iiinova — where your digital self keeps evolving

Hadi Vafaii @hadivafaii.bsky.social · 16/03/2026

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] 🧵 🧠🤖🧠📈

1235

Hadi Vafaii @hadivafaii.bsky.social · 03/12/2025

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 🧠🤖🧠📈

0111

Hadi Vafaii @hadivafaii.bsky.social · 30/11/2025

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] 🧠🤖🧠📈

neurips.cc

NeurIPS Poster Brain-like Variational InferenceNeurIPS 2025

1184

Reposted by Hadi Vafaii

Mitya @chklovskii.bsky.social · 23/11/2025

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

x.com

021

Hadi Vafaii @hadivafaii.bsky.social · 21/11/2025

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... 🧠🤖🧠📈

youtube.com

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

YouTube video by Sensorimotor AI

1101

Hadi Vafaii @hadivafaii.bsky.social · 19/11/2025

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... 🧠🤖🧠📈

174

Hadi Vafaii @hadivafaii.bsky.social · 10/11/2025

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... 🧠🤖🧠📈

youtube.com

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

YouTube video by Sensorimotor AI

1132

Reposted by Hadi Vafaii

Dan Levenstein @dlevenstein.bsky.social · 21/12/2024

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 😂

Cover of the book “the brain abstracted” by M Chirimuuta

A passage from chapter 1 including the quote

4877

Hadi Vafaii @hadivafaii.bsky.social · 23/10/2025

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... 🧠🤖🧠📈

youtube.com

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

YouTube video by Sensorimotor AI

172

Hadi Vafaii @hadivafaii.bsky.social · 18/10/2025

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-... 🧠🤖🧠📈

youtube.com

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

YouTube video by Sensorimotor AI

1115

Reposted by Hadi Vafaii

Nicole Rust @nicolecrust.bsky.social · 16/10/2025

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

77431

Reposted by Hadi Vafaii

Nicole Rust @nicolecrust.bsky.social · 09/10/2025

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.

2132

Hadi Vafaii @hadivafaii.bsky.social · 03/10/2025

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/ 🧠🤖🧠📈

0142

Hadi Vafaii @hadivafaii.bsky.social · 03/10/2025

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... 🧠🤖🧠📈

youtube.com

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

YouTube video by Sensorimotor AI

1111

Reposted by Hadi Vafaii

Mark Histed @markhisted.org · 25/09/2025

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...

annualreviews.org

Active Filtering: A Predictive Function of Recurrent Circuits of Sensory Cortex | Annual Reviews

Our brains encode many features of the sensory world into memories: We can sing along with songs we have heard before, interpret spoken and written language composed of words we have learned, and reco...

29729

Hadi Vafaii @hadivafaii.bsky.social · 18/09/2025

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!

060

Reposted by Hadi Vafaii

Grace @gracekind.net · 17/09/2025

Very good juxtaposition

051

Hadi Vafaii @hadivafaii.bsky.social · 17/09/2025

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] 🧠🤖🧠📈

23710

Hadi Vafaii @hadivafaii.bsky.social · 05/09/2025

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... 🧠🤖🧠📈

youtube.com

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

YouTube video by Sensorimotor AI

1113

Hadi Vafaii @hadivafaii.bsky.social · 10/08/2025

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] 🧠🤖🧠📈

1225

Hadi Vafaii @hadivafaii.bsky.social · 09/07/2025

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] 🧠🤖🧠📈

12412

Hadi Vafaii @hadivafaii.bsky.social · 30/06/2025

“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]🧵 🧠🤖🧠📈

1245

Hadi Vafaii @hadivafaii.bsky.social · 19/05/2025

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 🧠🤖🧠📈

13713

Hadi Vafaii @hadivafaii.bsky.social · 14/01/2025

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

1152

Reposted by Hadi Vafaii

Ricard Solé @ricardsole.bsky.social · 09/01/2025

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...

1376

Hadi Vafaii @hadivafaii.bsky.social · 18/12/2024

"Probability is the most important concept in modern science, especially as nobody has the slightest notion what it means." —Bertrand Russell, 1929 "Probability does not exist." —Bruno de Finetti, 1974 www.nature.com/articles/d41... 🧠🤖🧠📈

nature.com

Why probability probably doesn’t exist (but it is useful to act like it does)

All of statistics and much of science depends on probability — an astonishing achievement, considering no one’s really sure what it is.

172

Hadi Vafaii @hadivafaii.bsky.social · 13/12/2024

Thank you for capturing this moment. Visa issues can make it difficult, but they won't stop the flow of ideas!

040

Hadi Vafaii @hadivafaii.bsky.social · 11/12/2024

To my Bluesky friends attending #NeurIPS2024: Check out our poster: “Poisson Variational Autoencoder” (P-VAE)! The P-VAE is a #generative model that encodes inputs into spike count variables and unifies major neuroscience theories with modern machine learning. w/ Jacob Yates and Dekel Galor 🧠🤖🧠📈

1303

Hadi Vafaii @hadivafaii.bsky.social · 05/12/2024

I started a blog to write about what I truly care about: the relationship between physics, brains, intelligence, perception, and reality. Here’s my "Hello World" post: mysterioustune.com 🧠🤖🧠📈

1130

Hadi Vafaii @hadivafaii.bsky.social · 02/12/2024

Beautiful thread! I extracted my personal favorites:

010

Reposted by Hadi Vafaii

PessoaBrain @pessoabrain.bsky.social · 07/01/2024

Building on amazing development of simultaneous Ca2+ optical imaging and fMRI-BOLD by Evelyn Lake, Todd Constable and Yale team, we investigated correspondence or lack thereof of large-scale cortical systems by considering overlapping networks. Check thread below. Part of Hadi's tireless PhD work!

02012

Hadi Vafaii @hadivafaii.bsky.social · 06/01/2024

Ever wondered how closely fMRI brain networks reflect a neural underpinning❓ We address this using simultaneous fMRI & widefield Ca²⁺ imaging in mice, and the answer is… complicated! 👉🧵[1/n] Jointly supervised by Evelyn Lake & @pessoabrain.bsky.social www.nature.com/articles/s41...

23312