🔥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

I'm laughing so hard at this slide a friend sent me from one of Geoff Hinton's courses; "To deal with hyper-planes in a 14-dimensional space, visualize a 3-D space and say 'fourteen' to yourself very loudly. Everyone does it."

cognito Convolution is equivariant to translations. Self-attention is equivariant to permutations. They both have a role to play. Conv is efficient for signals with strong local correlations and motifs that can appear anywhere. SelfAtt is good for "object-based" representations where

Can machine learning uncover the multivariate neural signature of major depressive disorder in individual patients? This large-scale study including 1,801 patients and controls finds no robust multivariate depression markers. ja.ma/3S0QgFY

Meta has always tried to do the Right Thing. Meta has always practiced open research in AI. Meta has been promoting open source AI platforms. After numerous discussions over the last year (sometimes contentious) a consensus is emerging that open source AI platforms are

# on shortification of "learning" There are a lot of videos on YouTube/TikTok etc. that give the appearance of education, but if you look closely they are really just entertainment. This is very convenient for everyone involved : the people watching enjoy thinking they are

I just moved the ChatGPT tab over to the left end of my main browser window, where I keep the tabs of things I use all the time, like GMail and Google Calendar.

* Language is low bandwidth: less than 12 bytes/second. A person can read 270 words/minutes, or 4.5 words/second, which is 12 bytes/s (assuming 2 bytes per token and 0.75 words per token). A modern LLM is typically trained with 1x10^13 two-byte tokens, which is 2x10^13 bytes.

Today we're excited to introduce Devin, the first AI software engineer. Devin is the new state-of-the-art on the SWE-Bench coding benchmark, has successfully passed practical engineering interviews from leading AI companies, and has even completed real jobs on Upwork. Devin is

Do LLMs really need to be so L? That's a rejected title for a new paper w/ Andrey Gromov, Kushal Tirumala, Hassan Shapourian, Paolo Glorioso on pruning open-weight LLMs: we can remove up to *half* the layers of Llama-2 70B w/ essentially no impact on performance on QA benchmarks. 1/

AlphaFold 3 predicts the structure and interactions of all of life’s molecules @google blog.google/technology/ai/…

The killer app of LLMs is Scarlett Johansson. You all thought it was math or something

Best tiled matmul animation I've found on the internet. Thanks Michal Sojka (@[email protected])

Do you use surface fMRI? We found spurious correlations in surface fMRI, with potentially serious implications for test-retest reliability, fingerprinting, functional parcellations and brain-behaviour associations (1/n) biorxiv.org/cgi/content/sh…

Excited to share our Graph Foundation Model, 🌐 GraphFM, trained on 152 datasets with over 7.4 million nodes and 189 million edges spanning diverse domains. 🚨 Check out our preprint for GraphFM where we test how our model scales with data and model size, and show efficient

Moths are attracted to lights because of the same mathematics that underlies twistor theory and compactification in theoretical physics: projective geometry. It all starts from a simple observation: translations are just rotations whose center is located "at infinity". (1/11)

Join us in congratulating the 2024 ACNP Travel Award Class! bit.ly/46GyJK1 Amanda Arulpragasam Estef Azevedo Igor D. Bandeira, MD, PhD Andrea Boscutti @CarinaSBrown Brenda Cabrera Mendoza Robert Y. Chen Seungwon (Sebastian) Choi 최승원 Dr. Kirstie Cummings Ashley Cunningham, MSc 🧠 Pasha Davoudian Kevin Dowling 🧬🧠 Lana Ruvolo, PhD

With neuroscience datasets and scientific collaborations growing in size, Gaelle Chapuis and Olivier Winter explain why neuroscience needs to create a career path for software engineers. thetransmitter.org/craft-and-care…

In the physical world, almost all information is transmitted through traveling waves -- why should it be any different in your neural network? Super excited to share recent work with the brilliant Mozes Jacobs: "Traveling Waves Integrate Spatial Information Through Time" 1/14

All Americans should think about this chart