Antoine Cully

640 posts

Antoine Cully banner
Antoine Cully

Antoine Cully

@CULLYAntoine

Professor in Machine Learning and Robotics and Director of the Adaptive and Intelligent Robotics Lab (AIRL) at Imperial College London.

London, England Katılım Aralık 2011
218 Takip Edilen2.2K Takipçiler
Antoine Cully retweetledi
Jenny Zhang
Jenny Zhang@jennyzhangzt·
Thrilled to be featured in the first ALife Newsletter of the year! I share about how I got into open-endedness research, the inspiration behind my recent work, and how I think open-endedness fits into the future of AI and AI researchers
Jenny Zhang tweet media
English
2
8
35
4.1K
Antoine Cully
Antoine Cully@CULLYAntoine·
Excited to share our latest work with @k_mitsides and @maxencefaldor: DiCode - Dreaming in Code! Imagining new situations is a great way to learn, and when we are dealing with virtual environments we can do it in code: using LLM to generate new environments to help the training!
Konstantinos Mitsides@k_mitsides

Can large language models (LLMs) act as the imagination of a reinforcement learning (RL) agent? We found that if you let an LLM "dream" - not by hallucinating pixels, but by writing executable Python code - it can create an open-ended curriculum that drives progress in complex, long-horizon worlds. Introducing Dreaming in Code (DiCode). 🧵👇

English
0
3
22
1.5K
Antoine Cully
Antoine Cully@CULLYAntoine·
This is an outstanding PhD-opportunity if you are interested in open-endedness and video games! Check it out!
Roberta Raileanu@robertarail

📢 New PhD Position 📢 We (@_rockt, @borruell, and I) are looking for a PhD student to work at the intersection of open-endedness and game design. The student will be part of the @UCL_DARK lab and funded by @iconicgamesio and UCL. See this doc for a more detailed description of the research direction and candidate expectations: docs.google.com/document/d/1Z7… To apply, please complete this form by January 15: docs.google.com/forms/d/16JGfS…

English
1
2
9
2.5K
Antoine Cully retweetledi
Iconic Interactive
Iconic Interactive@iconicgamesio·
Can a game really talk back? We built The Oversight Bureau to find out : a narrative experiment powered by our on-device AIs. The public demo is live today. Will you challenge The Bureau? store.steampowered.com/app/4005360/Th…
English
1
2
9
6K
Antoine Cully retweetledi
ALICE Workshop
ALICE Workshop@alice_workshop_·
Of first set of guest speakers are set 🧑‍🔬 - Alyssa Adams - Alexander Mordvintsev @zzznah - Angel Goñi-Moreno - Eric Medvet @EricMedvetTs - Kyrre Glette @kyrre2000 - Stefano Nichele @stenichele - Susan Stepney
ALICE Workshop tweet media
Norsk
0
8
31
3.8K
Antoine Cully retweetledi
ICARL
ICARL@ic_arl·
A new season of the ICARL seminars begins🥳🥳 This year we are kicking off with @max_nlp from @GoogleDeepMind! Max will be sharing his insights through various works with LLMs and RL. 🗓️Oct 17th, 5 pm 📍Huxley Building, Imperial College London, room 311 @ICComputing This is a Hybrid seminar co-hosted with @ICDoCSoc with a caloric-rewarded in-person networking session as usual. This event is also open to non-Imperial attendees! Register here: eventbrite.com/e/imperial-col…
English
1
3
7
1.1K
Antoine Cully
Antoine Cully@CULLYAntoine·
Excited to present our latest paper "Time to Play"! It's the kind of paper I love: a simple idea that shows some powerful results. What if all the energy of children, which progressively decreases as they grow up, is an essential part of the curriculum? Turns out that's the case!
Paul Templier@p_templier

What if your robot was just missing a childhood to walk faster? Introducing SMOL, for Scaling Mechanical Output over Lifetime, tomorrow (Oct 9) at #ALIFE25! with @CULLYAntoine, @hannah_janmo, and D. Labonte from @EvoBiomech

