On negative social ties.
The number of "hasslers" in your lifeโpeople who create problems or make life difficult, especially family members (not spouse)โand the link to promoting accelerated aging, inflammation, and adverse health outcomes
@pnas.org
pnas.org/doi/full/10....
๐ค๐ NEW in the Deeper Learning blog: @annhuang42.bsky.social & @kanakarajanphd.bsky.social break down their recent work examining how #RNNs solve the same task in different ways, and why that matters. Joint work with @satpreetsingh.bsky.social & @flavioh.bsky.social bit.ly/4kj4fVd #NeuroAI
03.02.2026 15:01 โ ๐ 26 ๐ 6 ๐ฌ 0 ๐ 1
What if you could train agents on a ๐ฑ๐ฒ๐ฐ๐ฎ๐ฑ๐ฒ of driving experience in ๐๐ป๐ฑ๐ฒ๐ฟ ๐ฎ๐ป ๐ต๐ผ๐๐ฟ, on a single GPU?
Excited to share ๐๐ช๐๐๐๐ง๐ฟ๐ง๐๐ซ๐ 2.0: A fast, friendly driving simulator with RL training via PufferLib at ๐ฏ๐ฌ๐ฌ๐ ๐๐๐ฒ๐ฝ๐/๐๐ฒ๐ฐ ๐ก + ๐
youtu.be/LfQ324R-cbE?...
Just published my review of neuroscience in 2025, on The Spike.
The 10th of these, would you believe?
This year we have foundation models, breakthroughs in using light to understand the brain, a gene therapy, and more
Enjoy!
medium.com/the-spike/20...
Congratulations!!
07.12.2025 05:55 โ ๐ 2 ๐ 0 ๐ฌ 0 ๐ 0
Thrilled to start 2026 as faculty in Psych & CS
@ualberta.bsky.social + Amii.ca Fellow! ๐ฅณ Recruiting students to develop theories of cognition in natural & artificial systems ๐ค๐ญ๐ง . Find me at #NeurIPS2025 workshops (speaking coginterp.github.io/neurips2025 & organising @dataonbrainmind.bsky.social)
#NeurIPS2025 workshops are underway!
Todayโs workshop presentations from the #KempnerInstitute cover a range topics, including the use of #AI in linguistics and the study of communication & sensing in electric fish.
#NeuroAI
Different seeds with same training loss doesn't always mean same solution. When do neural nets converge vs diverge? What are the implications for inverse problems, #AI4Science & #MechInterp?
#NeurIPS2025 poster 2001 (โa space odysseyโ), 4:30โ7:30pm today 12/5:
Mid-conference momentum! ๐ฌ๐
Todayโs #NeurIPS2025 presentations from the #KempnerInstitute showcase a wide variety of research projects at the frontiers of #AI and #NeuroAI.
@thomasfel.bsky.social @andykeller.bsky.social @gershbrain.bsky.social @yilundu.bsky.social @kanakarajanphd.bsky.social
Conference poster schedule
Workshop poster schedule
Celebrating the Rajan Labโs papers at #NeurIPS2025! Stop by to chat with these talented students and postdocs ๐
04.12.2025 16:08 โ ๐ 16 ๐ 3 ๐ฌ 0 ๐ 0
33 neuroscience researchers from across the world shared how their labs our funded, providing insight into the current state of funding and how that might shift.
By @claudia-lopez.bsky.social
#neuroskyence #StateOfNeuroscience
www.thetransmitter.org/funding/whic...
How do brain areas control each other? ๐ง ๐๏ธ
โจIn our NeurIPS 2025 Spotlight paper, we introduce a data-driven framework to answer this question using deep learning, nonlinear control, and differential geometry.๐งตโฌ๏ธ
We do in a recent follow-up:
bsky.app/profile/neur...
Looking forward to sharing our work at #NeurIPS2025 next week!
