This might be the secret to breaking through the next plateau in deeper reasoning, planning and retrieval capabilities for AI agents 🤔 LGGMs (large generative graph models) are on the rise! While Adobe and Intel were first at it with LGGMs, researchers at Georgia Tech have

What will a foundation model for the brain look like? We argue that it must be able to solve a diverse set of tasks across multiple brain regions and animals. Check out our preprint where we introduce a multi-region, multi-animal, multi-task model (MtM): arxiv.org/abs/2407.14668

✨🎨🏰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

Here it is! A huge milestone in neuroscience – the complete connectome of the fly brain from the FlyWire team (FlyWire). In this special issue, we have 9 research articles. I’ll try to summarize them in a couple threads starting here 🧵

Checkout the launch of The Transmitter's new essay series on NeuroAI, with an intro essay by Tony Zador exploring how neuroscience has inspired advances in artificial intelligence and how AI has provided a testing ground for models in neuroscience. thetransmitter.org/neuroai/neuroa…

Animals are born with innate abilities, such as spiders spinning webs. But where do these abilities come from? CSHL’s Tony Zador & Alexei Koulakov propose AI that could solve the mystery. cshl.edu/the-next-evolu…

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.

language modeling is not unsupervised learning. it is not (and please stop saying this) self-supervised learning. next-token prediction is textbook _supervised_ learning, and i will die on this hill

jianlin.su Super cool! We tried the same in arxiv.org/abs/2310.16046 on a brain-decoding task (2023) and saw real gains—details in Appendix A.1. (sry, we didn't do ablations) VO rotation helped a lot in our case since many input tokens were identical and only had different positions.

Scaling models across multiple animals was a major step toward building neuro-foundation models; the next frontier is enabling multi-task decoding to expand the scope of training data we can leverage. Excited to share our #ICLR2025 Spotlight paper introducing POYO+🧠 🧵

1/6 🚀 Excited to share that BrainNRDS has been accepted as an oral at #CVPR2025! We decode motion from fMRI activity and use it to generate realistic reconstructions of videos people watched, outperforming strong existing baselines like MindVideo and Stable Video Diffusion.🧠🎥

Excited to announce the Foundation Models for the Brain and Body workshop at #NeurIPS2025!🧠 We invite short papers or interactive demos on AI for neural, physiological or behavioral data. Submit by Aug 22 👉 brainbodyfm-workshop.github.io