Lightnews — Scholar-powered news

Reposted by Simon Schug

Brenden Lake @brendenlake.bsky.social · Jun 12

I'm joining Princeton University as an Associate Professor of Computer Science and Psychology this fall! Princeton is ambitiously investing in AI and Natural & Artificial Minds, and I'm excited for my lab to contribute. Recruiting postdocs and Ph.D. students in CS and Psychology — join us!

Nassau Hall. Photo credit to Debbie and John O'Boyle

4 2 47

Simon Schug @smonsays.bsky.social · Apr 25

Are transformers smarter than you? Hypernetworks might explain why.

Come checkout our Oral at #ICLR tomorrow (Apr 26th, poster at 10:00, Oral session 6C in the afternoon).

openreview.net/forum?id=V4K...

1 8

Reposted by Simon Schug

Taylor Webb @taylorwwebb.bsky.social · Mar 10

LLMs have shown impressive performance in some reasoning tasks, but what internal mechanisms do they use to solve these tasks? In a new preprint, we find evidence that abstract reasoning in LLMs depends on an emergent form of symbol processing arxiv.org/abs/2502.20332 (1/N)

Emergent Symbolic Mechanisms Support Abstract Reasoning in Large Language Models

Many recent studies have found evidence for emergent reasoning capabilities in large language models, but debate persists concerning the robustness of these capabilities, and the extent to which they ...

arxiv.org

4 33 110

Reposted by Simon Schug

Konrad Kording @kordinglab.bsky.social · Feb 14

New blog post: The principle of neuroscience. medium.com/@kording/the...

The Principle of Neural Science

I first encountered Principles of Neural Science as a young student of neuroscience. The book was filled with delightful narratives…

medium.com

3 5 45

Reposted by Simon Schug

Marine Schimel @marineschimel.bsky.social · Jan 31

For my first Bluesky post, I'm very excited to share a thread on our recent work with Mitra Javadzadeh, investigating how connections between cortical areas shape computations in the neocortex! [1/7] www.biorxiv.org/content/10.1...

Dynamic consensus-building between neocortical areas via long-range connections

The neocortex is organized into functionally specialized areas. While the functions and underlying neural circuitry of individual neocortical areas are well studied, it is unclear how these regions op...

www.biorxiv.org

1 11 19

Reposted by Simon Schug

Guillaume Bellec @bellecguill.bsky.social · Jan 8

Pre-print 🧠🧪
Is mechanism modeling dead in the AI era?

ML models trained to predict neural activity fail to generalize to unseen opto perturbations. But mechanism modeling can solve that.

We say "perturbation testing" is the right way to evaluate mechanisms in data-constrained models

1/8

4 46 120

Reposted by Simon Schug

Mark D Humphries @markdhumphries.bsky.social · Dec 30

Cutting it a bit fine, but here’s my review of the year in neuroscience for 2024

The eighth of these, would you believe? We’ve got dark neurons, tiny monkeys, the most complete brain wiring diagram ever constructed, and much more…
Published on The Spike

Enjoy!

medium.com/the-spike/20...

2024: A Review of the Year in Neuroscience

Feeling a bit wired

medium.com

7 73 190

Reposted by Simon Schug

Kris Jensen @kristorpjensen.bsky.social · Dec 21

I wrote an introduction to RL for neuroscience last year that was just published in NBDT: tinyurl.com/5f58zdy3

This review aims to provide some intuition for and derivations of RL methods commonly used in systems neuroscience, ranging from TD learning through the SR to deep and distributional RL!

An introduction to reinforcement learning for neuroscience | Published in Neurons, Behavior, Data analysis, and Theory

By Kristopher T. Jensen. Reinforcement learning for neuroscientists

tinyurl.com

6 31 130

Reposted by Simon Schug

Ben Recht @beenwrekt.bsky.social · Dec 20

Stitching component models into system models has proven difficult in biology. But how much easier has it been in engineering? www.argmin.net/p/monster-mo...

Monster Models

Systems-level biology is hard because systems-level engineering is hard.

www.argmin.net

3 2 12

Reposted by Simon Schug

Badr AlKhamissi @bkhmsi.bsky.social · Dec 19

🚨 New Paper!

Can neuroscience localizers uncover brain-like functional specializations in LLMs? 🧠🤖

Yes! We analyzed 18 LLMs and found units mirroring the brain's language, theory of mind, and multiple demand networks!

w/ @gretatuckute.bsky.social, @abosselut.bsky.social, @mschrimpf.bsky.social
🧵👇

2 27 110

Reposted by Simon Schug

Blake Richards @tyrellturing.bsky.social · Dec 16

1/ Okay, one thing that has been revealed to me from the replies to this is that many people don't know (or refuse to recognize) the following fact:

The unts in ANN are actually not a terrible approximation of how real neurons work!

A tiny 🧵.

🧠📈 #NeuroAI #MLSky

Blake Richards @tyrellturing.bsky.social · Dec 16

Why does anyone have any issue with this?

I've seen people suggesting it's problematic, that neuroscientists won't like it, and so on.

