Hadi Vafaii
@hadivafaii.bsky.social
Postdoc at UC Berkeley, Redwood Center | 🧠🤖 | 🎹 | 🎾 | https://mysterioustune.com/
Pinned
Hadi Vafaii
@hadivafaii.bsky.social
· May 19
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
🧠🤖🧠📈
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
🧠🤖🧠📈
Reposted by Hadi Vafaii
Thanks @hadivafaii.bsky.social for the invitation! x.com/hadivafaii/s...
x.com
November 23, 2025 at 10:36 PM
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...
🧠🤖🧠📈
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
www.youtube.com
November 21, 2025 at 6:06 AM
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...
🧠🤖🧠📈
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...
🧠🤖🧠📈
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...
🧠🤖🧠📈
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
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
A habit and working memory model as an alternative account of human reward-based learning
Nature Human Behaviour - In this study, Collins proposes an alternative dual-process (working memory and habit) model of reinforcement learning in humans.
rdcu.be
November 19, 2025 at 7:28 AM
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...
🧠🤖🧠📈
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...
🧠🤖🧠📈
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...
🧠🤖🧠📈
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
www.youtube.com
November 10, 2025 at 3:37 AM
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...
🧠🤖🧠📈
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...
🧠🤖🧠📈
Reposted by Hadi Vafaii
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 😂
“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 😂
December 21, 2024 at 5:09 PM
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 😂
“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...
🧠🤖🧠📈
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
www.youtube.com
October 23, 2025 at 9:52 PM
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...
🧠🤖🧠📈
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 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-...
🧠🤖🧠📈
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
www.youtube.com
October 18, 2025 at 6:26 AM
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-...
🧠🤖🧠📈
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-...
🧠🤖🧠📈
Reposted by Hadi Vafaii
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
go.bsky.app/2LmKSDN
October 16, 2025 at 4:22 PM
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
go.bsky.app/2LmKSDN
Reposted by Hadi Vafaii
We started our RL debate series!
www.youtube.com/watch?v=E0A0...
www.youtube.com/watch?v=E0A0...
RL Debate Series: Eli "abolish the value function" Sennesh
YouTube video by Sensorimotor AI
www.youtube.com
October 2, 2025 at 10:44 PM
We started our RL debate series!
www.youtube.com/watch?v=E0A0...
www.youtube.com/watch?v=E0A0...
Reposted by Hadi Vafaii
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.
October 8, 2025 at 11:52 PM
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.
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/
🧠🤖🧠📈
- 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/
🧠🤖🧠📈
October 3, 2025 at 6:19 AM
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/
🧠🤖🧠📈
- 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/
🧠🤖🧠📈
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...
🧠🤖🧠📈
Watch @elisennesh.bsky.social abolish the value function:
youtube.com/watch?v=E0A0...
🧠🤖🧠📈
October 2, 2025 at 11:30 PM
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...
🧠🤖🧠📈
Watch @elisennesh.bsky.social abolish the value function:
youtube.com/watch?v=E0A0...
🧠🤖🧠📈
Reposted by Hadi Vafaii
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...
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...
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...
www.annualreviews.org
September 25, 2025 at 7:35 PM
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...
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...
Reposted by Hadi Vafaii
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.
www.thetransmitter.org
September 22, 2025 at 6:40 PM
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...
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!
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!
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
🧠🤖🧠📈
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
🧠🤖🧠📈
September 18, 2025 at 8:31 PM
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!
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!
Reposted by Hadi Vafaii
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]
🧠🤖🧠📈
📢 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]
🧠🤖🧠📈
September 17, 2025 at 4:32 PM
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]
🧠🤖🧠📈
📢 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...
🧠🤖🧠📈
📜 (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
www.youtube.com
September 5, 2025 at 4:10 AM
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...
🧠🤖🧠📈
📜 (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...
🧠🤖🧠📈
Reposted by Hadi Vafaii
Had a great time visiting Berkeley's Redwood Center for Theoretical Neuroscience!
archive.org/details/Redw...
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
August 30, 2025 at 6:49 AM
Had a great time visiting Berkeley's Redwood Center for Theoretical Neuroscience!
archive.org/details/Redw...
archive.org/details/Redw...
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]
🧠🤖🧠📈
(...which, we might as well just call the "AI Club for Non-conformists"👇😎)
📽️ full presentation: youtube.com/watch?v=efc7...
🧵[1/4]
🧠🤖🧠📈
August 10, 2025 at 12:50 AM
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]
🧠🤖🧠📈
(...which, we might as well just call the "AI Club for Non-conformists"👇😎)
📽️ full presentation: youtube.com/watch?v=efc7...
🧵[1/4]
🧠🤖🧠📈
Reposted by Hadi Vafaii
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
www.youtube.com
August 9, 2025 at 6:08 PM
Thanks to @hadivafaii.bsky.social for presenting at our very first Sensorimotor AI Journal Club! www.youtube.com/watch?v=efc7...
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]
🧠🤖🧠📈
w/ Kaylene Stocking, Tommaso Salvatori, and @elisennesh.bsky.social
Sign up link: forms.gle/o5DXD4WMdhTg...
More details below 🧵[1/5]
🧠🤖🧠📈
July 9, 2025 at 10:31 PM
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]
🧠🤖🧠📈
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]🧵
🧠🤖🧠📈
✅ 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]🧵
🧠🤖🧠📈
June 30, 2025 at 5:30 AM
“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]🧵
🧠🤖🧠📈
✅ 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
🧠🤖🧠📈
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
🧠🤖🧠📈
May 19, 2025 at 6:36 AM
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
🧠🤖🧠📈
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
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
January 14, 2025 at 7:53 AM
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
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