Check out this new paper: Led by @mehdiazabou and @evadyer, we show that it is possible to get SOTA brain decoding with transfer across individuals and tasks! The key is a clever way to tokenize spiking data for transformers. #brain #neurotech #NeurIPS2023

Autoregressive language models learn to compress data by mapping sequences to high-dimensional representations and decoding one token at a time. The quality of compression, as defined by the ability to predict the next token given a prompt, progressively improves (as measured by

4/4) Keep your eyes out for what our Paradigms of Intelligence team will be producing in the coming years! I’m pumped about the work and I’m confident that this group will produce some major breakthroughs in the near future to make AI more efficient and robust. 🙂 🧠 🤖

3/4) I’m going to maintain a reduced position at @mcgillu and @Mila_Quebec, so don’t consider me as having completely abandoned academia. (I'm lucky to be where I am...) But, I’m keen to get more time to work with a team on some bigger problems I couldn’t tackle in my own lab.

2/4) This is a big step for me, having spent my adult life in academia. But, there was no way I could pass up an opportunity to work with some of the smartest iconoclasts in the business, including @blaiseaguera himself, @dileeplearning, and many others.

1/4) I’m excited to announce that I have joined the Paradigms of Intelligence team at @Google ( https://t.co/5FCISKXkXb)! Our team, led by @blaiseaguera, is bringing forward the next stage of AI by pushing on some of the assumptions that underpin current ML. #AI #neuroscience

How can large-scale models + datasets revolutionize neuroscience 🧠🤖🌐? We are excited to announce our workshop: “Building a foundation model for the brain: datasets, theory, and models” at @CosyneMeeting #COSYNE2025. Join us in Mont-Tremblant, Canada from March 31 - April 1.

It’s been a long time coming, but I’m thrilled to share my first research paper with @arna_ghosh , @ckaplanis1, @tyrell_turing, and Doina! Just accepted to NeurIPS 2024 (see u in Vancouver! 🇨🇦). This will be a longer thread—thanks for following along! https://t.co/UvG7h2LA2H 1/11

Why does #compneuro need new learning methods? ANN models are usually trained with Gradient Descent (GD), which violates biological realities like Dale’s law and log-normal weights. Here we describe a superior learning algorithm for comp neuro: Exponentiated Gradients (EG)! 1/12

CC @KordingLab @TonyZador - we need people lively people like you to boost the network effects. 🙂

For real, everyone in neuroscience and AI: Get off this site. Elon is now using this platform to mess with American democracy. No one should be here anymore. NeuroAI Bluesky is getting livelier every day. Please come join us.

✨🎨🏰Super excited to share our new paper Ensemble everything everywhere: Multi-scale aggregation for adversarial robustness Inspired by biology we 1) get adversarial robustness + interpretability for free, 2) turn classifiers into generators & 3) design attacks on vLLMs 1/12

A fun @a16zBioHealth podcast w/@vijaypande & @liubowen16 on AI and drug discovery covering, among other things, foundation models in biology, LLMs for small molecules, clinical trial opt, evolution and AI, and many opportunities for AI powered efficiency in drug design

What are foundation models in neuroscience? I'll be giving a talk next week to the NIH neuroscience ethics working group. I started writing a short blog post which snowballed into this 5,000 word essay

She’s gonna publish a dozen papers on the internet’s reaction to her terrible breakdancing. This woman is playing 5D chess on an academic scale.

The degree of rigor by Colin (et al) to formalize what’s meant by “biologically plausible” in terms of locality (TL;DR which variables have access to which other variables) is quite impressive, and worth thinking through for anyone interested in neuro/AI.

New research from our lab, led by @KarinSaltoun: #brain #asymmetry changes *within-subjects* over years, which explains individual differences in i) everyday behavior and ii) vulnerability to disease; demonstrated at population scale preprint: https://t.co/9fu6AsbjPU

Our review on Language in Brains, Minds, and Machines (with @Nancy_Kanwisher @ev_fedorenko) is now officially published and the volume is OPEN access! https://t.co/lXyp4ZgSbu

you know you would

Is exponential gradient descent a solution to explain learning in biological neurons? Presentation by @tyrell_turing at Neuro-AI at @uwcnc

Holy shit this is awesome 🇺🇸🇺🇸🇺🇸🇺🇸🇺🇸