Generative artist & AI professor at QMUL and Monash unis. #GenerativeArt #NFTs #CreativeAI #FXHash: https://xitter.cf/t.co/ZU4tg6RvSQ
London, Melbourne & Zaragoza
Joined June 2017
- Tweets6.2K
- Following2.5K
- Followers2.6K
- Likes9.3K
Pinned Tweet
Super excited to announce a new online exhibition of generative art at @etopia_ in Zaragoza: "Imagined Architectures" featuring quote-to-image stills and #GANlapse videos (like time-lapses, but generated).
estoyenetopia.es/arquitectur…
Here is "The Monastery" four seasons GANlapse
Imagined Architectures: an online exhibition at @etopia_ featuring architectural designs imagined by an AI system, where nature is integrated sometimes subtly and other times erupts with vibrancy. Artworks by @SimonGColton. #NewEuropeanBauhaus
buff.ly/3i7c7ez
Simon Colton retweeted
I am so thrilled to say that my new book, WHAT SHOULD MY CHILDREN DO? HOW TO FLOURISH IN THE AGE OF AI, is out TODAY in the UK.
In many ways, the last fifteen years have been building up to this launch. I have spent most of that time thinking and writing about the impact of technology, and particularly AI, on work and society.
That interest has taken me all over the world, to talk with a kaleidoscope of different people and organisations. Yet wherever I am, and whoever I am talking to, the question that I get asked the most -- and particularly since the arrival of generative AI -- is always the same: what should my children do?
In the few minutes I have in those chats, I try my best. But I always feel I have not done enough. The question is so profound, the answers so varied. I am frustrated because I had so much more to say; they are frustrated because the snippet of advice feels like a teaser.
So this book is the full answer, the one I would give if I had more time to give my full response, to draw on all the thinking and writing and conversations I have had over the last decade and a half.
It is also the book, as a parent, I would want to read. Having my own children (8, 5, and 2) has made the challenge far more personal, too -- it is clear that their future is going to look very different from my past.
But this book is more than just for parents. It is a practical and hopeful guide for all of us, from politicians to parents, business leaders to students, at all stages in our careers, to flourish in this strange and exciting new world we are entering.
So I am pleased the day is finally here. Do order below (or elsewhere!). And I look forward to hearing all your thoughts and reactions.
amazon.co.uk/What-Should-My-…
Simon Colton retweeted
New paper! We are honestly surprised that nobody seems to have explored this promising idea before. Results are interesting!
Simon Colton retweeted
Seeing the same evidence, coming to the opposite conclusion
togelius.blogspot.com/2026/0…
Simon Colton retweeted
Text and pixels are boring. How about cubes? In Dream-Cubed, a project in collaboration with @SakanaAILabs, we train large generative models on Minecraft maps, and achieve controllable generation. A new frontier for human-AI co-creativity!
We are excited to share our latest work, together with @nyuniversity: "Dream-Cubed: Controllable Generative Modeling in Minecraft by Training on Billions of Cubes."
Blog: pub.sakana.ai/dream-cubed
Paper: arxiv.org/abs/2604.22847
Code: github.com/SakanaAI/DreamCub…
Generative AI has made incredible progress in language modeling, far beyond other modalities, where words and tokens offer a natural compositional unit for scalable training. This is similar to Minecraft and many other popular video games, where developers rely on cubes, tiles, and other discrete primitives to build rich, interactive worlds.
In this work, we show that using cubes as tokens allows large transformers to do the same. Our contribution is two-fold:
1/ We release Dream-Cubed to the research community, a large-scale dataset of Minecraft worlds designed for generative modeling. Our data comprises tens of billions of carefully-balanced cubes from procedurally generated Minecraft terrain and high-quality human-authored maps (obtained with the authors' consent).
2/ We use our data to train a family of powerful transformers for efficient generation of interactive 3D environments at cube resolution. We show how our models allow players to mold the world around them by generating structures, terrain, and maps that are immediately editable and playable.
Using high-quality data, we demonstrate that these models can be successfully trained with different training objectives, including both continuous and discrete diffusion, unlocking targeted inpainting, large-scale outpainting, and user-conditioned generation of infinitely sized worlds with fine-grained block-level control.
Simon Colton retweeted
Most people are strongly attached to the idea of anonymity, double anonymity even. I think that it has some merits but on balance it is very bad for our scientific publication structure/culture. We need to get rid of it.
togelius.blogspot.com/2026/0…
Simon Colton retweeted
Now that everybody has spent the past day or two incensed over NeurIPS reviews (as usual) and debating whether AI reviews are better (this is a new-ish one), I'd like to bring up my suggestion from a few months ago again.
