I’m super excited to finally put my recent work with @behrenstimb.bsky.social on bioRxiv, where we develop a new mechanistic theory of how PFC structures adaptive behaviour using attractor dynamics in space and time! www.biorxiv.org/content/10.1...

Exciting news! 🎉 Our Computational Neuroscience course has been awarded NIH BRAIN Initiative funding! Students will get hands-on experience w real BRAIN Initiative datasets, helping them build computational skills that are essential for the future of neuroscience. www.linkedin.com/feed/update/...

“Perception as Inference” is a century-old idea that has inspired all major theories in neuroscience 🧠, including: ✅ Sparse Coding ✅ Predictive Coding ✅ Free Energy Principle & more! In my new blog post, I build the intuition behind this idea from ground up 👉[1/6]🧵 🧠🤖🧠📈

Google Glass walked so Meta Ray Ban Glasses could also walk

What drives behavior in living organisms? And how can we design artificial agents that learn interactively? 📢 To address these, the Sensorimotor AI Journal Club is launching the "RL Debate Series"👇 w/ @elisennesh.bsky.social, @noreward4u.bsky.social, @tommasosalvatori.bsky.social 🧵[1/5] 🧠🤖🧠📈

An overview of @logseq DB Task Management youtu.be/ITCcMFNSSmw?... with the new Schema and improved UX #logseq #TaskManagement #pkm #Productivity

It is almost time to welcome you all in Santa Cruz! 🦕 We will start with an exciting and timely keynote by @guyvdb.bsky.social on "Symbolic Reasoning in the Age of Large Language Models" 👀 📆 Full conference schedule: 2025.nesyconf.org/schedule/

Is anarchist science possible? As an experiment, we got together a large group of computational neuroscientists from around the world to work on a single project without top down direction. Read on to find out what happened. 🤖🧠🧪

Looking for more engagement on Bluesky? I've compiled tips with t he help of others in the community: publish.obsidian.md/debbieohi/bl... #BlueSkyTips

1/ What if we make robots that process touch the way our brains do? We found that Convolutional Recurrent Neural Networks (ConvRNNs) pass the NeuroAI Turing Test in currently available mouse somatosensory cortex data. New paper by @Yuchen @Nathan @anayebi.bsky.social and me!

Introducing Bases, a new core plugin that lets you turn any set of notes into a powerful database. Now available to everyone with Obsidian 1.9!

Join us on a (mathematical) journey to a shire - oops, HIGHER - standard and principled evaluation schema for our benchmark datasets. This is the reward of the RINGS framework. 📒 Blog: aidos.group/blog/rings/ 📃 Paper: doi.org/10.48550/arX... 👩‍💻 Code: github.com/aidos-lab/ri...

1/3) This may be a very important paper, it suggests that there are no prediction error encoding neurons in sensory areas of cortex: www.biorxiv.org/content/10.1... I personally am a big fan of the idea that cortical regions (allo and neo) are doing sequence prediction. But... 🧠📈 🧪

1/ 🚨Another New Paper Drop! 🚨 “Hierarchy or Heterarchy? A Theory of Long-Range Connections for the Sensorimotor Brain” 👇 Dive into the full thread 🧵 arxiv.org/abs/2507.05888

🔥 Want to understand how the neocortex builds intelligence? Artem Kirsanov made a great video on the Thousand Brains Theory, the foundation of everything we’re building at here Thousand Brains Project! 🎥 youtu.be/Dykkubb-Qus #Neuroscience #AI #ThousandBrains #Neocortex

Hello world! This is the RL & Agents Reading Group We organise regular meetings to discuss recent papers in Reinforcement Learning (RL), Multi-Agent RL and related areas (open-ended learning, LLM agents, robotics, etc). Meetings take place online and are open to everyone 😊

Announcing the new "Sensorimotor AI" Journal Club — please share/repost! w/ Kaylene Stocking, Tommaso Salvatori, and @elisennesh.bsky.social Sign up link: forms.gle/o5DXD4WMdhTg... More details below 🧵[1/5] 🧠🤖🧠📈

Super excited to share our new paper! We spent the past years building an alternative AI approach, and now we demonstrate a whole range of advantages. Robust object & pose detection, generalization, data and compute efficient training, continual learning, shape bias, intelligent policies, and more!🦾

Nice paper arxiv.org/abs/2506.01622

Together with @repromancer.bsky.social, I have been musing for a while that the exponentiated gradient algorithm we've advocated for comp neuro would work well with low-precision ANNs. This group got it working! arxiv.org/abs/2506.17768 May be a great way to reduce AI energy use!!! #MLSky 🧪

New paper dropped! “Hierarchy or Heterarchy? A Theory of Long-Range Connections for the Sensorimotor Brain” The Thousand Brains Theory explains the cortex’s non-hierarchical connections, and why they matter for building machine intelligence. Read it now: arxiv.org/abs/2507.05888

1/ This week, we’re releasing two milestone papers: one shows the amazing capabilities of thousand-brains systems and their benefits over deep learning, the other proposes a new theory of long-range connections in the neocortex. Years of work led to this.

Such a timely find. I was just about to find some source to delve into the field HRL. I think this could be a good starting point.

🚨 Excited to share our new work: "Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning"! 📈 We propose gradient interventions that enable stable, scalable learning, unlocking significant performance gains across agents and environments! Details below 👇

Introducing Reinforcement-Learned Teachers (RLTs): Transforming how we teach LLMs to reason with reinforcement learning (RL). Blog: sakana.ai/rlt Paper: arxiv.org/abs/2506.08388 Code: github.com/SakanaAI/RLT We introduce a new way to teach LLMs how to reason by learning to teach, not solve.

