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
🧠🤖🧠📈
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
Reposted by Hadi Vafaii
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...
January 9, 2025 at 9:27 PM
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...
"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...
🧠🤖🧠📈
"Probability does not exist." —Bruno de Finetti, 1974
www.nature.com/articles/d41...
🧠🤖🧠📈
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.
www.nature.com
December 18, 2024 at 5:34 PM
"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...
🧠🤖🧠📈
"Probability does not exist." —Bruno de Finetti, 1974
www.nature.com/articles/d41...
🧠🤖🧠📈
Thank you for capturing this moment.
Visa issues can make it difficult, but they won't stop the flow of ideas!
Visa issues can make it difficult, but they won't stop the flow of ideas!
It is sad to see authors not being able to present their work at #NeurIPS2024 because of visa issues.
But some authors went above and beyond.
Here is @hadivafaii.bsky.social tele-presenting his work with an impressive setup (ipad, mic, speaker, holder, battery).
Well done sir!
But some authors went above and beyond.
Here is @hadivafaii.bsky.social tele-presenting his work with an impressive setup (ipad, mic, speaker, holder, battery).
Well done sir!
December 13, 2024 at 5:41 PM
Thank you for capturing this moment.
Visa issues can make it difficult, but they won't stop the flow of ideas!
Visa issues can make it difficult, but they won't stop the flow of ideas!