xuukyu's profile picture. cs, ai, open-endedness, emergence, representations, evolutionary optimization, artificial life.

i have a cool github username

austin, tx

kevin xu

@xuukyu

cs, ai, open-endedness, emergence, representations, evolutionary optimization, artificial life. i have a cool github username austin, tx

the book that got me interested in research last year is now out 😺

Excited to announce our MIT Press book “Neuroevolution: Harnessing Creativity in AI Agent Design” by Sebastian Risi (@risi1979), Yujin Tang (@yujin_tang), Risto Miikkulainen, and myself. We explore decades of work on evolving intelligent agents and shows how neuroevolution can…



kevin xu reposted

Excited to announce our MIT Press book “Neuroevolution: Harnessing Creativity in AI Agent Design” by Sebastian Risi (@risi1979), Yujin Tang (@yujin_tang), Risto Miikkulainen, and myself. We explore decades of work on evolving intelligent agents and shows how neuroevolution can…


kevin xu reposted

imo entire ai field switched from explore to exploit 2 yrs early


muon is good


saw the poster for this at ALIFE last month 😺

Excited to release our new work: Petri Dish Neural Cellular Automata pub.sakana.ai/pdnca We investigate how multi-agent NCAs can develop into artificial life 🦠 exhibiting complex, emergent behaviors like cyclic dynamics, territorial defense, and spontaneous cooperation!



kevin xu reposted

Thanks @MLStreetTalk for covering our ARC-NCA research and the #ALIFE2025 conference! Tim I'm so happy that we had a chance to meet earlier online and that I convinced you to come to @ALifeConf Keep up with the great work!

I was so excited when I saw that Neural Cellular Automata had been applied to the @arcprize - do you remember the famous self-repairing Gecko from @zzznah in 2020? I think ALIFE methods are an exciting path forward in AI research! This is @stenichele and Etienne Guichard at…



kevin xu reposted

The SONI session turned out great—shout out to the speakers & panelists @blaiseaguera, @risi1979, @SidneyPontesF & @emilyldolson for great talks & discussion on how we can rethink intelligence under the complexity lens. #ALife2025 @ALifeConf

EIiasNajarro's tweet image. The SONI session turned out great—shout out to the speakers & panelists @blaiseaguera, @risi1979, @SidneyPontesF & @emilyldolson for great talks & discussion on how we can rethink intelligence under the complexity lens. 

#ALife2025 @ALifeConf
EIiasNajarro's tweet image. The SONI session turned out great—shout out to the speakers & panelists @blaiseaguera, @risi1979, @SidneyPontesF & @emilyldolson for great talks & discussion on how we can rethink intelligence under the complexity lens. 

#ALife2025 @ALifeConf

Announcing SONI: Self-Organising Neural Intelligence(s) 🧠 An #ALife2025 special session to bring together AI & @ALifeConf communities to explore how self-organisation can contribute to neural paradigms of intelligence Call for papers sites.google.com/view/soni-alife |Deadline: May 4th

EIiasNajarro's tweet image. Announcing SONI: Self-Organising Neural Intelligence(s) 🧠

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

Call for papers sites.google.com/view/soni-alife |Deadline: May 4th


kevin xu reposted

Great conversations when presenting my poster on the Weight Transformer MetaNCA at ALife 2025! It's about learning local update rules for neural networks in order to be able to generate weights for arbitrary architectures ("architecture generalization").

mythosscience's tweet image. Great conversations when presenting my poster on the Weight Transformer MetaNCA at ALife 2025! It's about learning local update rules for neural networks in order to be able to generate weights for arbitrary architectures ("architecture generalization").

very happy to finally see this be done and i hope the results hold up

Reinforcement Learning (RL) has long been the dominant method for fine-tuning, powering many state-of-the-art LLMs. Methods like PPO and GRPO explore in action space. But can we instead explore directly in parameter space? YES we can. We propose a scalable framework for…



first conference has been great so far very fun to actually talk to people coming from only having done mostly independent research


Happy to say my first paper from my first semester working on research was accepted for presentation at ALIFE later this year in Kyoto. Hopefully more ambitious projects coming soon 😺


fair enough tbh if true. benchmark farming is like 50% for hype in the tech space and it would be bad if the most mainstream-used model had negative side effects from that

GPT-5 is the smartest model we've ever done, but the main thing we pushed for is real-world utility and mass accessibility/affordability. we can release much, much smarter models, and we will, but this is something a billion+ people will benefit from. (most of the world has…



a certain loud portion of the internet is so unfathomably against “ai” as a concept but as a social movement that was never rooted in legitimate argument very difficult to tell what the actual average person knows or thinks


United States Trends

Loading...

Something went wrong.


Something went wrong.