Erwan Plantec
PhD candidate @real.itu.dk
Artificial Life | Complex Systems | Neural Networks
- Reposted by Erwan PlantecThe 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
- Reposted by Erwan PlantecWe 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
- Reposted by Erwan Plantec1 To predict the behaviour of a primate, would you rather base your guess on a closely related species or one with a similar brain shape? We looked at brains & behaviours of 70 species, you’ll be surprised! 🧵Thread on our new preprint with @r3rt0.bsky.social , doi.org/10.1101/2025...
- Reposted by Erwan PlantecHow do ant colonies perform computations? What kind of dynamical state allows them to do it? It has already been 30 years since my colleague, Octavio Miramontes, and I suggested that they, as liquid neural networks, might exploit critical states. Check: hal.elte.hu/~vicsek/down...
- Reposted by Erwan PlantecI don't know why, I just love these cell simulations :)
- Reposted by Erwan PlantecExtended Flow-Lenia paper is out in the ALife journal, with more experiments and insights! See 🧵 from 1st-author @eplantec.bsky.social for a summary. For a full overview of our research in Artificial Life, here is a talk I gave at the Demeco workshop at EPFL : youtube.com/watch?v=YYFr...
- Synthetic ecosystems that autonomously and continuously evolve in silico 👾 An Alifer dream we pursue with Flow-Lenia, a mass-conservative continuous CA ! If you are interested in complex systems with (1) emergent creatures and (2) intrinsic evolutionary dynamics, go check our new paper ! A 🧵
- FL allows to embed the CA parameters within its dynamics, making them localised, just like genomes ! This makes FL a unique system to simulate multi-species environments where rules can compete for mass, spread and undergo mutations: all the ingredients for evolution to emerge !
- We go larger scales in this work by simulating larger environments for longer ! We then use evolutionary activity metrics (see tinyurl.com/3chv37m9), a framework designed to analyse systems that evolve under intrinsic fitnesses, to evaluate the long-term evolutionary dynamics
-
View full threadWith @hamongautier.bsky.social , Mayelen Etcheverry, @bertchakovsky.bsky.social , @pyoudeyer.bsky.social and @clemmoulinfrier.bsky.social Go check our paper for more ! 📄 doi.org/10.1162/artl... 📄 www.arxiv.org/abs/2506.08569