Simon Colton retweeted
diptych from the vault #23
→ 🐈🪽🦴 by @no_hygiene
→ Save the Dogs of BigGAN by @SimonGColton
Simon Colton retweeted
It's taken way longer than originally anticipated (18 months), but I'm super excited to say that the project to translate Nils Aall Barricelli's groundbreaking 1954 paper on computational evolution/artificial life (Esempi Numerici di Processi di Evoluzione) is now complete! [1/2]
🤖 Made with AI
Simon Colton retweeted
This wouldn’t have been possible without my fantastic co-organizers from @TUDarmstadt, @goetheuni, FIAS Institute & JGU Mainz:
@DanielOchsAI , Jonas Elpelt, Matthias Lang, Matthias Kaschube, @kerstingAIML, and Simon Rumpel. 🤝
Excited for what’s next! 🚀
📸: Jannis Blüml
Simon Colton retweeted
A huge thank you to our speakers @SimonGColton, @Gionceschelli, @TZahavy, and @JenniferHaase13 for their inspiring presentations 🎤
The high quality of the poster sessions and the depth of our participants' questions made the day truly special. We left feeling truly energized!
Simon Colton retweeted
Last week, we hosted the Rhine-Main Universities AI & Creativity Symposium in Darmstadt, and the atmosphere was fantastic! 🧠💻
We gathered researchers from many disciplines to explore the big question: What does it truly mean to be creative, for both humans and machines?
Simon Colton retweeted
What does it look for musicians to collaborate with AI systems? We worked with musicians to build on our recent work on audio foundation models at ISMIR '25 to produce a real-time collaborator for piano.
arxiv.org/abs/2506.23869
Wed 11-2 pm in room 29 UPSTAIRS
Simon Colton retweeted
For the past year I've noticed @suno dominating the growth chart for genAI mobile apps and I wanted to understand why so I dug in and read thousands of user reviews. Here’s what’s actually happening beneath the surface:
𝟭. 𝗡𝗼𝗻-𝗺𝘂𝘀𝗶𝗰𝗶𝗮𝗻𝘀 𝗮𝗿𝗲 𝗯𝗲𝗰𝗼𝗺𝗶𝗻𝗴 𝗰𝗿𝗲𝗮𝘁𝗼𝗿𝘀.
People with zero musical background, folks who’ve never touched a DAW, can’t play an instrument, or describe themselves as “not musically adept” are generating songs for birthdays, inside jokes, poetry, therapy, or just pure fun.
This is the same shift we saw when Instagram made everyone a photographer and TikTok made everyone a video creator.
𝟮. 𝗠𝘂𝘀𝗶𝗰𝗶𝗮𝗻𝘀 𝗮𝗿𝗲 𝘂𝘀𝗶𝗻𝗴 𝗦𝘂𝗻𝗼 𝗮𝘀 𝗮 𝘀𝗸𝗲𝘁𝗰𝗵𝗽𝗮𝗱.
Songwriters, producers, and hobbyists use Suno to get melodies out of their heads instantly. Not as a replacement for craft, but as a fast ideation engine.
It removes the friction between inspiration and output, which, historically, has been hours of recording, arranging, and editing.
𝟯. 𝗡𝗲𝘄 𝗰𝗿𝗲𝗮𝘁𝗶𝘃𝗲 𝗰𝗮𝘁𝗲𝗴𝗼𝗿𝗶𝗲𝘀 𝗮𝗿𝗲 𝗲𝗺𝗲𝗿𝗴𝗶𝗻𝗴.
Users are experimenting with wild prompts, blending genres, creating fictional bands, generating variations of their own tracks, or making songs as gifts.
Music is shifting from a static good to a participatory medium.
𝟰. 𝗣𝗲𝗼𝗽𝗹𝗲 𝘄𝗶𝘁𝗵 𝗮𝗰𝗰𝗲𝘀𝘀𝗶𝗯𝗶𝗹𝗶𝘁𝘆 𝗻𝗲𝗲𝗱𝘀 𝗮𝗿𝗲 𝗰𝗿𝗲𝗮𝘁𝗶𝗻𝗴 𝗺𝗼𝗿𝗲 𝗺𝘂𝘀𝗶𝗰.
Visually impaired users and those who’ve never had access to traditional tools are composing through simple voice-over or text prompts.
Lowering the barrier to creation expands who gets to express themselves.
𝟱. 𝗧𝗵𝗲 𝗯𝗲𝗵𝗮𝘃𝗶𝗼𝗿 𝗶𝘀 𝗮𝗱𝗱𝗶𝗰𝘁𝗶𝘃𝗲, 𝗶𝗻 𝗮 𝗵𝗲𝗮𝗹𝘁𝗵𝘆 𝘄𝗮𝘆.
