Kim Stachenfeld, PhD
@neurokim.bsky.social
Neuro + AI Research Scientist at DeepMind; Affiliate Professor at Columbia Center for Theoretical Neuroscience. Likes studying learning+memory, hippocampi, and other things brains have and do, too. she/her.
New work on automated (interpretable!!) experimental design, led by @noemielteto.bsky.social See 👇 for thread
Noémi Éltető@noemielteto.bsky.social · 2mo agoFirst paper since joining Google DeepMind! We present 🌍ATLAS (Active Theory Learning for Automated Science), a pipeline that generates interpretable mechanistic models from data and optimizes experiments to test them. Thread below
Agentic coding makes it possible to specify a neuroscience model in hours instead of months, writes @briandepasquale.bsky.social. The field risks becoming prolific but shallow—generating models faster than we can generate insights. #neuroskyence www.thetransmitter.org/the-big-pict...
How AI coding is reshaping theoretical neuroscience
Agentic coding makes it possible to specify a neuroscience model in hours instead of months. Neuroscientists weigh in on that tectonic change.
thetransmitter.org
I have been so excited about this project. In many ways the most surprising thing to me was how seemingly similar the AI-discovered models were to simple ones I thought I understood, even though they fit way better. This means we can also really get what makes them work.
Kevin J Miller@kevinjmiller.bsky.social · 2mo agoComputational models are a key part of science but discovering new ones is hard! DataDIVER discovers concise models from data, which surface new mechanistic ideas and clear predictions for future experiments From Google Deepmind Neuroscience Lab + collaborators www.biorxiv.org/content/10.6...
New preprint! Very excited to share our new work introducing DataDIVER, for automatically discovering interpretable computational models from scientific data 📊🤿 See below for a visual summary from my magnificent co-lead @kevinjmiller.bsky.social ! 👇
Kevin J Miller@kevinjmiller.bsky.social · 2mo agoComputational models are a key part of science but discovering new ones is hard! DataDIVER discovers concise models from data, which surface new mechanistic ideas and clear predictions for future experiments From Google Deepmind Neuroscience Lab + collaborators www.biorxiv.org/content/10.6...
The US/Iran war and escalating rhetoric are already disrupting civilian life and academic infrastructure across the region. We drafted a letter in defense of academic life, and to mobilize concrete support for affected students, scholars, and collaborations. Please check Sepi’s message and sign.
Protect Academic Life in Iran
We, the undersigned academics and researchers from around the world, express our profound concern over recent military strikes on Iran, the retaliatory responses, and the reported impact on civilian l...
sites.google.com
Sepiedeh Keshavarzi @sepikeshavarzi.bsky.social · 4mo agoWhen universities and research institutions become military targets, academics cannot remain silent. I co-initiated an open letter calling for global academic solidarity and support for affected students and scholars. Please share. to read and sign: sites.google.com/view/protect...
Some reports say over 500 schools, 55 libraries, & 25 universities hit. You can debate the numbers, but hitting Sharif University & Beheshti is like hitting MIT & Stanford. I keep wondering: How would the scientific community respond differently if it was those universities? What’s the difference?
Last night, US/Israeli strikes bombed Sharif University, my alma mater, heavily damaging the IT Center, Philosophy of Science building, EE, and more. Trump spoke of sending Iran "back to the Stone Age." That is the goal of this war. Scientists worldwide should speak up against these atrocities.
There are universities in Iran being bombed, the Weizmann Institute in Israel was bombed, Gaza universities destroyed, and US science and universities under authoritarian attack. I have friends and colleagues doing neuroscience in or from those places. Across countries, we have much in common.
Puff the Magic Hater@mskellymhayes.bsky.social · 4mo agoYou have more in common with the people of Iran than you do with anyone in this administration, any member of the technocracy, anyone who is profiting from this war, or any billionaire. When you see Iranians forming human chains outside key infrastructure sites, you should feel a sense of kinship.
How can machines achieve the kind of flexible learning mastered by our brains? That’s what our own @neurokim.bsky.social is trying to find out! Learn more about ARNI’s work on natural and artificial intelligence: youtu.be/gM8YCaiAWrc?... #BrainAwarenessWeek
ARNI: Memory Driven Learning with Kim Stachenfeld
YouTube video by Columbia Engineering
youtu.be
#Cosyne2026 workshops pro tip: It's often hard to pick a single workshop due to fomo about the cool workshops you *cannot* attend. I recommend a buddy system: Have a friend go to a different session, and then both of you report back at the next meal.
Wonderful work by @weijiazh.bsky.social at #Cosyne2026, who beautifully navigated a busy poster session yesterday!
Jesse Geerts@jessegeerts.bsky.social · 5mo agoIn the same session, also make sure to visit poster [3-135] by @weijiazh.bsky.social , who’s presenting joint work with @neurokim.bsky.social and Josh Jacobs showing that Human Single Neurons and Predictive Models Remap Differently in Reward and Transition Relearning
Awesome work by esteemed colleague @jessegeerts.bsky.social at #Cosyne2026
Jesse Geerts@jessegeerts.bsky.social · 5mo agoExcited to be at #COSYNE2026 ! I’m presenting our recent preprint with Francesca Greenstreet, @juangallego.bsky.social an and @clopathlab.bsky.social in today’s poster session [3-026] www.biorxiv.org/content/10.6...
