We got a great lineup of invited speakers so far, including @jfoerst.bsky.social @creativeendvs.bsky.social @rockt.ai @ozgursimsek.bsky.social @frabraendle.bsky.social imol2025.github.io/pages/speake...

Ever thought of joining DeepMind's RL team? We're recruiting for a research engineering role in London: job-boards.greenhouse.io/deepmind/job... Please spread the word!

Excited to share our latest work on EvoTune, a novel method integrating LLM-guided evolutionary search and reinforcement learning to accelerate the discovery of algorithms! 1/12🧵

Looking forward to representing the Open-Endedness research community with a keynote at ICLR 2025 in Singapore! 🚀

Join us for our next I-X seminar with Professor Tim Rocktäschel (UCL & Google DeepMind) titled "Open-Endedness and General Intelligence". 🕓 13:30 - 14:30 (GMT) 📅 Thursday, 3 April 📍 Hybrid (White City Campus / MS Teams) 🔗Register now: ix.imperial.ac.uk/event/i-x-se... @e-giunchiglia.bsky.social

My group @FLAIR_Ox is recruiting a postdoc and looking for someone who can get started by the end of April. Deadline to apply is in one week (!), 19th of March at noon, so please help spread the word: my.corehr.com/pls/uoxrecru...

Can AI agents adapt zero-shot, to complex multi-step language instructions in open-ended environments? We present MaestroMotif, a method for skill design that produces highly capable and steerable hierarchical agents. Paper: arxiv.org/abs/2412.08542 Code: github.com/mklissa/maestromotif

A few years back, AI researchers (Heinrich Kuttler, @egrefen.bsky.social and @rockt.ai to name a few) foresaw the importance of such an environment and created the NetHack Learning Environment, which allows for experimenting with RL agents.

Thank you for the kind words Jeff 🙏

Hi Open-Endedness community, what are everyone's favorite "the stepping stones don't look anything like the final product" real-world examples?

🚨BALROG leaderboard update This week's new entries on balrogai.com are: Llama 3.3 70B Instruct 🫤 Claude 3.5 Haiku✨ Mistral-Nemo-it (12B) 🆗 Github: github.com/balrog-ai/BA...

It’s been a crazy 2 years seeing so many amazingly talented researchers bring GENerative Interactive Environments alive in Genie 1 and 2. the future is agents in generative environments

Memorization is a big problem for diffusion models - you don't want them to output the actual training data! We present a new way to understand memorization from a dynamic systems perspective, and an effective mitigation method that does not require weight updates.

Thrilled to share Genie 2! Endless environments created by text or images, a key to open-ended/AI-Generating Algorithms. Genie 1 showed it's possible. 9 months later, Genie 2 shows jaw-dropping progress.🤯 Witness the magic of scale, again. 📈🚀 Thx to all team members @deep-mind.bsky.social!

Excited to reveal Genie 2, our most capable foundation world model that, given a single prompt image, can generate an endless variety of action-controllable, playable 3D worlds. Fantastic cross-team effort by the Open-Endedness Team and many other teams at Google DeepMind! 🧞

It's great to see BALROG featured on Jack Clark's Import AI newsletter! Check out what he had to say about it here: jack-clark.net And check out BALROG's leaderboard on balrogai.com

I really loved recording this since I don't know that much NAS. Colin is really good at connecting different strands within that research direction from the beginning to what's next 🌟

I'll also be giving a talk about this at the @neuripsconf.bsky.social workshop on "Language Gamification" in two weeks. Pop by if you're around! language-gamification.github.io

I'm hugely impressed by the quality of this paper, doubly so having tried and failed to do the engineering necessary to carry out a study like this. Laura is one of those people you can't miss: I've read every paper she's written and whenever a new one comes out it's at the top of my reading list.