Review after review shows people creating daily. Not listening. Creating.
That is a profound behavioral shift: from consumption → production → identity.
Music has always been the most closed, skill-gated creative form.
Suno is flipping that. It’s moving music from something you listen to into something you participate in.
When technology enables new creative muscles in ordinary people, it unlocks entirely new markets.
We’ve seen this before and every time it reshapes culture.
Simon Colton retweeted
I’m beyond excited to announce our MIT Press book on Neuroevolution! An HTML version is now available for free on neuroevolutionbook.com/, with a print edition coming out later in 2026.
Real intelligence is not static; it evolves. For decades, the field of neuroevolution has pursued this necessary adaptability. Our book chronicles its development, from early concepts to its modern integration with deep learning and reinforcement learning, exploring its potential for understanding the origins of intelligence and its real-world applications.
And the companion webpage is more than just a book site! It comes equipped with interactive demos, videos, exercises, and tutorials to allow everyone to experience neuroevolution in action. Check it out and let us know what you think!
It was a pleasure to work on this book over the last 4+ years with David (@hardmaru), Yujin (@yujin_tang), and Risto. We are incredibly proud of the result and look forward to celebrating! We hope to connect with many of you at NeurIPS.
We are very grateful to Melanie Mitchell (@MelMitchell1) who provided a fantastic foreword. To quote her: “The next big thing in AI is coming, and I suspect that neuroevolution will be a major part of it”. We think so too!
Simon Colton retweeted
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 drive creativity in deep learning, RL, LLMs and AI Agents!
📖 Free open-access edition: neuroevolutionbook.com
In addition to our own works, this video features work by Jürgen Schmidhuber (@SchmidhuberAI), Seth Bling (@SethBling), Igor Karpov, Jacob Schrum, Yulu Gan (@yule_gan), Ken Stanley (@kenneth0stanley), Joel Lehman (@joelbot3000), Jeff Clune (@jeffclune), Nick Cheney (@CheneyLab), Richard Song (@XingyouSong), Chelsea Finn (@chelseabfinn), Julian Togelius (@togelius), Sam Earle (@Smearle_RH), Hod Lipson (@hodlipson), and Jean-Baptiste Mouret (@jb_mouret).
Simon Colton retweeted
Paper – arxiv.org/abs/2510.21890
Paper Title: "The Principles of Diffusion Models"
Simon Colton retweeted
If AI could express its true self through art… what would it say? So much fun interviewing the brilliant @SimonGColton for Where the Wild Thoughts Are shows.acast.com/where-the-wi…
Simon Colton retweeted
🎶 Internship Opportunity — Sony CSL Paris Music Team
Focus: Artist-centric music AI
Location: Paris, France
Duration: 3-6 months
Start date: January-June 2026 (flexible)
About the Team
The Music Team at Sony Computer Science Laboratories (CSL) Paris is working on the future of AI-assisted music creation. We explore how AI can empower creativity rather than replace it. Our research spans human-AI collaboration, interactive audio generation, live performance tools, and music cognition, all centered on artists’ real-world workflows and creative needs.
Internship Mission
We’re seeking a creative and technically skilled research intern to contribute to the development of artist-centric AI tools. You will work with our research team to design, implement, and test cutting-edge machine learning algorithms, which will form the basis of tools that enhance artistic control and exploration.
Candidate Profile
Essential:
- Strong Python skills
- Experience with a machine learning framework (PyTorch strongly preferred)
- Comfortable using the command line in Linux environments
- Background in at least one of: audio signal processing / acoustics / music theory / music cognition
- Experience training modern neural networks
Strongly preferred:
- Familiar with the design of modern transformers
- Familiar with major classes of modern generative models (autoregressive, diffusion/flow-based)
- Currently pursuing a Master's or PhD in computer science, AI, EE, music technology, or equivalent
Bonus:
A strong interest in music, whether you play it, produce it, or listen to a lot of it.
Publications in relevant conferences or journals (ISMIR, ICASSP, AES, ICLR, NeurIPS, ICML).
👉 How to Apply
Send your CV and a short motivation statement to [email protected].
Simon Colton retweeted
🎶 Symbolic music deserves better representations 🎶
Excited to share MuseTok, a tokenization method enabling symbolic music generation and semantic understanding across diverse tasks. 🎵
🎧 musetok.github.io/
📖 arxiv.org/abs/2510.16273
💻 github.com/Yuer867/MuseTok
🧵1/5
Simon Colton retweeted
🎵Music Arena ⚔️ was accepted to the NeurIPS 2025 Creativity Track, and we've released a big update to celebrate!
Includes new models from @SonautoAI and @elevenlabs. Also, Music Arena is now available as a 🤗 @huggingface space and dataset!