Cosyne Viewing Parties
Visas, costs, care responsibilities, and environmental concerns all limit Cosyne attendance. Luckily, the talks are livestreamed; but watching alone is the high road to an aneurism. Hence: viewing parties! Gather regionally to watch Cosyne talks! More info: shorturl.at/3DHZX.
So happy to see this out, congrats Mohammad!!
In this piece for @thetransmitter.bsky.social, I argue that ecological neuroscience should leverage generative video and interactive models to simulate the world from animals' perspectives.
The technological building blocks are almost here - we just need to align them for this application.
🧠🤖
We are excited to announce that the Cognitive Computational Neuroscience meeting (CCN 2026) will be held at New York University from August 3–6, 2026.
2026.ccneuro.org
Great piece by @natolambert.bsky.social on the current state of human exhaustion in the AI world. Makes this important point:
Happy birthday!!
This work has been accepted to #COLM2025. If you are in Montreal this week for COLM and would like to chat about this (or anything related to discovery / exploration / RL), drop me a note!
Poster session 2: Tuesday Oct 7, 4:30-6:30pm
Poster number 68
Nice write-up on the top-performing models of Algonauts 2025 competition by @humanscotti.bsky.social
paulscotti.substack.com/p/insights-f...
None of the teams trained the models from scratch, mainly relied on pre-trained foundation models, and ensembling seemed to be the key ingredient.
🧠🤖
Congrats!!!
Levine's take on the success of LLMs compared to video models is interesting, but I'll expand on how efforts toward AI could take two different paths, and why I think AI and NeuroAI could take different approaches moving forward. 🧵
🧠🤖 #MLSky
Alona Fyshe @alonaf.bsky.social on the BabyLM Challenge, a competition that trains language models (LMs) on smaller datasets, more akin to how a baby learns, in search of solutions to some of the major challenges of today’s LLMs.
#NeuroAI #neuroskyence
www.thetransmitter.org/neuroai/the-...
New work: AI agents learn from adult data, inheriting our biases when making decisions. What if we trained them to think like kids, who rigorously explore and make causal inferences?
Fascinating preprint from with our "blicket detector" paradigm from Chen et al at NYU& Mila. LLM's make the same causal inference mistakes that adults make but 4 year olds don't! Of course, models are trained on adult data, kids figure it out for themselves.
im-ant.github.io/publications...
Preprint Alert 🚀
Can we simultaneously learn transformation-invariant and transformation-equivariant representations with self-supervised learning?
TL;DR Yes! This is possible via simple predictive learning & architectural inductive biases – without extra loss terms and predictors!
🧵 (1/10)
Want to spend 3 weeks in South Africa for an unforgettable summer school experience? Imbizo 2026 (imbizo.africa) student applications are OPEN! Lectures, new friends, and Noordhoek beach await. Apply by July 1!
More info and apply: imbizo.africa/apply/
#Imbizo2026 #CompNeuro
on my way back to NYC, i met wise Leon Bottou in the airport. we talked. then i told him "you should tweet that!"
and, he delivered much more than a tweet: a blog post with thoughts and insights on AI research only he can deliver this clearly and succinctly.
leon.bottou.org/news/two_les...
It feels so good to see Imbizo students doing great things! @imbizo.bsky.social #imbizo
Top-down feedback is ubiquitous in the brain and computationally distinct, but rarely modeled in deep neural networks. What happens when a DNN has biologically-inspired top-down feedback? 🧠📈
Our new paper explores this: elifesciences.org/reviewed-pre...
To my Canadian colleagues: you should know that a key component of what the US is doing right now involves purging scientists & research programs for ideological impurity & (illegally) reclaiming their funds.
If you don’t want a repeat of what happened down south here in Canada, PP is not your guy
Francis Crick called it “impossible” in 1979. Now it’s real.
A 1 mm cube of mouse brain, 200k cells, 500M synapses, all mapped alongside neuronal activity.
This new MICrONS dataset maps brain structure and function in a way that we've never seen🧪
🔗 www.microns-explorer.org
📄 doi.org/10.1038/s415...
Yeah, that’s an alternative!
Depends on the school… some in-person schools eg. Imbizo put in huge amount of resources for each individual student to warrant a letter
Can LLMs be used to discover interpretable models of human and animal behavior?🤔
Turns out: yes!
Thrilled to share our latest preprint where we used FunSearch to automatically discover symbolic cognitive models of behavior.
1/12
Dr. Dan Wetmore giving a lecture
Students at Imbizo working hard on their presentation
Student presentation on designing ML solutions to understand cardiac rhythms
Student presentation on designing ML solutions to sleep paralysis
🎉 Exciting day at #Imbizo2025! Dr. Dan Wetmore & Dr. Garrick Orchard from Meta’s Reality Labs shared their industrial insights on designing top-notch AI/ML experiments, including innovative BCI applications 🤖💡 Students showcased creative solutions for EMG, sleep, wind, epilepsy monitoring & more! 🌟
Photo of the planet Earth taken from Apollo 8 during the lunar sunrise. You can see the Moon and its grey, pockmarked surface curving in the foreground and a portion of the planet Earth emerging from the darkness of space in the background like a distant, precious blue and white gem.
Christmas Eve, 1968:
“And from the crew of Apollo 8, we close, with good night, good luck, a Merry Christmas, and God bless all of you, all of you on the good Earth.”
Delighted to be in Leeds joining the School of Computing! Fantastic first impressions — like a "less offensive London" (youtu.be/watch?v=_6_VVLgrgFI). Stay tuned for a PhD position starting next October. Meanwhile, drop me a message with your CV and research interests—I'd love to hear from you!
Neuroscience is starting to grow past relying on single neuron selectivity to understand computations, now that we have more data and better analyses. This could have interesting implications for mechanistic interpretability in AI models as well!
There's plenty of evidence that suggest children explore better than adults, eg. journals.sagepub.com/doi/abs/10.1..., which seems useful for RL (eg. openreview.net/forum?id=5uU...)
🙋♀️Would love to be added!