Are there limits to what you can learn in a closed system? Do we need human feedback in training? Is scale all we need? Should we play language games? What even is "recursive self-improvement"? Thoughts about this and more here: arxiv.org/abs/2411.16905

@ucl-dark.bsky.social entered the stage! Thanks @lauraruis.bsky.social :)

This may sound odd, but game-based benchmarks are some of the most useful for AI, since we have human scores and they require reasoning, planning & vision The hardest of all is Nethack. No AI is close, and I suspect that an AI that can fairly win/ascend would need to be AGI-ish. Paper: balrogai.com

A little thread on NotebookLM and journalism uses. First and most obviously, if you’re a journalist working a specific beat and often referring to reports, research or inquiry evidence, NotebookLM is just an excellent way of keeping those reports in one place, and sharing them with collaborators /1

Excited to announce "BALROG: a Benchmark for Agentic LLM and VLM Reasoning On Games" led b UCL DARK's @dpaglieri.bsky.social! Douwe Kiela plot below is maybe the scariest for AI progress — LLM benchmarks are saturating at an accelerating rate. BALROG to the rescue. This will keep us busy for years.

New here (as nearly everybody), so I'd like to briefly introduce myself. I am working in natural language processing #NLP #NLProc – the field in computer science and linguistics that teaches computers to understand, generate, and process human language. (1/4)

The LLM parrot analogy is dead. Fantastic work by UCL DARK's @lauraruis.bsky.social on rigorously investigating whether LLMs learn reasoning from procedural knowledge during pretraining.

NeurIPS Conference is now Live on Bluesky! -NeurIPS2024 Communication Chairs

ive followed more awesome researchers here than I ever managed to on the other app. Starter packs are epic another gem go.bsky.app/MdVxrtD

Now that @jeffclune.bsky.social and @joelbot3000.bsky.social are here, time for an Open-Endedness starter pack. go.bsky.app/MdVxrtD

👋 Welcome @pcastr.bsky.social , another RL researcher 🤩🥳🙌

Proud to announce that Dr @samvelyan.com defended his PhD thesis titled "Robust Agents in Open-Ended Worlds" yesterday 🥳. Massive thanks to @togelius.bsky.social and Ilija Bogunovic for examining! As is customary, Mikayel received a personal mortarboard from UCL DARK.

The RL (and some non-RL folks) starter pack is almost full. Pretty clear that the academic move here has succeeded go.bsky.app/3WPHcHg

Google DeepMind is hiring Student Researchers in EMEA 👇

I created a starter pack of scientists in the European Laboratory for Learning and Intelligent Systems (ELLIS) 🇪🇺 Please ping me and I‘ll add you. go.bsky.app/Cihupkk

I made a starter pack with the people doing something related to Neurosymbolic AI that I could find. Let me know if I missed you! go.bsky.app/RMJ8q3i

New here? Interested in AI/ML? Check out these great starter packs! AI: go.bsky.app/SipA7it RL: go.bsky.app/3WPHcHg Women in AI: go.bsky.app/LaGDpqg NLP: go.bsky.app/SngwGeS AI and news: go.bsky.app/5sFqVNS You can also search all starter packs here: blueskydirectory.com/starter-pack...

Welcome!

Really excited to share publicly the Academic Engagement Programme that I've been building at the UK government's AI Safety Institute over the past few months! If you're a researcher and want to do hands-on academic collaborations with us - take a look here www.aisi.gov.uk/academic-eng...

Hello World!

Our team has been working hard to harness the power of AI to make software more secure.✨🔐 Today we are excited to share a major milestone: our AI agent has discovered its first real-world security vulnerability! Read here for more: googleprojectzero.blogspot.com/2024/10/from...

There seems to be some renewed interest in making this work in the ML/AI space, so I'm here as well 👋 Here's my latest blog post for good measure, about how diffusion models of images perform autoregression in frequency space: sander.ai/2024/09/02/s... When I write more, I'll share here as well!

Hello world!

🌳🏡 🏃‍♂️ 🧟‍♂️🏚️🔥 I have heard the grass is greener here.