Milton

Code monkey @RoboEvoArtLab

[Milton @miltonllera]

@patrickmineault @EIiasNajarro @JakobSchauser @risi1979 Yes! Big fan of Stan's work. Good to see it finally out.

[Milton @miltonllera]

New research out — A developmental model with morphogenetic scaffoldings to guide self-organisation: a single model, many grown patterns. The memory-compute trade-off but in self-organizing systems.

A collab featuring @EIiasNajarro @JakobSchauser and @risi1979 and yours truly

[Sebastian Risi @risi1979]

We're excited to announce GAME: Adversarial Coevolutionary Illumination with Generational Adversarial MAP-Elites ⚔️

Game is a new coevolutionary QD algorithm that illuminates both sides of an adversarial problem by alternating the evolution of solutions on one side that maximize the adversarial fitness against fixed opponents from the other side. If you have any tasks requiring adversarial training, check it out!

Blog: https://t.co/4dcd0fscwb
Paper: https://t.co/X9NudMCOFL

[Milton @miltonllera]

@dileeplearning @carlkolon It doesn't because to do that you need to establish which learning/search algorithm you are talking about.
If evolution were random mutations only would it scale with computation effectively as demanded by the bitter-lesson?

[Sebastian Risi @risi1979]

Biological development reliably builds complex structure from local cell interactions. How does it do it?

Beyond self-organisation itself, a substantial amount of organisational information is offloaded to initial conditions: maternal morphogen gradients and pre-patterns.

We model this with a Neural Cellular Automaton paired with a learned coordinate-based generator (SIREN), trained jointly. In our model, offloading information to initial conditions improves robustness, encoding capacity, and symmetry breaking. 🧬

Check it out:

https://t.co/btRRWTu2fn

[Elias Najarro @EIiasNajarro]

Self-organising systems often trade compute for memory. Here, we study how prepatterns give developmental systems some nice properties like symmetry breaking and memory capacity. Preprint in the 🧵

[Milton @miltonllera]

7/n Thus we show that the system can offer a valuable insight related to the functional utility of pre-patterns. Furthermore we can use it to replicate how embryogenesis combines growth and self-organisation.

Check out the preprint here: https://t.co/glZWLgmwzo

[Milton @miltonllera]

6/n Most surprisingly, we find that the pre-patterns are not used to directly approximate the target.

Indeed, even though more complex SIREN functions support better target generation, the initial patterns are not closer to the target when we increase complexity

[Milton @miltonllera]

@aran_nayebi If that is because you are collecting data so that you can create a theory that explain the patterns in the data then sure. But the point is that prediction on its own is not understanding. Does a baseball player understand the physics of ball throwing?

[Milton @miltonllera]

@aran_nayebi Also, I would wager most scientists would agree that understanding in this context is just the ability to intervene in the system in predictable ways, which is not something we can reliably do for ANNs. Otherwise there wouldn't be so much research on topics like alignment

[Milton @miltonllera]

@aran_nayebi Are people saying they are at odds? Or that Neuroscience has skewed heavily towards relying on one while neglecting the other?

[Milton @miltonllera]

We are happy to announce a new special session for ALIFE 2026: "ALife for Science and Engineering" with @EIiasNajarro @nisioti_eleni @BeneHartl

https://t.co/g3ohMi37hV

Note that special sessions at ALIFE are still part of the main proceedings

[hartl.bene @BeneHartl]

If you wonder what 9 interdisciplinary researchers did at the #alice2026 workshop last month, here is our novel take on symbiogenesis.

It was great fun and an inspiring experience!

[Stefano Nichele @stenichele]

What can a 70-year-old idea about digital organisms teach us about the future of AI and artificial life? 🧬💡

📄 Read our report: https://t.co/pIJjL1WaWT

#ArtificialLife #ComplexSystems #OpenEndedEvolution #ArtificialIntelligence #ALife

[Ettore Randazzo @RandazzoEttore]

Excited about self-organising sytems? Do you have a cool paper, either in the works or ready? Then consider applying to our Evolving self-organisation workshop at @GeccoConf ! Submission Deadline March 27
Also check out the amazing workshop website:
https://t.co/8gXc8CERWS