A great writeup of our virtual zebrafish agent work by @hadivafaii.bsky.social! sensorimotorai.github.io/2026/04/09/z...

Reece Keller@reecedkeller.bsky.social · last yr.

1/ I'm excited to share recent results from my first collaboration with the amazing @anayebi.bsky.social and @leokoz8.bsky.social ! We show how autonomous behavior and whole-brain dynamics emerge in embodied agents with intrinsic motivation driven by world models.

The "decoupling of information and energy" is a major point of divergence between biological and artificial computers. Energy consumption is the biggest bottleneck in scaling AI. To address this, we need an "energy-aware theory of computation." This work is an attempt to that end. [1/11] 🧵 🧠🤖🧠📈

Enough #Bayesplaining. It's time to start "deriving." We're unifying physics and neuroscience from first principles (yes, really). Come argue with me tomorrow @ 11 AM. @neuripsconf.bsky.social 🧠🤖🧠📈

Hadi Vafaii@hadivafaii.bsky.social · 8mo ago

I will be at @neuripsconf.bsky.social Dec 2-8 to present our "Brain-like Variational Inference" paper 👇 Let's connect if you enjoy first-principles thinking and brain-inspired AI 🧠 🤖 Poster info: 📅 Wed, Dec 3, 11 AM — 2 PM 📍Exhibit Hall C,D,E #500 🔗 neurips.cc/virtual/2025... 🧵[1/4] 🧠🤖🧠📈

I will be at @neuripsconf.bsky.social Dec 2-8 to present our "Brain-like Variational Inference" paper 👇 Let's connect if you enjoy first-principles thinking and brain-inspired AI 🧠 🤖 Poster info: 📅 Wed, Dec 3, 11 AM — 2 PM 📍Exhibit Hall C,D,E #500 🔗 neurips.cc/virtual/2025... 🧵[1/4] 🧠🤖🧠📈

Hadi Vafaii@hadivafaii.bsky.social · last yr.

Elegant theoretical derivations are exclusive to physics. Right?? Wrong! In a new preprint, we: ✅ "Derive" a spiking recurrent network from variational principles ✅ Show it does amazing things like out-of-distribution generalization 👉[1/n]🧵 w/ co-lead Dekel Galor & PI @jcbyts.bsky.social 🧠🤖🧠📈

Thanks @hadivafaii.bsky.social for the invitation! x.com/hadivafaii/s...

Stop treating neurons as passive processors... They are active controllers! 🧠 🎮 In our latest Journal Club session, Thelonious Cooper presented "The neuron as a direct data-driven controller" by Moore et al., with special commentary from Mitya Chklovskii. 🎥 www.youtube.com/watch?v=0P7k... 🧠🤖🧠📈

The neuron as a direct data-driven controller (Moore et al., 2024) — Sensorimotor AI Journal Club

YouTube video by Sensorimotor AI

youtube.com

RL Debates 5: Anne "not everything is RL" Collins Anne delivered an amazing synthesis of her extensive work on how working memory shapes reward-based learning in humans. 📜 Read the paper: nature.com/articles/s41... 📽️ Watch the full presentation: www.youtube.com/watch?v=eEqZ... 🧠🤖🧠📈

My paper is out! Computational modeling of error patterns during reward-based learning show evidence that habit learning (value free!) supplements working memory in 7 human data sets. rdcu.be/eQjLN

RL Debates 4: Adam "I literally measured value in the brain" Lowet Adam's talk covered a lot of ground — from his recent work on distributional RL (nature.com/articles/s41...) to a broader discussion of RL & the brain. 📽️ Watch the full meeting here: www.youtube.com/watch?v=Xe7B... 🧠🤖🧠📈

RL Debates 4: Adam "I literally measured value in the brain" Lowet

YouTube video by Sensorimotor AI

youtube.com

Picked this one up for reading over the holidays. “The thesis of this book is that the dominant ideas that have shaped #neuroscience are best understood as attempts to simplify the brain.” 🧠 …which is itself a simplification 😂

RL Debates 3: Niels "you have 1000 brains in your brain" Leadholm See how Monty (a cortex-inspired model), crushes powerful ViTs in out-of-distribution & continual learning tasks—all while being millions of times more efficient in data & FLOPs! 📽️ Watch here: www.youtube.com/watch?v=Q0FF... 🧠🤖🧠📈

RL Debates 3: Niels "you have 1000 brains in your brain" Leadholm

YouTube video by Sensorimotor AI

youtube.com

RL Debates 2: Fritz "learning for the sake of learning" Sommer Fritz introduced an information-theoretic, first-principles approach to modeling exploration through the maximization of "predicted information gain." 📽️ Watch the full presentation here: www.youtube.com/watch?v=rlF-... 🧠🤖🧠📈

RL Debates 2: Fritz "learning for the sake of learning" Sommer

YouTube video by Sensorimotor AI

youtube.com

A new user influx - welcome! A great nudge to pass this around. (Psst: Scientist authors tend to have fascinating Bsky feeds). go.bsky.app/2LmKSDN

We started our RL debate series! www.youtube.com/watch?v=E0A0...