Hippocampal sequences encode recent history independent of task relevance. Poster in today's session (2-149) at @cosynemeeting.bsky.social . led by @gabymichel.bsky.social (collab w Spruston Lab at @hhmijanelia.bsky.social )!
Poster in today's session (2-115) at @cosynemeeting.bsky.social : Parallel dopamine signals support hierarchical reinforcement learning of motor sequences 🧠 by @arnavraha.bsky.social , an awesome student working with me + Vikram Gadagkar
Fabulous keynote session at @cosynemeeting.bsky.social. @neurokim.bsky.social and I kicked off the meeting and introduced Chris Olah. m.youtube.com/watch?v=koGy...
Cosyne 2026 - Session 1: Opening Remarks
YouTube video by Cosyne Talks
m.youtube.com
I have just arrived at @cosynemeeting.bsky.social ! During my flight, as I thought about opening remarks (and had a glass of wine), I got to reflect on why I love neuroscience. Maybe other folks are doing the same and would like to read or add, so I thought I'd do something unusual and share!
Updated work from @jessegeerts.bsky.social extending his results on transitive inference in transformers (including LLMs!) updated paper: arxiv.org/abs/2506.04289 bleeprint (what are we calling these?) below ⬇️
Relational reasoning and inductive bias in transformers and large language models
Transformer-based models have demonstrated remarkable reasoning abilities, but the mechanisms underlying relational reasoning remain poorly understood. We investigate how transformers perform \textit{...
arxiv.org
Jesse Geerts@jessegeerts.bsky.social · 6mo agoUpdate on this work! We've extended our transitive inference study to large language models 🧵
Researchers are using LLMs to analyze the literature, brainstorm hypotheses, build models and interact with complex datasets. Hear from @mschrimpf.bsky.social, @neurokim.bsky.social, @jeremymagland.bsky.social, @profdata.bsky.social and others. #neuroskyence www.thetransmitter.org/machine-lear...
How neuroscientists are using AI
Eight researchers explain how they are using large language models to analyze the literature, brainstorm hypotheses and interact with complex datasets.
thetransmitter.org
Our summer program values mentorship as much as scientific skill-building, connecting Africa’s talents with experts in both #academia and #industry. Grateful to @neurokim.bsky.social & @ankahira.bsky.social for inspiring our 2025 cohort. @columbiauniversity.bsky.social @astra-zeneca.bsky.social
🧠 How do transformers learn relational reasoning? We trained small transformers on transitive inference (if A>B and B>C, then A>C) and discovered striking differences between learning paradigms. Our latest work reveals when and why AI systems generalize beyond training data 🤖
New work on relational reasoning in transformers! TLDR: Inductive biases of In-Weight and In-Context Learning in transformers are really different for relational reasoning, and pretraining can make a big difference for in-context. Check out @jessegeerts.bsky.social's thread for more!
Relational reasoning and inductive bias in transformers trained on a transitive inference task
Transformer-based models have demonstrated remarkable reasoning abilities, but the mechanisms underlying relational reasoning in different learning regimes remain poorly understood. In this work, we i...
arxiv.org
Jesse Geerts@jessegeerts.bsky.social · last yr.🧠 How do transformers learn relational reasoning? We trained small transformers on transitive inference (if A>B and B>C, then A>C) and discovered striking differences between learning paradigms. Our latest work reveals when and why AI systems generalize beyond training data 🤖
💥 Do we now have all the components necessary to reach #AGI, or are there more discoveries to be made? Can the study of the brain help provide them? We tackle these questions and more at our Conference on the Mathematics of Neuroscience and AI in sun-soaked Split, Croatia: www.neuromonster.org
Tomorrow is our @cosynemeeting.bsky.social workshop on Graph Neural Networks! From molecules to circuits to biomechanics to reasoning behaviors to social behaviors, neuroscience is rich with geometrically structured data. Our goal: demystify GNNs, talk opportunities for 🧠
Brian DePasquale@briandepasquale.bsky.social · last yr.@cosynemeeting.bsky.social Also! Don’t miss a 💡 insightful tutorial on GNNs for connectomics analysis tomorrow at the workshop! Details here: sites.google.com/bu.edu/gnnwo...
@cosynemeeting.bsky.social workshops are almost here! Join GNN workshop w @neurokim.bsky.social and Sam Lewallen to hear @herrsaalfeld.bsky.social head of computation @hhmijanelia.bsky.social present on GNNs for learning structure and function underlying neural assemblies #cosyne2025
Her lab does impressive foundational work on geometric statistics and manifold learning, sure to be an amazing talk! Come for the GNNs, stay for the manifolds! #cosyne2025 @neurokim.bsky.social
More 🔥🔥 speakers at @cosynemeeting.bsky.social GNN workshop: @ninamiolane.bsky.social who runs the @geometric-intel.bsky.social lab at UCSB. She will take us beyond 🚀🚀 GNNs, presenting a survey of message passing topological neural networks for neuroscience
Rounding out our speakers @cosynemeeting.bsky.social GNN workshop is @dom-beaini.bsky.social of @mila-quebec.bsky.social and @valenceai.bsky.social. Come hear him tell us how to learn a…MOLECULE! Don’t forget brains 🧠 are made of chemicals ⚗️ and chemicals + graphs = 🫶