English
0
1
5
742
Antoine Cully retweetledi
Stephen James
Stephen James@stepjamUK·
As a newly appointed 𝗔𝘀𝘀𝗶𝘀𝘁𝗮𝗻𝘁 𝗣𝗿𝗼𝗳𝗲𝘀𝘀𝗼𝗿 at @imperialcollege, I'm thrilled to announce the 𝗦𝗮𝗳𝗲 𝗪𝗵𝗼𝗹𝗲-𝗯𝗼𝗱𝘆 𝗜𝗻𝘁𝗲𝗹𝗹𝗶𝗴𝗲𝗻𝘁 𝗥𝗼𝗯𝗼𝘁𝗶𝗰𝘀 𝗟𝗮𝗯 (𝗦𝗪𝗜𝗥𝗟) at 𝗜𝗺𝗽𝗲𝗿𝗶𝗮𝗹 𝗖𝗼𝗹𝗹𝗲𝗴𝗲 𝗟𝗼𝗻𝗱𝗼𝗻. 𝗦𝗮𝗳𝗲 𝗪𝗵𝗼𝗹𝗲-𝗯𝗼𝗱𝘆 𝗜𝗻𝘁𝗲𝗹𝗹𝗶𝗴𝗲𝗻𝘁 𝗥𝗼𝗯𝗼𝘁𝗶𝗰𝘀 𝗟𝗮𝗯 (𝗦𝗪𝗜𝗥𝗟) (swirl.uk) is a new research lab focused on the intersection of safety and intelligence in next-generation robotics. We're hiring exceptional PhD students who are passionate about pushing the boundaries of robot learning. 𝗪𝗵𝗮𝘁 𝗺𝗮𝗸𝗲𝘀 𝗦𝗪𝗜𝗥𝗟 𝘂𝗻𝗶𝗾𝘂𝗲? We operate at the exciting convergence of: • Online & offline reinforcement learning • Imitation learning & human demonstrations • Sample-efficient learning methods • Whole-body and soft robotics systems We're 𝗹𝗼𝗼𝗸𝗶𝗻𝗴 𝗳𝗼𝗿 𝗽𝗿𝗼𝘀𝗽𝗲𝗰𝘁𝗶𝘃𝗲 𝗣𝗵𝗗 𝘀𝘁𝘂𝗱𝗲𝗻𝘁𝘀 interested in: • Developing safe exploration algorithms for robotic systems • Creating sample-efficient learning methods that minimize real-world trials • Building foundation models for robotics with safety guarantees • Advancing soft robotics and compliant human-robot interaction • Bridging theory and practice in embodied AI Why now? As robots become more capable and work closer with humans, we need systems that are both intelligent enough to handle complex tasks 𝗔𝗡𝗗 safe enough for real-world deployment. Traditional approaches treat safety and intelligence as competing priorities, we believe they're synergistic. If you're a motivated researcher who wants to develop the theoretical foundations and practical algorithms for tomorrow's safe, intelligent robots, I'd love to hear from you. Want to join? Apply via swirl.uk
English
13
14
178
16.5K
Antoine Cully
Antoine Cully@CULLYAntoine·
@edwardfhughes Good luck with your new adventure! Curious to see what is coming next for you!
English
0
0
2
261
Edward Hughes
Edward Hughes@edwardfhughes·
After almost 1000.1 (binary) years, today was my last day at Google DeepMind. What a privilege it has been to work alongside such inspiring and talented colleagues on the quest to solve intelligence. Now the time is right for me to embark on a new open-ended adventure!
Edward Hughes tweet media
English
31
4
647
66.2K
Antoine Cully
Antoine Cully@CULLYAntoine·
Almost exactly 10 years after joining @imperialcollege as a Postdoc, I am honoured to announce that I am now Professor in Machine Learning and Robotics! 👨‍🎓 🤖 My fantastic team found the best gift to celebrate this special occasion!
Antoine Cully tweet media
English
31
6
239
11.5K
Antoine Cully
Antoine Cully@CULLYAntoine·
@jeffclune @imperialcollege Thanks Jeff! And thanks for being an inspiring colleague and collaborator! I always learn a lot from you each time we work together!
English
0
0
1
77
Antoine Cully retweetledi
Davide Paglieri
Davide Paglieri@PaglieriDavide·
"Always reasoning" (ReAct) isn't optimal for LLM agents! 🧠 Our new paper identifies a "Goldilocks" effect: planning too frequently or not enough degrades performance. We show how to train agents to learn to dynamically allocate test-time compute when needed for best results. 👇
Bartłomiej Cupiał@CupiaBart

Almost all agentic pipelines prompt LLMs to explicitly plan before every action (ReAct), but turns out this isn't optimal for Multi-Step RL 🤔 Why? In our new work we highlight a crucial issue with ReAct and show that we should make and follow plans instead🧵

English
2
19
90
11.8K

Keşfet

@k_mitsides @maxencefaldor @ic_arl @max_nlp @zzznah @EricMedvetTs @kyrre2000 @stenichele