Yali Du @NeurIPS San Diego✈️
@yalidux
Followers
2K
Following
371
Media
33
Statuses
227
Researcher in reinforcement learning/multi-agent cooperation. @turinginst @KingsCollegeLon Ex at @AI_UCL @UCLCS
London, UK
Joined September 2016
@ZiyanWang98 #402
https://t.co/eP3PCDdofW
#3603
https://t.co/SNXwsrTDoz
#4005
https://t.co/SxRmQFjEie
#1006
https://t.co/H3aI38U2R9 Abstract Counterfactuals for Language Model Agents https://t.co/8sj5d4WOCR
1
1
5
Cooperative AI Lab is heading to NeurIPS! Shuqing, @ZiyanWang98 Hao Liang and myself will be in San Diego, while Edoardo Pona will be in Mexico City. All posters are on Wednesday — don’t miss out! 🚀 See you there!
4
2
27
This bug unintentionally helps flag malicious reviews, but it may also suppress constructive debate.
0
0
4
This seminar will explore the future of human-AI collaboration and how to optimize agentic AI systems to automate intelligently while augmenting meaningfully. A huge thank you to Dr. Yang for taking the time to share her insights with us. Looking forward to seeing you there! 🚀
2
0
4
Agentic AI Frontier Seminar Excited to welcome Dr @Diyi_Yang from Stanford University for an online talk this Friday, 28 Nov. Title: Automation or Augmentation? Optimizing Human-AI Collaboration Time: 9-10am PT, 28/11 Join us via Zoom — link https://t.co/wkSe2vcJFt🎙️
3
2
23
DAI 2025 London has wrapped up at KCL on 21-24 Nov! 🎉 https://t.co/TnJtbPyBdB Thanks to the amazing keynotes! Hope to see you another time!
0
1
8
I will be attending EMNLP in Suzhou. Welcome to chat with my collaborators and me! @kclnlp
9 works from KCL NLP has been accepted to #COLM2025 & #EMNLP2025 ✨ From LLM benchmarking to cognitive distortion detection, reasoning, distillation, reinforcement learning, and more. @yan_hanqi
@HYannakoudakis
@yalidux
@LinGui_KCL
@yulanhe
0
0
7
🚨 Call for Workshops and Tutorials @ the 7th Distributed AI conference (DAI 2025) at KCL in London. Deadline extended to 1 Sep.
🚨 Call for Workshops and Tutorials @ the 7th Distributed AI conference (DAI 2025) 🗓️ Deadline: August 15, 2025 📍 Nov 21–22 | London, UK 🔗 https://t.co/Hwd4Eu2Dp9
#DAI2025 #AI #MAS #MachineLearning #ReinforcementLearning
0
2
3
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 🤩
1
1
20
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.
5
43
272
🔥 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
0
3
11
Attending #AAMAS this week! Richard, Lukas, and Ziyan are also here. Feel free to connect! Detroit@#AAMAS2025 💪💪
0
0
14
Drs @cbentl2 and @yalidux have been awarded grants by @AISecurityInst 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!👏 https://t.co/sMK5lFbMtq
0
3
7
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 https://t.co/Ea8CtLWiwT
0
0
3
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! @ZhiyuanCS @Xidong_Feng @CanyuChen3 @PangWeiKoh Yilun, Min-Yen, Jiaying , Nouha, Arman, Bryan
Although the ICLR main conference is coming to an end, we are excited to invite you to the Reasoning and Planning for LLMs Workshop, which will be held all day on Monday, April 28. We are honored to host an outstanding lineup of keynote speakers and panelists from Meta, OpenAI,
0
1
3
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 @AISecurityInst
We've funded 20 new research projects to enhance AI security in critical infrastructure ⚡ Our Systemic AI Safety Grants Programme, announced at the Seoul AI Summit, has awarded up to £200,000 seed grants to projects tackling AI risks 🧵👇
1
0
12
🚀 Together with @jzl86 , 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! 👇 https://t.co/fKdO0TfQTQ
github.com
SocialJax: sequential social dilemma environments. Contribute to cooperativex/SocialJax development by creating an account on GitHub.
1
1
30
The next seminar is this Friday (Mar 28) and starts at 12pm midday UK time! @yalidux from Kings College London is going to talk about "Towards cooperative AI"! https://t.co/WIZ32HhI2G This seminar is hybrid. 👉 https://t.co/9pUy2RWAy1
ucl.zoom.us
Zoom is the leader in modern enterprise cloud communications.
0
2
5