🔥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

Spread over five years, the #CAESAR competition focused on #encryption processes for digital information. Now the jury has selected TU Graz’s #ASCON #algorithm as a means of secure encryption for the internet of things. tugraz.at/en/tu-graz/ser… #IoT Computer Science & Biomedical Engineering @TUGraz

This is the image obtained by EHT of M87! You are looking at the first direct image of a black hole! #EHTBlackHole #RealBlackHole 🌀

Learning to Learn on Neuromorphic Hardware: frontiersin.org/articles/10.33… - Neuromorphic hardware (mixed-signal) - Transfer learning - Meta-plasticity - Spiking neural networks

We are releasing our App. for chord recognition! 🎉🎸🎹🤳 It's called Chord AI and it's real time. I wanted to play music but I got to be a nerd. Beautiful! Thanks Vivien Seguy for the hard work Link on apple store: apps.apple.com/fr/app/chord-a… Android version planned for January.

One-shot learning with spiking neural networks biorxiv.org/content/10.110…

🧠🖥️ Researchers led by Robert Legenstein and Wolfgang Maass have succeeded in modelling the emergence and interaction between neuron groups called "assemblies". This could lead to efficient new AI methods: tugraz.at/en/tu-graz/ser… Human Brain Project TU Graz

The spikes must flow! I'd love to announce a new paper with that title, but sadly the editors at Neuron changed it. Still v happy this paper is out because there's a revolution taking place in spiking neural networks and I want everyone to know about it. 👇🧵

We’ve acquired the MuJoCo physics simulator (mujoco.org) and are making it free for all, to support research everywhere. MuJoCo is a fast, powerful, easy-to-use, and soon to be open-source simulation tool, designed for robotics research: dpmd.ai/mujoco-blog

This is the only programming trick in ML. I have seen it get people riches and fame. Please learn it 🥺

A teaser from our paper with Franz Scherr on Self-supervised learning Through Efference Copies (S-TEC). It just got accepted at #NeurIPS2022

#NeuroAI: Could principles of embodied sensorimotor neuroscience unify and improve the various Self-Supervised Learning (SSL) methods? How could the brain self-supervise itself? We are happy to share our #NeurIPS2022 paper arxiv.org/abs/2210.09224 with Franz Scherr and Q. Guo🧵:

lol, draft of full GPT-4 paper with architecture and data details is already leaked on torrent😂 The vision component in the architecture is an interesting twist to plain ViT, and scaled up quite a bit! Link to the torrent for the curious: assets.speakcdn.com/assets/2703/bu…

When LLM's are prompted like "You are [Task]GPT, your purpose is to...", I always recall the scene of Westworld, where Dr. Ford talks to a newly awakened host (i.e. robot) that "it is the perfect instrument, the ideal partner...", shaping the robot's personality and behavior.

Westworld lured millions of us into a fantasy of human-like robots in a Wild West-themed world. Could it be real one day? Stanford/Google researchers just told us how they used AI to make "generative agents". Here's what they did 👇

Our latest work in nature today: #AlphaDev discovered a new faster sorting algorithm that we open sourced to the main C++ library for all developers to use. This is just the beginning of AI being used to find many more efficiencies in code in future dpmd.ai/alphadev-tw

Why are policy gradient methods typically so sample inefficient? Whenever a trajectory contains a reward, they credit all actions leading to it. But not all actions mattered! What if we could only credit actions that did matter? Our NeurIPS spotlight paper does just that 🧵️

Our research project SIMA is creating a general, natural language instructable, multi 3D game-playing AI agent. The agent can carry out a wide range of tasks in virtual worlds, making AI more adaptable, helpful & fun! dpmd.ai/sima-1

Mechazilla has caught the Super Heavy booster!

everyone today