Sebastian Risi

📖 Free open-access edition: neuroevolutionbook.com

Excited to announce our book “Neuroevolution: Harnessing Creativity in AI Agent Design” by Sebastian Risi, Yujin Tang, Risto Miikkulainen, and myself. We explore decades of work on evolving intelligent agents and shows how neuroevolution can drive creativity in deep learning, RL, LLMs and AI Agents!

Kan naturens egen designproces videreudvikle AI?

En ny lærebog skrevet af ITU-professor @risi.bsky.social m.fl. udforsker feltet 𝙉𝙚𝙪𝙧𝙤𝙚𝙫𝙤𝙡𝙪𝙩𝙞𝙤𝙣, der kan ændre fremtidens kunstige intelligens.

"Grundideen er at efterligne, hvordan intelligens opstod i naturen."

Læs mere 👉 itu.dk/Om-ITU/Press...

ALICE workshop guest speakers

This year's ALICE guest speakers 🧑‍🔬

- Angel Goñi-Moreno - @angelgm.bsky.social
- Alyssa Adams - @alyssa-m-adams.bsky.social
- Alexander Mordvintsev
- Eric Medvet - @ericmedvetts.bsky.social
- Kyrre Glette - @kyrre2000.bsky.social
- Stefano Nichele - @stenichele.bsky.social
- Susan Stepney

Our (in the making) paper combining morphogenetic fields and neural cellular cellular automata with @miltonllera.bsky.social, Eleni Nisioti & @risi.bsky.social got a little award at @alife2025.bsky.social #ALife2025 💮✨

The SONI session turned out a great—shout out to the speakers & the panelists @emilydolson.bsky.social, @risi.bsky.social, @blaiseaguera.bsky.social & Sidney Pontes-Filho for great talks & discussion on how we can rethink intelligence under the complexity lens.

#ALife2025 @alife2025.bsky.social

If you are attending @alife2025.bsky.social next week you shouldn’t miss our workshop on Monday! Besides the opportunity to share an exciting idea or a (research) project you’ve been working on, we’ll have talks by @risi.bsky.social and @bhartl.bsky.social giving some career insights. 😮
#ALIFE2025

We are excited to announce the Artificial Life, Intelligence, Complexity & Evolution (𝗔𝗟𝗜𝗖𝗘) workshop. This first edition will be hosted in Copenhagen on the first week of February.

We will soon be announcing the guest speakers—Stay tuned!

Check our website for more information: aliceworkshop.org

We're excited to announce final program of the @alife2025.bsky.social SONI session
which will host a panel discussion with @blaiseaguera.bsky.social, @risi.bsky.social, @emilydolson.bsky.social & Sidney Pontes-Filho

Check out the full program: sites.google.com/view/soni-al...

See you in Kyoto ⛩️

The @alife2025.bsky.social deadline has been extended one week—new deadline May 11th 2025 23:59 AoE

Join us in Kyoto for #ALife2025 🎏

Self-Organising Neural Intelligence(s) Important dates: Submission Deadline: May 4th, 2025 Author Notification: TBA

Announcing SONI: Self-Organising Neural Intelligence(s) 🧠

An #ALife2025 special session to bring together AI & ALife communities to explore how self-organisation can contribute to neural paradigms of intelligence.

Call for papers sites.google.com/view/soni-al... |Submission deadline: May 4th

YouTube video by Worasuchad Haomachai [IROS25] Bio-Inspired Plastic Neural Nets for Zero-Shot Out-of-Distribution Generalization in Robots

www.youtube.com/watch?v=jnoa...
Bio-Inspired Plastic Neural Nets that continually adapt their own synaptic strengths can make for extremely robust locomotion policies!
Trained exclusively in simulation, the plastic networks transfer easily to the real world, even under various extra OOD situations.

First two days of the conference, if they didn’t change anything :) I’ll double check

Join us for the Evolving Self-Organisation workshop at #GECCO this year! Great chance to submit your favourite ideas concerning self-organisation processes and evolution, and how they interact.
Relevant for Alifers #ALife and anyone interested in #evolution, #self-organisation, and #ComplexSystems.

Organised by Ettore Randazzo, Eleni
Nisioti, Alex Mordvintsev, Joachim Winther Pedersen (@joachimwpedersen.bsky.social), Eyvind Niklasson and myself.

haha, yes. I was waiting to get the bluesky tags of everybody

We're excited to announce the first Evolving Self-organisation workshop at GECCO 2025!

Submission deadline: March 26, 2025

More information: evolving-self-organisation-workshop.github.io

This was a great collaboration driven by Timothee Anne and Noah Syrkis (@syrkis.com) w/ Meriem Elhosni, Florian Turati, Franck Legendre, and Alain Jaquier.

We also highlight critical limitations of current LLMs, including processing spatial visual information and formulating long-term strategic plans.

Beyond games, HIVE could be useful in other domains that require the coordinate of many agents, ranging from disaster response to urban planning.

Harnessing Language for Coordination: A Framework and Benchmark for LLM-Driven Multi-Agent Control Large Language Models (LLMs) have demonstrated remarkable performance across various tasks. A promising but largely under-explored area is their potential to facilitate human coordination with many ag...

A promising but largely under-explored LLM use-case is to facilitate human coordination with many agents. HIVE enables users to command up to several thousand units by delegating the tedious task of assigning behaviors and objectives to each unit through a LLM.

PDF: arxiv.org/abs/2412.11761

Ever wish you could coordinate thousands of units in games such as StarCraft through natural language alone?

We are excited to present our HIVE approach, a framework and benchmark for LLM-driven multi-agent control.

See you in Vancouver!

Thanks!

GROW-AI

I would like to join :) Here is a link to our GROW-AI project page that has relevant publications: sebastianrisi.com/grow-ai/

👋

Hi, I'm Joachim, I work as a postdoc on the Grow-AI project lead by @risi.bsky.social at ITU of CPH.
My PhD is titled "Bio-Inspired Approaches to Adaptive Artificial Agents" and since then, a lot of my time has revolved around Neural Developmental Programs:
watermark.silverchair.com/isal_a_00755...

This may sound odd, but game-based benchmarks are some of the most useful for AI, since we have human scores and they require reasoning, planning & vision

The hardest of all is Nethack. No AI is close, and I suspect that an AI that can fairly win/ascend would need to be AGI-ish. Paper: balrogai.com

Now that @jeffclune.bsky.social and @joelbot3000.bsky.social are here, time for an Open-Endedness starter pack.

go.bsky.app/MdVxrtD

Helpless infants are learning a foundation model Humans have a protracted postnatal helplessness period, typically attributed to human-specific maternal constraints causing an early birth when the brain is highly immature. By aligning neurodevelopme...

Do babies pretrain? www.cell.com/trends/cogni...

Hello Bluesky 🦋

We are the REAL Lab. We work on Robotics, Evolution and Artificial Life at #ITU in #Copenhagen

Follow, cite & subscribe for more news on our research 🤖