehaene, Francisco C. Pereira

jeanremiking.bsky.social
🚨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 👇
2 17 58

Reposted by Taku Ito

adeelrazi.bsky.social
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
1 14 37

Reposted by Taku Ito

mwcole.bsky.social
“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...
2 26 100

Reposted by Taku Ito, Drew B. Winters, Dara M. Cannon

richardfbetzel.bsky.social
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!
1 49 52

by Taku Ito

takuito.bsky.social
Our new NeurIPS paper on naturalistic representations in dynamic WM models, led by @xiaoxuanlei.bsky.social and @bashivan.bsky.social
Thread by Xiaoxuan 👇
xiaoxuanlei.bsky.social
Xiaoxuan @xiaoxuanlei.bsky.social · Nov 28
🌟 New Research Alert! 🌟
Excited to share our latest work (accepted to NeurIPS2024) on understanding working memory in multi-task RNN models using naturalistic stimuli!: with @takuito.bsky.social and @bashivan.bsky.social
#tweeprint below:
1 3 7

Reposted by Taku Ito

xiaoxuanlei.bsky.social
🌟 New Research Alert! 🌟
Excited to share our latest work (accepted to NeurIPS2024) on understanding working memory in multi-task RNN models using naturalistic stimuli!: with @takuito.bsky.social and @bashivan.bsky.social
#tweeprint below:
3 17 50

Reposted by Taku Ito

claeneuro.bsky.social
JAMA Psychiatry

A Dynamical Systems View of Psychiatric Disorders—Theory
A Review

jamanetwork.com/journals/jam...
A Dynamical Systems View of Psychiatric Disorders—Theory
This narrative review describes a new approach to the diagnosis and treatment of psychiatric disorders that is based on dynamical systems theory, which addresses the concepts of tipping points, cycles...
jamanetwork.com
3 10 28

Reposted by Taku Ito

mwcole.bsky.social
Lab’s latest at PLOS Comp Biol, led by Carrisa Cocuzza: “Distributed network flows generate localized category selectivity in human visual cortex”. This one changed how I think the brain works! Even "localized" functions are likely generated by distributed processes doi.org/10.1371/jour...
Distributed network flows generate localized category selectivity in human visual cortex
Author summary A fundamental question in neuroscience has persisted for over a century: to what extent do distributed processes drive brain function? The existence of category-selective regions within...
doi.org
11 17

References

Fields & subjects

Updated 1m