Session 6 on Fri 12/5 at 4:30-7:30pm, Poster 2001 ("a space odyssey")
Details on this thread by the brilliant lead author @annhuang42.bsky.social below:
Controversial take: our ICLR reviews actually helped make our paper better
19.11.2025 18:29 โ ๐ 7 ๐ 1 ๐ฌ 2 ๐ 0
Our next paper on comparing dynamical systems (with special interest to artificial and biological neural networks) is out!! Joint work with @annhuang42.bsky.social , as well as @satpreetsingh.bsky.social , @leokoz8.bsky.social , Ila Fiete, and @kanakarajanphd.bsky.social : arxiv.org/pdf/2510.25943
10.11.2025 16:16 โ ๐ 70 ๐ 24 ๐ฌ 4 ๐ 5
new paper with @robertchisciure.bsky.social
link.springer.com/article/10.1...
"Cognition all the way down 2.0: neuroscience beyond neurons in the diverse intelligence era"
๐งช
Excited to release our new work: Petri Dish Neural Cellular Automata!
pub.sakana.ai/pdnca
We investigate how multi-agent NCAs can develop into artificial life ๐ฆ exhibiting complex, emergent behaviors like cyclic dynamics, territorial defense, and spontaneous cooperation.
In case you don't know already, the journal Open Mind has a Bluesky account that automatically posts new papers:
@openmindjournal.bsky.social
The journal is diamond open access (free to read, free to publish) thanks to the support of MIT Press, Harvard Library, & MIT Library.
Congratulations!! ๐๐
01.10.2025 12:48 โ ๐ 5 ๐ 0 ๐ฌ 0 ๐ 0
Excited to announce that my first postdoc paper is now online!
Links:
www.nature.com/articles/s41...
rdcu.be/eAcN7
In it, we examine the perennial question: what changes in the brain when learning a new motor skill?
Read more below to find out ๐
Excited to share a new project spanning cognitive science and AI where we develop a novel deep reinforcement learning model---Multitask Preplay---that explains how people generalize to new tasks that were previously accessible but unpursued.
12.07.2025 16:19 โ ๐ 45 ๐ 9 ๐ฌ 2 ๐ 1
For the past 3 years, I've taught a course on Machine Learning for Climate Change to undergrads. At times, people have asked if the course lectures could be made available online. While I can't offer that, I have decided to start making "5 Minute Papers on AI for the Planet" videos. Hope its useful!
20.06.2025 01:55 โ ๐ 203 ๐ 54 ๐ฌ 10 ๐ 2
Might be a bit outside your time-range, but these reviews are key refs:
arxiv.org/abs/2210.05050
www.nowpublishers.com/article/Deta...
CC: @swarat.bsky.social @yisongyue.bsky.social
If you're at #RLDM2025, check out our contributed talk at Session 3 (Fri 6/13, 12:10pm), presented by my brilliant co-first-author on this project @sjohnsonyu.bsky.social!
Wasn't able to make it in person, but would love to hear your thoughts
@kempnerinstitute.bsky.social @harvardmed.bsky.social
Check out our new work on making robots process touch more like brains!
Surprisingly, ConvRNNs best matched mouse cortexโpassing the NeuroAI Turing Test. We also developed tactile-specific SSL augmentations and an Encoder-Attender-Decoder framework unifying ConvRNNs, SSMs & Transformers.
It was an honor to speak at the
@kempnerinstitute.bsky.social
on how some of our recent works can be interpreted as an application of rational analysis to language model behaviors โ seeing both their successes and failures through the lens of adaptation to the properties of their training data.
After using electrical stimulation to activate their muscles, patients improved movement in their paralyzed limbs even when the system was turned off. The team leading the clinical trial believes new nerve connections may have begun to grow. https://cbsn.ws/43ocCrA
11.05.2025 23:33 โ ๐ 254 ๐ 49 ๐ฌ 5 ๐ 8
Big day for the Rajan lab at @harvardmed.bsky.social Friday Seminar Series ๐
@satpreetsingh.bsky.social & Siyan Zhou gave outstanding talks on collective behaviors in artificial fish schools & disordered attractors in mice. Iโm so proud of their work! ๐ค๐ง
Aran Nayebi (@anayebi.bsky.social): Why NeuroAI Needs NeuroAgents
www.youtube.com/watch?v=s3kl...
