🔥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

❤️this! I dream of a computer that could do this after construction (I guess my brain is a bit like this, but SDK has a lot to be desired) developer.nvidia.com/blog/autodmp-o…

Are LLMs able to exhibit traits usually associated with ALife approaches? How can ALife perspectives help improve the current limitations of LLMs? Read more in this review that examines LLMs from a different angle, featuring some nice graphics along the way!

There's another work by Joachim Winther Pedersen with adaptable, trainable weights instead of fixed, scalar ones. "Each neuron in our network has a small matrix associated with it. ... making each neuron in the network into a tiny RNN." 4/ x.com/JoachimWinther…

Scaling laws in deep RL? Turns out that batch size, learning rate, and UTD (update-to-data) for getting the most efficient and scalable deep RL has predictable relationships. Checkout the analysis in new work by Oleg Rybkin & collaborators: arxiv.org/abs/2502.04327

We're excited to announce the first Evolving Self-organisation workshop at GECCO 2025! Submission deadline: March 26, 2025 More information: …-self-organisation-workshop.github.io

a bit more than a week left until the submission deadline for the Evoself workshop at Gecco! if you're working on anything at the intersection of self-organisation (emergent or designed) and evolution, submit your work soon and come join us in Málaga in July!

Excited to share our latest work: “Bio-Inspired Plastic Neural Networks for Zero-Shot Out-of-Distribution Generalization in Complex Animal-Inspired Robots” 🪲🦎 We show that Hebbian learning outperforms LSTM-based adaptation for real-world transfer. It even works without domain

We believe this work highlights the power of bio-inspired learning mechanisms in robotics. Our Hebbian networks are simple, lightweight, and robust and they generalize without requiring architectural complexity or training tricks. Paper: arxiv.org/abs/2503.12406 Project page with

I had so much fun working on this project. Who is going to take the challenge? People are running around saying AGI is here because we solved ARC-AGI. This is ARC-AGI++++;the absolute best reasoning systems in the world can't even begin solving most of puzzles in the benchmark...

Announcing SONI: Self-Organising Neural Intelligence(s) 🧠 An #ALife2025 special session to bring together AI & ALIFE Conference 2025 communities to explore how self-organisation can contribute to neural paradigms of intelligence Call for papers sites.google.com/view/soni-alife |Deadline: May 4th

Excited about self-organizing systems and their likely synergies with modern approaches to AI? Then submit to the SONI special session at #ALife2025

How can we collect the best stepping stones for open-ended discovery? I am excited to share Learned Quality-Diversity — a family of algorithms meta-optimized to be efficient stepping stone collectors! 📄: arxiv.org/abs/2502.02190 🌟: github.com/maxencefaldor/… work done in

Work done at the Astera Institute, astera.org Arxiv link: arxiv.org/abs/2503.19815… This is very much work in progress! More coming soon.

Why not try something different? Instead of using the activations in a layer of a neural network as the representation, like we have forever. How about using the *synchronization* between neurons over time instead? The behavior that results is quite different! Please take a look!

New Paper! Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents A longstanding goal of AI research has been the creation of AI that can learn indefinitely. One path toward that goal is an AI that improves itself by rewriting its own code, including any code

One promising direction is combining ideas from AlphaEvolve and the Darwin Gödel Machine. Imagine a self-referential system improving itself even at the lowest algorithmic levels at *scale* AlphaEvolve: deepmind.google/discover/blog/… Darwin Gödel Machine: arxiv.org/abs/2505.22954

Autopoiesis, autocatalytic sets, Ganti’s chemoton, Prigogine’s dissipative structures, Rosen’s (M, R)-systems... the notion of organizational closure is ubiquitous in all of them. Thus, can we unify them into a single framework?🤔 #complexitycat 🐈‍⬛./1 amahury.github.io/posts/review-c…

Milliardærer burde slet ikke findes‼️ Ingen har brug for at eje en MILLIARD kroner. Det er en pervers ophobning af rigdom hos en lille elite. Og det risikerer at flå vores demokrati og vores solidariske velfærdsland fra hinanden. Det er svært at forstå, hvor helt absurd rig