🔥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

arXiv -> alphaXiv Students at Stanford have built alphaXiv, an open discussion forum for arXiv papers. alphaXiv You can post questions and comments directly on top of any arXiv paper by changing arXiv to alphaXiv in any URL!

Richard Feynman on government and freedom ✍️ I hope for freedom for future generations-- freedom to doubt, to develop, to continue the adventure of finding out new ways of doing things, of solving problems. We are not so smart. We are dumb. We are ignorant. We must maintain an

In 1890, Henri Poincaré proved the non-existence of the uniform first integral of the three-body problem and the sensitive dependence to initial conditions of its trajectories. Yet, stable solutions to it do exist and these are some of them.

During elastic collision, particles of equal mass simply exchange their velocities. en.wikipedia.org/wiki/Elastic_c… en.wikipedia.org/wiki/Inelastic…

As we move towards more powerful AI, it becomes urgent to better understand the risks in a mathematically rigorous and quantifiable way and use that knowledge to mitigate them. More in my latest blog entry where I describe our recent paper on that topic. yoshuabengio.org/2024/08/29/bou…

Many AI experts, including Mila’s Yoshua Bengio and Alondra Nelson Nelson, Harold F. Linder Professor at the Institute for Advanced Study (IAS), put forward the Manhattan Declaration after a High-level meeting at the United Nations General Assembly. Read the Declaration: mila.quebec/en/news/milas-…

BREAKING NEWS The Royal Swedish Academy of Sciences has decided to award the 2024 #NobelPrize in Physics to John J. Hopfield and Geoffrey E. Hinton “for foundational discoveries and inventions that enable machine learning with artificial neural networks.”

Academic ironies

"You're unlikely to discover something new without a lot of practice on old stuff." - Richard Feynman

A Survey paper of Small Language Models

🚨 New paper alert! [NeurIPS 2024 spotlight] 🚨 Trajectory Flow Matching with Applications to Clinical Time Series Modeling ⏳📈 With: Yuan Pu , Yuki Kawamura 川村祐貴 , Andrew Loza, Yoshua Bengio, Dennis Shung, Alex Tong 💻: github.com/nZhangx/Trajec… 📄: arxiv.org/abs/2410.21154 🧵👇

the transformer architecture in full detail

I am delighted to share our NeurIPS'24 paper "Bayesian Online Natural Gradient" arxiv.org/abs/2405.19681. BONG can be thought of as a version of the Bayesian Learning Rule (BLR), extended to the fully online setting. We combine several key ideas: implicit regularization to the

Time evolution of a complex function f: R→ C

Excited to share our NeurIPS 2024 Oral, Convolutional Differentiable Logic Gate Networks, leading to a range of inference efficiency records, including inference in only 4 nanoseconds 🏎️. We reduce model sizes by factors of 29x-61x over the SOTA. Paper: arxiv.org/abs/2411.04732

We often think of an "equilibrium" as something standing still, like a scale in perfect balance. But many equilibria are dynamic, like a flowing river which is never changing—yet never standing still. These dynamic equilibria are nicely described by so-called "detailed balance"

Nature Neuroscience Inferring neural activity before plasticity as a foundation for learning beyond backpropagation nature.com/articles/s4159…

Have you wondered why I've posted all these nice plots and animations? 🤔 Well, the slides for my lectures on (Bayesian) Active Learning, Information Theory, and Uncertainty are online now! They cover quite a bit from basic information theory to some recent papers 🥳

One of the most bizarre + complex talks at NeurIPS [1] was given by my fellow Yorkshireman, the inimitable Prof Karl Friston [2], explaining active inference to a room full of #AI people who are not really neuroscientists. This was interesting to me because 💡Karl Friston is a

🚨IT'S HAPPENING🚨 a woman who cannot speak now speaks through her brain, in real time, with her own voice. no typing, delay, or sounds made. just neural intent to streaming speech this isn’t prediction. it’s embodiment 1/