Interested in multitasking RNNs from a theory perspective? Check out this preprint with the amazing @lpezon.bsky.social. TLDR: A low-rank / latent space approach to @lndriscoll.bsky.social & @sussillodavid.bsky.social style shared components. And a story starring solution space degeneracy.

Louis Pezon@lpezon.bsky.social · last mo.

Both brains and RNNs can re-use components of computation across similar tasks or contexts. But what exactly are those “shared components”? How can they be used to solve several tasks? We address these questions in a new preprint with @avm.bsky.social! Link: www.biorxiv.org/content/10.6...

Distinct roles of hippocampus and neocortex in symbolic compositional generalization Awesome work from: @summerfieldlab.bsky.social Lab www.sciencedirect.com/science/arti...

Distinct roles of hippocampus and neocortex in symbolic compositional generalization

Humans can combine symbols to generate new meanings. Here, we studied the regional neural mechanisms that might make this possible. We asked participa…

sciencedirect.com

www.linkedin.com/posts/alexan...

We are seeking two postdoctoral fellows to join our team working at the intersection of artificial intelligence and neuroscience. Our research is built around three intertwined questions: how to… | ...

We are seeking two postdoctoral fellows to join our team working at the intersection of artificial intelligence and neuroscience. Our research is built around three intertwined questions: how to mea...

linkedin.com

Accepted at ICML 2026. I am extremely proud of this work. Local learning is starting to work really well! The theoretical perspective of local learning minimizing an emergent global objective has been eye opening Congrats @zihan-wu.bsky.social and Ariane Delrocq! Great team

Zihan Wu@zihan-wu.bsky.social · 2mo ago

Can we match self-supervised backpropagation using local learning rules? We show it is possible in our new paper accepted by ICML. We achieve: 1. theoretical equivalence to BP in a controlled setup 2. new SOTA for local learning across image datasets 3. same performance as BP on multiple datasets

Can we match self-supervised backpropagation using local learning rules? We show it is possible in our new paper accepted by ICML. We achieve: 1. theoretical equivalence to BP in a controlled setup 2. new SOTA for local learning across image datasets 3. same performance as BP on multiple datasets

New job posting! If you're interested in working with our group, check it out. 3 year position (with possibility to extend) at >100k. alleninstitute.org/careers/jobs...

Open Positions | Allen Institute

Build your career at the Allen Institute. Explore current job openings and find your place in a team driving some of the most ambitious open science in the world.

alleninstitute.org

1/11 Happy to share our TICS paper on using the flexibility of one of the most basic cognitive functions, perception, to understand one of the most complex cognitive dysfunctions, psychiatric conditions (also my first formal work in computational psychiatry 🎉) 📄: www.cell.com/trends/cogni... 🧵 : 👇

Perceptual multistability: a multifaceted window into brain dysfunctions

Perceptual multistability, observed across species and sensory modalities, offers valuable insights into numerous cognitive functions and dysfunctions. For instance, differences in temporal dynamics a...

cell.com

Trends in Cognitive Sciences@cp-trendscognsci.bsky.social · 4mo ago

Online Now: Perceptual multistability: a multifaceted window into brain dysfunctions

Ever heard of the lottery ticket hypothesis? Our new paper shows that lottery tickets are not a useful metaphor to explain the success of overparameterized neural networks - and suggests an alternative metaphor: escape dimensions

Flavio Martinelli@flavioh.bsky.social · 2mo ago

NEW PAPER. Why do larger networks train better? "Because they contain more candidate *sub*networks that can learn the task" → lottery tickets This popular explanation uses an appealing but misleading metaphor🧵 We propose an intuitive alternative grounded in theory: escape dimensions

NEW PAPER. Why do larger networks train better? "Because they contain more candidate *sub*networks that can learn the task" → lottery tickets This popular explanation uses an appealing but misleading metaphor🧵 We propose an intuitive alternative grounded in theory: escape dimensions

Excited to share that our study on how cell-type-specific synaptic scaling mechanisms regulate memory representations in associative learning is now published! www.jneurosci.org/content/earl...

Cell-type-specific synaptic scaling mechanisms differentially contribute to associative learning

Excitatory synaptic scaling regulates network dynamics by proportionally adjusting excitatory synaptic strengths after sensory perturbations. During associative learning, blocking excitatory scaling i...

jneurosci.org

Incredibly grateful to @cmiehl.bsky.social and @gjorjulijana.bsky.social for their thoughtful and spot-on Preview "Novelty beyond counting" of our recent work in Neuron with @modirshanechi.bsky.social and @gerstnerlab.bsky.social! 🧠✨ It's a real honor 🙏 www.cell.com/neuron/fullt...

Some incredibly exciting news that still feels a bit surreal: I am starting my research group @mpicybernetics.bsky.social! The best part? We are hiring at all levels! Curious about the science we plan to tackle, read along :) #NeuroSky

Novelty is not just about whats new, but also what feels new given past experience. New study from Sophia Becker in Wulfram Gerstner’s @epfl-brainmind.bsky.social lab posits a model showing how similarity between familiar and novel stimuli shapes exploration and learning - doi.org/10.1016/j.ne...

So excited to see this finally out!! 🤩🎉 A big thank you to our reviewers for their helpful feedback and to @modirshanechi.bsky.social and Wulfram Gerstner for the wonderful collaboration!

EPFL Brain Mind Institute@epfl-brainmind.bsky.social · 4mo ago

Novelty is not just about whats new, but also what feels new given past experience. New study from Sophia Becker in Wulfram Gerstner’s @epfl-brainmind.bsky.social lab posits a model showing how similarity between familiar and novel stimuli shapes exploration and learning - doi.org/10.1016/j.ne...

How does circuit structure shape neural activity? The lab of @epfl-brainmind.bsky.social Prof. Wulfram Gerstner shows that distinct neural circuits can produce similar low-dimensional dynamics, while retaining clear signatures in single neuron and population activity data: doi.org/10.1016/j.ne...

So happy to see this work out! 🥳 Huge thanks to our two amazing reviewers who pushed us to make the paper much stronger. A truly joyful collaboration with @lucasgruaz.bsky.social, @sobeckerneuro.bsky.social, and Johanni Brea! 🥰 Tweeprint on an earlier version: bsky.app/profile/modi... 🧠🧪👩‍🔬

Open Mind@openmindjournal.bsky.social · 12mo ago

Excited to share new work led by @vivekmyers.bsky.social and @crji.bsky.social that proves you can learn to reach distant goals by solely training on nearby goals. The key idea is a new form of invariance. This invariance implies generalization w.r.t. the horizon.

Vivek Myers@vivekmyers.bsky.social · last yr.

Reinforcement learning agents should be able to improve upon behaviors seen during training. In practice, RL agents often struggle to generalize to new long-horizon behaviors. Our new paper studies *horizon generalization*, the degree to which RL algorithms generalize to reaching distant goals. 1/

Stoked to be at RLDM! Curious how novelty and exploration are impacted by generalization across similar stimuli? Then don't miss my flash talk in the PIMBAA workshop (tmr at 10:30, E McNabb Theatre) or stop by my poster tmr (#74)! Looking forward to chat 🤩 www.biorxiv.org/content/10.1...

Representational similarity modulates neural and behavioral signatures of novelty

Novelty signals in the brain modulate learning and drive exploratory behaviors in humans and animals. While the perceived novelty of a stimulus is known to depend on previous experience, the effect of...

biorxiv.org