Thanks for having me! Really enjoyed the discussion!

At NeurIPS Conference ? Here are two pre today. Learning to Discuss Strategically for Werewolf, in East Exhibit Hall A-C #1312 AM. Policy Learning from Books, in West Ballroom A-D #7108 PM. Oral Session 2B on RL in West Meeting Room 211-214 Check more here neurips.cc/virtual/2024/s…

Call for papers: International Workshop on Citizen-Centric Multiagent Systems (C-MAS 2025) - May 2025, Detroit, USA Explore MAS solutions prioritising citizens in challenges like energy decarbonisation, disaster response, and smart mobility. Details: sites.google.com/view/cmas25

🚀 Check out our special issue from Robotics and Computer-Integrated Manufacturingon “Generative Artificial Intelligence for Robotics and Smart Manufacturing”! 🤖✨📚 🔗 Read the full scope here:sciencedirect.com/special-issue/… #AI #Robotics #SmartManufacturing #Research #GenerativeAI

Couldn't agree more. "UK Research and Innovation funding in the UK fell under the previous government from 6,835 in 2018-19 to 4,900 in 2022-23". To give a concrete example (with my @UCLCS professor hat on): 4 out of 7 UCL DARK PhD students were funded by the Centre for Doctoral

A reminder to submit to the Citizen-Centric Multi-agent System workshop at AAMAS 2025 in Detroit USA. The AAMAS Conference Check details here.

Congrats to the new Turing Award winners! And to RL folks!

The next seminar is this Friday (Mar 28) and starts at 12pm midday UK time! Yali Du from Kings College London is going to talk about "Towards cooperative AI"! ucl.zoom.us/j/99748820264 This seminar is hybrid. 👉ucl-ellis.github.io/jt_csml_semina…

🚀 Together with Joel Z Leibo , we’ve released SocialJax — a suite of sequential social dilemma environments for multi-agent RL in JAX! Built for speed and scalability, SocialJax leverages JAX’s GPU acceleration to push MARL research forward. Check it out! 👇 github.com/cooperativex/S…

Excited to be one of the grantees. We're studying how LLM agents behave in social dilemmas under competitive pressure and investigate the systemic risks in multi-agent AI. Will they cooperate—or exploit? 🔬 More soon. #AISafety #MultiAgentAI AI Security Institute

Not at 🚀 #ICLR2025, but do not miss the 🔥𝐑𝐞𝐚𝐬𝐨𝐧𝐢𝐧𝐠 𝐚𝐧𝐝 𝐏𝐥𝐚𝐧𝐧𝐢𝐧𝐠 𝐟𝐨𝐫 𝐋𝐋𝐌𝐬 𝐖𝐨𝐫𝐤𝐬𝐡𝐨𝐩@ICLR2025, putting together by my amazing co-organisers on April 28! Zhiyuan Xidong Feng Canyu Chen Pang Wei Koh Yilun, Min-Yen, Jiaying , Nouha, Arman, Bryan

A great opportunity to join The Alan Turing Institute for the Research Associate position below, supervised by the wonderful Prof. Adam Sobey and in collaboration with me. Feel free to get in touch if you're interested! Application deadline: 26 May 2025 buff.ly/MrURhAZ

Drs Caitlin Bentley and Yali Du have been awarded grants by AI Security Institute to help create a more harmonious AI-enabled future.🤖 They’ll explore how to prevent deskilling in the modern maritime workforce and how AI models can work together better. Congrats!👏 kcl.ac.uk/news/kings-sci…

Attending #AAMAS this week! Richard, Lukas, and Ziyan are also here. Feel free to connect! Detroit@#AAMAS2025 💪💪

🔥 Chain-of-thought (CoT) reasoning in natural language is powerful—but inefficient. What if LLMs could reason in a compact continuous space instead? 🚀 Introducing CODI, our new paper on post-training LLMs for continuous reasoning via self-distillation. 💡TL;DR: CODI

We now know RL agents can zero-shot crush driving benchmarks. Can we put them on a car and replace the planning stack? We're hiring a postdoc at NYU to find out! Email me if interested and please help us get the word out.

ICML Board Election — If you receive the voting invitation, please consider voting for Yali Du. I’ve been actively contributing to the community in various roles (organising committees for NeurIPS 2024 & AAMAS 2023) and look forward to making more contributions in the future 🤩

Excited for the upcoming travels! 📍 7/13–7/19: Vancouver for ICML ICML Conference 📍 7/20–7/24: San Francisco (Apple Park/Cupertino) Look forward to meeting up! #ICML

🚨 Call for Workshops and Tutorials @ the 7th Distributed AI conference (DAI 2025) at KCL in London. Deadline extended to 1 Sep.

I will be attending EMNLP in Suzhou. Welcome to chat with my collaborators and me! KCL NLP