Lightnews — Scholar-powered news

Iliya Zhechev

@ilzhechev.bsky.social

14 followers 25 following 3 posts

🧠AI 🦎 Emergence 🦠 Cellular Automata

Posts Media Videos Starter Packs

Reposted by Iliya Zhechev

Harald M. Ludwig @haraldludwig.bsky.social · 2d

First day of the @alife2025.bsky.social conference was fun! Our @eralife.bsky.social workshop was a success. Thanks to @risi.bsky.social, @bhartl.bsky.social, and @zzznah.bsky.social for their talks! After we checked out the local cuisine with @ilzhechev.bsky.social.

#ALIFE25 #ERA

1 2

Reposted by Iliya Zhechev

Harald M. Ludwig @haraldludwig.bsky.social · 8d

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

Emerging Researchers in Artificial Life @eralife.bsky.social · 13d

Join ERA Workshop Lightning Talks⚡6th Oct!

Present your work!
This is your moment to shine ✨ (and maybe blow a few minds 💥).

It doesn’t have to be finished work: project, idea, early results, or just something you want to share! 🌱

👉 Sign up here and grab a slot:
🔗 forms.gle/99jR5Kazgq66...

#ERA

ERA Workshop Lightning Talks Registration

Event Timing: 06.10.2025 (during the ALIFE 25 conference) Contact us at [email protected]

forms.gle

5 6

Iliya Zhechev @ilzhechev.bsky.social · Mar 25

Thanks to my co-author @haraldludwig.bsky.social for this collaboration! Check out the poster: 🔗 drive.google.com/file/d/12lJF...

Iliya Zhechev @ilzhechev.bsky.social · Mar 25

Effectively implementing an embodied form of autoencoding as coined by @stenichele.bsky.social.

The system demonstrates robust generalization between training and validation sets, suggesting reliable learning of the underlying computational principles.

1 1 2

Iliya Zhechev @ilzhechev.bsky.social · Mar 25

🪧 Last week we presented a poster at #SSCI2025: "Embodied Autoencoding Through Neural Cellular Automata".

We show that NCAs can learn to compress, transport, and reconstruct complex patterns through extreme spatial bottlenecks using only local interactions.

Picture of the Embodied Autoencoder Poster

1 4