But, I literally don't see why this is problematic...

PessoaBrain @pessoabrain.bsky.social · Dec 15

This would be funny if it weren't sad...
Coming from the "giants" of AI.
Or maybe this was posted out of context? Please clarify.
I can't process this...

21 38 150

Reposted by Simon Schug

Razvan Pascanu @razvan-pascanu.bsky.social · Dec 15

For my first post on Bluesky .. I'll start by announcing our 2025 edition of EEML which will be in Sarajevo :) ! I'm really excited about it and hope to see many of you there. Please follow the website (and Bluesky account) for more details which are coming soon ..

EEML @eemlcommunity.bsky.social · Dec 15

Hello Bluesky! 🦋

This will be the official account of the Eastern European Machine Learning (EEML) community.

Follow us for news regarding our summer schools, workshops, education/community initiatives, and more!

1 7 32

Reposted by Simon Schug

Markus Meister @mameister4.bsky.social · Nov 14

Have you had private doubts whether we'll ever understand the brain? Whether we'll be able explain psychological phenomena in an exhaustive way that ranges from molecules to membranes to synapses to cells to cell types to circuits to computation to perception and behavior?

1 12 39

Reposted by Simon Schug

Andrew Lampinen @lampinen.bsky.social · Dec 10

What counts as in-context learning (ICL)? Typically, you might think of it as learning a task from a few examples. However, we’ve just written a perspective (arxiv.org/abs/2412.03782) suggesting interpreting a much broader spectrum of behaviors as ICL! Quick summary thread: 1/7

The broader spectrum of in-context learning

The ability of language models to learn a task from a few examples in context has generated substantial interest. Here, we provide a perspective that situates this type of supervised few-shot learning...

arxiv.org

2 31 120

Reposted by Simon Schug

Kai Sandbrink @ackaisa.bsky.social · Dec 3

Thrilled to share our NeurIPS Spotlight paper with Jan Bauer*, @aproca.bsky.social*, @saxelab.bsky.social, @summerfieldlab.bsky.social, Ali Hummos*! openreview.net/pdf?id=AbTpJ...

We study how task abstractions emerge in gated linear networks and how they support cognitive flexibility.

2 15 64

Simon Schug @smonsays.bsky.social · Nov 20

Would love to be added as well :)

Reposted by Simon Schug

Blake Richards @tyrellturing.bsky.social · Nov 13

Great thread from @michaelhendricks.bsky.social!

Reminds me of something Larry Abbott once said to me at a summer school:

Many physicists come into neuroscience assuming that the failure to find laws of the brain was just because biologists aren't clever enough. In fact, there are no laws.

🧠📈 🧪

Michael Hendricks 🇨🇦 @michaelhendricks.bsky.social · Nov 12

I came across a quote in an article, which I will paraphrase: the ultimate goal of neuroscience is to model the brain and derive laws that define the brain’s computational abilities. Statements like this are common and presented as self-evident, but I think they are wrong.

4 9 68

Reposted by Simon Schug

Griffiths Computational Cognitive Science Lab @cocoscilab.bsky.social · Nov 19

(1/5) Very excited to announce the publication of Bayesian Models of Cognition: Reverse Engineering the Mind. More than a decade in the making, it's a big (600+ pages) beautiful book covering both the basics and recent work: mitpress.mit.edu/978026204941...

15 120 520

Simon Schug @smonsays.bsky.social · Nov 16

🙋‍♂️

1

Simon Schug @smonsays.bsky.social · Nov 13

To help find people at the intersection of neuroscience and AI. Of course let me know if I missed someone or you’d like to be added 🧪 🧠

#neuroskyence

go.bsky.app/CAfmKQs

33 18 50

Simon Schug @smonsays.bsky.social · Nov 13

I think you are already part of it - just double checked :)

1

Simon Schug @smonsays.bsky.social · Oct 28

tl;dr: hypernetworks are hiding in our beloved transformers.

github.com/smonsays/hyp...

GitHub - smonsays/hypernetwork-attention: Official code for the paper "Attention as a Hypernetwork"

Official code for the paper "Attention as a Hypernetwork" - smonsays/hypernetwork-attention

github.com

Simon Schug @smonsays.bsky.social · Oct 28

With language being highly compositional itself, could the hypernetwork mechanism play a part in explaining the success of multi-head attention?

Maybe! Have a look at the paper in case you are curious!

arxiv.org/abs/2406.05816

Attention as a Hypernetwork

Transformers can under some circumstances generalize to novel problem instances whose constituent parts might have been encountered during training but whose compositions have not. What mechanisms und...

arxiv.org

1 1

Simon Schug @smonsays.bsky.social · Oct 28

Indeed in line with the hypothesis that the hypernetwork mechanism supports compositionality, this modification (hyla) improves performance on unseen tasks.

1

Simon Schug @smonsays.bsky.social · Oct 28

So what happens if we strengthen the hypernetwork mechanism?
Could we maybe further improve compositionality?

We can for instance make the value network nonlinear - without introducing additional parameters.

1