Big week for astrocyte research: 3 new Science papers link astrocytes to behavior. We're excited to add to the momentum with our new PNAS paper: a theory, grounded in biology, proposing astrocytes as key players in memory storage and recall. w/ JJ Slotine and @krotov.bsky.social (1/6)

Thrilled to share the new paper from the lab out today in @nathumbehav.nature.com, led by the great @jetrach.bsky.social! "Mental graphs structure the storage and retrieval of visuomotor associations" www.nature.com/articles/s41...

New preprint, w/ @predictivebrain.bsky.social ! we've found that visual cortex, even when just viewing natural scenes, predicts *higher-level* visual features The aligns with developments in ML, but challenges some assumptions about early sensory cortex www.biorxiv.org/content/10.1...

Out now in TiCS, something i've been thinking about a lot: "Physics vs. graphics as an organizing dichotomy in cognition" (by Balaban & me) relevant for many people, related to imagination, intuitive physics, mental simulation, aphantasia, and more authors.elsevier.com/a/1lBaC4sIRv...

We just pushed “Memory by a 1000 rules” onto bioRxiv, where we use clever #ML to find #plasticity quadruplets (EE, EI, IE, II) that learn basic stability in spiking nets. Why is it cool? We find 1000s!! of solutions, and they don’t just stabilise. They #memorise! www.biorxiv.org/content/10.1...

Following our Sudoku-based reasoning benchmark announcement, we've been evaluating the latest models to track improvements in their reasoning capabilities. Today, we’re launching the Sudoku-Bench Leaderboard: pub.sakana.ai/sudoku/ New technical report: arxiv.org/abs/2505.16135

🧵Training binary or spiking neural networks is hard. Gradients vanish, surrogates are noisy, batchnorm is brittle. We propose a Bayesian approach based on KL divergence minimization—and it works. Paper: arxiv.org/abs/2505.17962 Work by James Walker & Moein Khajehnejad @neuro-ai.bsky.social 1/6

1/6 Why does the brain maintain such precise excitatory-inhibitory balance? Our new preprint explores a provocative idea: Small, targeted deviations from this balance may serve a purpose: to encode local error signals for learning. www.biorxiv.org/content/10.1... led by @jrbch.bsky.social

New #NeuroAI #compneurosky preprint! To better understand how target-directed learning works in the brain, we sought to engineer an artificial neural network capable of solving complex image classification tasks that comprises only experimentally-supported biological building blocks. (1/15)

More and more exciting papers to sift through each day

Sometimes I do science for the prestige. Sometimes I do science for the money. And sometimes I do science for the pretty pictures. Preprint at arxiv.org/abs/2505.07308 Explanations in thread ⬇️

New Paper: Continuous Thought Machines pub.sakana.ai/ctm/ Neurons in brains use timing and synchronization in the way that they compute, but this is largely ignored in modern neural nets. We believe neural timing is key for the flexibility and adaptability of biological intelligence. Thread ↓

Excited to go through this paper

I think we're overdue for a rollup of the best papers of the past year in NeuroAI. Candidates?

Announcing AlphaEvolve, our new LLM coding agent that has - made new scientific discoveries - discovered algorithms that are now deployed at Google (in Gemini, Transformers, TPU hardware design & data centers) Blog: deepmind.google/discover/blo... White paper: storage.googleapis.com/deepmind-med...

[Past weekends side project] A quick introduction to contextual speech models I made some interactive visualisations to explain a bit better how recent contextual speech models and audio tokenization work (e.g. Sesame's demo).

If you have not read the story of how Neuromatch came to be, it really is inspiring. We have so many incredible founders and contributors to thank. ❤️ Can't believe it's been five years!

🚨 New video drop! 🚨 @tristanls.bsky.social talks about our bold new sensorimotor paradigm for AI at the Austin Robotics & AI Meetup 🤖🧠 Learn how the Thousand Brains Project is reverse-engineering the neocortex to revolutionize intelligent systems. Watch now: www.youtube.com/watch?v=8IOX...

In studying the brain, we almost always take the neuron’s perspective. But we can gain new insights by reorienting our frame of reference to that of the messages flowing over brain networks, writes @danieljgraham.bsky.social #neuroskyence www.thetransmitter.org/neural-codin...

Can we understand the mechanisms of a frontier AI model? 📝 Blog post: www.anthropic.com/research/tra... 🧪 "Biology" paper: transformer-circuits.pub/2025/attribu... ⚙️ Methods paper: transformer-circuits.pub/2025/attribu... Featuring basic multi-step reasoning, planning, introspection and more!

Unidentified men grabbing someone off the street and putting her in a car because she wrote an op-Ed. This as flatly authoritarian as anything we’ve seen in this country in a very long time.

Jeff, @vivianeclay.bsky.social , @cortical-canonical.bsky.social , and Ramy revisit key ideas from the retreat - diving into reference frames, minicolumns, and models. Watch now: youtu.be/GU4y-CylCLc

After 6+ months in the making and over a year of GPU compute, we're excited to release the "Ultra-Scale Playbook": hf.co/spaces/nanot... A book to learn all about 5D parallelism, ZeRO, CUDA kernels, how/why overlap compute & coms with theory, motivation, interactive plots and 4000+ experiments!

After all this time, I still feel like the initial YouTube time-stamped note taking functionality in #Logseq was way better than anything else. I've tried setting up plugins in @obsidian.md , but there's always some bug or it's not as seamless 🥲 Thinking about moving back to #Logseq