RL Debate Series: Eli "abolish the value function" Sennesh

YouTube video by Sensorimotor AI

youtube.com

Wonderful to see this high-level conversation about reinforcement learning happen not just “at the top” but across many professional levels (including trainees). 👏👏👏 to everyone involved. Such a thoughtful way to expedite progress. I look forward to following along.

Eli Sennesh@elisennesh.bsky.social · 10mo ago

We started our RL debate series! www.youtube.com/watch?v=E0A0...

I'm excited to announce that we've added two more contenders to the RL Debate Series! - Anne Collins (Professor @ucberkeleyofficial.bsky.social) - Niels Leadholm (Research Manager @thousandbrains.org) Things are heating up!! See the flyer for details👇 🌎 sensorimotorai.github.io/debates/ 🧠🤖🧠📈

Hadi Vafaii@hadivafaii.bsky.social · 11mo ago

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] 🧠🤖🧠📈

The first meeting of the 'RL Debate Series' is now on YouTube! Watch @elisennesh.bsky.social abolish the value function: youtube.com/watch?v=E0A0... 🧠🤖🧠📈

RL Debate Series: Eli "abolish the value function" Sennesh

YouTube video by Sensorimotor AI

youtube.com

Hadi Vafaii@hadivafaii.bsky.social · 11mo ago

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] 🧠🤖🧠📈

The brain is incredibly densely connected. Human cerebral cortex may have as many as *one trillion* connections. Most of those cortical connections are recurrent, inside each area. What do they do? New paper from me in Annual Reviews: 🧪 🧠📈 1/ www.annualreviews.org/content/jour...

Thanks to @pessoabrain.bsky.social and @thetransmitter.bsky.social for featuring our paper and to @aliyarumana.bsky.social and Peter Tse for engaging so generously with the ideas! 😊 www.thetransmitter.org/the-big-pict...

Beyond Newtonian causation in neuroscience

The traditional mechanistic framework must give way to a richer understanding of how brains actually generate behavior over time.

thetransmitter.org

Now accepted to #NeurIPS2025 - see y'all in sunny San Diego ☀️ Also, big thanks to our reviewers. Their deep reading of the paper and thoughtful feedback really helped sharpen our contributions. Stay tuned for a much-enhanced final version in a couple weeks!

Hadi Vafaii@hadivafaii.bsky.social · last yr.

Elegant theoretical derivations are exclusive to physics. Right?? Wrong! In a new preprint, we: ✅ "Derive" a spiking recurrent network from variational principles ✅ Show it does amazing things like out-of-distribution generalization 👉[1/n]🧵 w/ co-lead Dekel Galor & PI @jcbyts.bsky.social 🧠🤖🧠📈

Very good juxtaposition

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] 🧠🤖🧠📈

In the second meeting of 'Sensorimotor AI Journal Club' we covered: 📜 (B)ayesian (O)nline learning in (N)on-stationary (E)nvironments (BONE; openreview.net/forum?id=ose...) Many thanks to the first author Gerardo for an amazing presentation! 🎥 watch it here: www.youtube.com/watch?v=49PP... 🧠🤖🧠📈

Bayesian online learning in non-stationary environments (BONE) by Duran-Martin et al., 2025

YouTube video by Sensorimotor AI

youtube.com

Had a great time visiting Berkeley's Redwood Center for Theoretical Neuroscience! archive.org/details/Redw...

Eli Sennesh: Oscillations, but not Spike Rates, Encode Predictive Processing : Free Download, Borrow, and Streaming : Internet Archive

Talk by Eli Sennesh of Vanderbilt University.  Given to the Redwood Center for Theoretical Neuroscience at UC Berkeley.Abstract: The appearance at the...

archive.org

Our first 'Sensorimotor AI Journal Club' meeting was a blast! (...which, we might as well just call the "AI Club for Non-conformists"👇😎) 📽️ full presentation: youtube.com/watch?v=efc7... 🧵[1/4] 🧠🤖🧠📈

Thanks to @hadivafaii.bsky.social for presenting at our very first Sensorimotor AI Journal Club! www.youtube.com/watch?v=efc7...

Bayesian Online Natural Gradient (BONG) by Jones et al., 2024 — Sensorimotor AI Journal Club

YouTube video by Sensorimotor AI

youtube.com

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] 🧠🤖🧠📈

“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]🧵 🧠🤖🧠📈

Elegant theoretical derivations are exclusive to physics. Right?? Wrong! In a new preprint, we: ✅ "Derive" a spiking recurrent network from variational principles ✅ Show it does amazing things like out-of-distribution generalization 👉[1/n]🧵 w/ co-lead Dekel Galor & PI @jcbyts.bsky.social 🧠🤖🧠📈

Every living system must adapt, or die. In my first blog post, I show how this fundamental principle can be mathematized: ✅ Brains adapt, and adaptation is about KL divergence minimization. Let's unpack the main insights 🧵[1/n] Link: mysterioustune.com/2025/01/13/w... 🧠🤖🧠📈 #AI

Is there an arrow of time in the brain? Can Boltzmann and Shannon's ideas be used to understand it? Check this paper by Morten Kringelbach, J Perl and Gustavo Deco on how physics and information theory reveal how hierarchical cognition works cell.com/trends/cogni...