🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

cramming for exams is actually optimal imo

🚨 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/ Greta Tuckute, Antoine Bosselut, & Martin Schrimpf 🧵👇

The dos and don’ts of LLM cognitive evaluations, finally published!

Graceful under pressure. Simply the best there is!

Deepseek was trained on NVIDIA GPUs.

TopoNets is accepted into ICLR 2025 🥳 Inducing brain-like self-similarity in the weights of vision and language models yields: - lower dimensionality - parameter efficiency - brain-like functional organization toponets.github.io

Unlike the brain, most ANNs lack any kind of organization of units🧠 In our paper (ICLR 2025) with mayukh09 Apurva Ratan Murty, we present TopoLoss, a simple, scalable way to add brain-like topography to AI models with minimal performance loss🧵 toponets.github.io

Very proud to share our ICLR 2026 paper: TopoNets! High-performing vision and language models with brain-like topography! Expertly led by grad student mayukh09 and Mainak Deb! A brief thread..

Excited to share that our paper, 'The LLM Language Network,' has been accepted to NAACL 2025! Looking forward to presenting it in Albuquerque—see you there! 🏜️ #NAACL2025

Anthropic. Finally.

🚨 New Preprint!! LLMs trained on next-word prediction (NWP) show high alignment with brain recordings. But what drives this alignment—linguistic structure or world knowledge? And how does this alignment evolve during training? Our new paper explores these questions. 👇🧵

LIT lab is presenting 2 posters at #CNS2025! Session D - Scaling Laws in Functional Region of Interest (fROI) Analyses by Ruimin Gao cogneurosociety.org/poster/?id=6458 and...

Ruimin Gao ... Session E - Characterizing the effects of content, task and modality on task-driven semantic processing in the brain (sketchpad series) by Jin Li 李锦 Feedback appreciated on both projects! cogneurosociety.org/poster/?id=5805

Together with Neil Rathi I will present our #ICLR2025 Oral paper on TopoLM, a topographic language model! Oral: Friday, 25 Apr 4:18 p.m. (session 4C) Poster: Friday, 25 Apr 10 a.m. --> Hall 3 + Hall 2B Paper: arxiv.org/abs/2410.11516 Code and weights: github.com/epflneuroailab…

Before ICLR 2025 comes to and end tomorrow, a few #NeuroAI impressions from Singapore. First, very happy to present our work on TopoLM as an oral, here with Neil Rathi x.com/HannesMehrer/s… paper: doi.org/10.48550/arXiv… code: github.com/epflneuroailab…

I think the devil doesn't exist, but man has created him, he has created him in his own image and likeness.

Heading over to #APS25DC ! Excited to talk about language, cognition, world knowledge and LLMs Friday @ 6pm. If you want to chat 1:1, feel free to reach out!

What are the organizing dimensions of language processing? We show that voxel responses are organized along 2 main axes: processing difficulty & meaning abstractness—revealing an interpretable, topographic representational basis for language processing shared across individuals.

This workshop is going to be properly epic...very honored to be included among the speakers

🚨New Preprint!! Thrilled to share with you our latest work: “Mixture of Cognitive Reasoners”, a modular transformer architecture inspired by the brain’s functional networks: language, logic, social reasoning, and world knowledge. 1/ 🧵👇