🔥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

Curiosity-driven exploration of Flow-Lenia universes 🔍First discoveries in our ongoing Alife project 🔬We use curiosity-driven autotelic algorithms as AI scientists 🤖 exploring the space of Flow-Lenia environments 🚀We aim to find environments that self-organize, from

So in short, we're interested in finding which environments can give rise to forms of Alife and AI from the very ground up, from very low-level artificial physics and chemistry Our approach is using curiosity-driven AI to help us find these environments

🔬Exploring complex systems has never been this easy! ADTool comes with multiple examples showing how to use Intrinsically Motivated exploration mechanisms for: - cellular automata🦠 - physics simulation engines🧲 - protein docking🧬 ... It's now open-source, give it a try😉

Symbolic dynamics bridges from #DynamicalSystems to computation/ #AI! In our #NeurIPS2024 (NeurIPS Conference) paper we present a new network architecture, Almost-Linear RNNs, that finds most parsimonious piecewise-linear representations of DS from data: arxiv.org/abs/2410.14240 1/4

We are very excited to announce Kinetix: an open-ended universe of physics-based tasks for RL! We use Kinetix to train a general agent on millions of randomly generated physics problems and show that this agent generalises to unseen handmade environments. 1/🧵

For Science Magazine, I wrote about "The Metaphors of Artificial Intelligence". The way you conceptualize AI systems affects how you interact with them, do science on them, and create policy and apply laws to them. Hope you will check it out! science.org/doi/full/10.11…

warm Systems as a Platform for Open-Ended Evolutionary Dynamics arxiv.org/abs/2409.01469

Everything you love about generative models — now powered by real physics! Announcing the Genesis project — after a 24-month large-scale research collaboration involving over 20 research labs — a generative physics engine able to generate 4D dynamical worlds powered by a physics

Automated Search for ALife with VLM as representation space🌌 Cant wait for when we can talk to the CA creatures!

The version of record is out in eLife - the journal - elifesciences.org/articles/92683 - the hard work of Mayalen Etcheverry , @Clement_MF_ , Pierre-Yves Oudeyer as we try to develop tools to characterize the behavior space of gene-regulatory networks (and pathways more broadly). For the interactive version of

Can we study gene regulatory networks from a behavioralist perspective, as "agents" navigating in transcriptional space? Our new paper at eLife - the journal explores this approach combining Michael Levin 's vision on basal cognition with Inria Flowers team 's automated discovery algorithms.

Here's my talk on open-endedness, curiosity-driven AI and automated search in artificial life Topics: + What is open-endedness? Is this a subjective notion? + The role of curiosity in open-ended cognitive development + Explanation of the concept of autotelic AI + Short

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

What Is Life? Evolution as Computation By Blaise Agüera (@blaiseaguera.bsky.social) Just finished reading this thought-provoking little book. Highly recommended if you’re interested in artificial life, self-replicating computer code, how it all relates to evolution, chaos, and AI. mitpress.mit.edu/9780262554091/…

Tim Rocktäschel’s keynote talk at #ICLR2025 about Open-Endedness and AI. “Almost no prerequisite to any major invention was invented with that invention in mind.” “Basically almost everybody in my lab at UCL and at DeepMind have read this book: Why Greatness Cannot Be Planned.”

i just got an art grant from the council for the arts at MIT! *Tangible Dreams* will let visitors experiment and play with a physical neural network generating images real-time—by twisting knobs and switches, by reconnecting nodes together Arts at MIT

Full time research position open at Google! Interested in how complexity emerges in AI? Join our Paradigms of Intelligence Team as a Research Scientist! We're exploring alternative paradigms beyond current trends. Focus on modularity & reuse. Apply now: shorturl.at/xdswe

Here are two cool simulations of Flow-Lenia, a continuous cellular automaton with two distinct features: 1. Mass conservation - sum of all activations is constant through time 2. Localized update rules - enables simulations with differently behaving matter on the same grid

🚀 New preprint! ARC-NCA shows how Neural Cellular Automata —incl. memory-rich EngramNCA—crack tasks from the ARC-AGI benchmark, hitting GPT-4.5-level accuracy at a fraction of the cost. 🌱🤖 Web: etimush.github.io/ARC_NCA/ Preprint: arxiv.org/abs/2505.08778 #NeuroAI #AGI #CA #ALIFE

Lenia inception... instead of static kernel, what if we use a moving pattern as the kernel of another pattern?