Jeff Clune
@jeffclune
Professor, CS, U. British Columbia. CIFAR AI Chair, Vector Institute. Sr. Advisor, DeepMind | ML, AI, deep RL, deep learning, AI-Generating Algorithms (AI-GAs)
I am thrilled to introduce OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Code. Led by @maxencefaldor and @jennyzhangzt, with @CULLYAntoine and myself. 🧵👇
This is a great summary of recent work in open-endedness and exploration!! Thanks @richardcsuwandi
We’re training AI on everything that we know, but what about things that we don’t know? At #ICML2025, the EXAIT Workshop sparked a crucial conversation: as AI systems grow more powerful, they're relying less on genuine exploration and more on curated human data. This shortcut…
We’re training AI on everything that we know, but what about things that we don’t know? At #ICML2025, the EXAIT Workshop sparked a crucial conversation: as AI systems grow more powerful, they're relying less on genuine exploration and more on curated human data. This shortcut…
Agreed 💯
Truly exciting achievements - current frontier AI models would be probably considered AGI 10 years ago, but AI goalposts always keep moving, and critics always downplay the achievements and emphasize imperfections (same old, same old :)
Starting in 10 minutes if you are around & interested. Packed house! Standing room only 🔥 🚀
I'll be giving a talk at this exciting workshop tomorrow at ICML and a panel after (with great panelists). Please stop by and say hello! #ICML2025
Honored to be in such esteemed company!
30 AI developers to follow: @AndrewYNg, @ylecun, @karpathy, @drfeifei, @yoshuabengio, @goodfellow_ian, @demishassabis, @ilyasut, @AlecRad, @jeremyphoward, @math_rachel, @chrisolah, @pabbeel, @SebastianThrun, @OriolVinyalsML, @wojbzaremba, @quaesita, @alliekmiller, @BernardMarr,…
I'll be giving a talk at this exciting workshop tomorrow at ICML and a panel after (with great panelists). Please stop by and say hello! #ICML2025
Join us on July 19th at @icmlconf, Vancouver, for the EXAIT Workshop— a full-day workshop on the role of exploration in AI today.
This paper, just like FER from @kenneth0stanley show that predictive capabilities, aren't equivalent to generalization, world model. We're still doing Ptolemaic epicycles - within distribution, models have predictive capabilities, but are still overcomplicated and brittle.
Can an AI model predict perfectly and still have a terrible world model? What would that even mean? Our new ICML paper formalizes these questions One result tells the story: A transformer trained on 10M solar systems nails planetary orbits. But it botches gravitational laws 🧵
Very interesting idea! A way to use Go-Explore to search trees of reasoning en route to a good answer. Humans could do this as well! Cool to see the First Return, Then Explore paradigm reimagined in this new setting. @AdrienLE @Joost_Huizinga @kenneth0stanley @joelbot3000
🚀 Thrilled to announce our new work: FR3E (First Return, Entropy-Eliciting Explore)! LLM reasoning with Reinforcement Learning often struggles with unstable and inefficient exploration. We propose FR3E, a structured framework to make it more robust & efficient.
I'm really excited to be presenting FMSPs at @RL_Conference later this year!
Thrilled to introduce Foundation Model Self-Play, led by @_aadharna. FMSPs combine the intelligence & code generation of foundation models with the curriculum of self-play & principles of open-endedness to explore diverse strategies in multi-agent games, like the one below 🧵👇
The first big part of my PhD research is out! Infinite thanks to @jeffclune and @cong_ml for all their guidance on this project
Thrilled to introduce Foundation Model Self-Play, led by @_aadharna. FMSPs combine the intelligence & code generation of foundation models with the curriculum of self-play & principles of open-endedness to explore diverse strategies in multi-agent games, like the one below 🧵👇