Jean-François Ton
@jeanfrancois287
Followers
1K
Following
6K
Media
29
Statuses
3K
ByteDance Seed @ByteDance_Seed | Senior Research Scientist working on LLMs | prev. @oxcsml @UniofOxford, @amazon, @apple, @bloomberg All opinions are my own
London, United Kingdon
Joined January 2015
📢 New paper on Multi-Agent LLMs 📢.Our new paper presents Multi-agent-guided Leader Policy Optimisation (MLPO). We train a single leader LLM that steers a team of off-the-shelf agents to solve tasks. Detailed thread below 👇 🧵.
1
4
20
RT @davidbau: Announcing a deep net interpretability talk series!. Every week you will find new talks on recent research in the science of….
youtube.com
We're a research computing project cracking open the mysteries inside large-scale AI systems. The NSF National Deep Inference Fabric consists of a unique combination of hardware and software that...
0
17
0
Generate videos in just a few seconds. Try Grok Imagine, free for a limited time.
419
692
3K
RT @StephenLCasper: OpenAI just claimed to introduce "malicious fine-tuning". In this thread, I'll give a list of academic works on tamp….
0
39
0
RT @GoogleDeepMind: What if you could not only watch a generated video, but explore it too? 🌐. Genie 3 is our groundbreaking world model th….
0
3K
0
RT @WenhuChen: MindLink from Skyworkd reported to achieve over 92% on MMLU-Pro with the dense 72B model. The results are insane. URL: htt….
0
7
0
RT @rob_cornish: I'm looking for talented and ambitious PhD students to join me at Nanyang Technological University Singapore to work on sa….
0
18
0
RT @PIN: How to Train a Leader: Hierarchical Reasoning in Multi-Agent LLMs.
arxiv.org
Large Language Models (LLMs) have achieved strong performance on a wide range of complex reasoning tasks, yet further gains are often possible by leveraging the complementary strengths of multiple...
0
1
0
RT @j_foerst: I recently had a lunch time conversation with a very senior AI researcher about how are multi-agent problems differ from sin….
0
17
0
RT @ai_nikolai: This week we will be presenting our work at #ACL2025. StateAct is like ReAct but better ;) @ShunyuYao12 . We discovered tha….
arxiv.org
Large language models (LLMs) are increasingly used as autonomous agents, tackling tasks from robotics to web navigation. Their performance depends on the underlying base agent. Existing methods,...
0
8
0
This has to be a joke, right? right?.
0
0
3
RT @lmthang: Right before #imo2025, together with colleagues from Mountain View, NYC, Singapore, etc, we all gathered at @GoogleDeepMind he….
0
40
0
RT @Alibaba_Qwen: >>> Qwen3-Coder is here! ✅. We’re releasing Qwen3-Coder-480B-A35B-Instruct, our most powerful open agentic code model to….
0
1K
0
RT @yusufma555: 🚀🚀🚀 Ever wondered what it takes for robots to handle real-world household tasks? long-horizon execution, deformable object….
0
92
0
RT @OwainEvans_UK: New paper & surprising result. LLMs transmit traits to other models via hidden signals in data. Datasets consisting only….
0
1K
0
RT @YIFENGLIU_AI: 1/6 We introduce RPG, a principled framework for deriving and analyzing KL-regularized policy gradient methods, unifying….
0
39
0
RT @ShehZaidi: Exciting and unique opportunity in our team at @GoogleDeepMind: we're hiring a laboratory scientist to build out a materials….
job-boards.greenhouse.io
0
1
0
RT @HolarisSun: 🚀 RL is powering breakthroughs in LLM alignment, reasoning, and agentic apps. Are you ready to dive into the RL x LLM front….
huggingface.co
0
12
0
RT @jeanfrancois287: 📢 New paper on Multi-Agent LLMs 📢.Our new paper presents Multi-agent-guided Leader Policy Optimisation (MLPO). We trai….
0
4
0
0
0
1
RT @pratyushmaini: At #ICML2025, I am super excited to introduce STAMP. This is a marriage b/w dataset inference & watermarking that finall….
0
15
0
8/ We have more ablations and insights in the paper, as well as a summary on the best practices. Thanks for reading, and big thanks to my co-authors: .Andrew Estornell,@FaaizTaufiq, Li Hang Link to paper below .📜
arxiv.org
Large Language Models (LLMs) have achieved strong performance on a wide range of complex reasoning tasks, yet further gains are often possible by leveraging the complementary strengths of multiple...
1
0
0