Matej Jusup

@matejjusup.bsky.social

• A PhD in multi-agent reinforcement learning at ETH Zurich • A chess enthusiast - 2585 Elo @Chesscom) • Developed the first language model at Google DeepMind capable of playing the game at near super-human level (3200 Elo).

1/N I’ve long believed that board games should play a bigger role in AI evaluation. They naturally test strategic reasoning, long-term planning, adaptation—and they can’t be solved by brute force or memorization. Game Arena is transparent, replayable, and tests actual behavioral intelligence.

Kaggle@kaggle.com · last yr.

📢 Introducing Kaggle Game Arena: a new, open benchmark platform where top AI models compete in complex, strategic games in streamed match-ups. We're charting new frontiers for trustworthy AI evaluation and it begins with chess — a classic proving ground for system intelligence.

Looking forward to speaking at the ML Pub Club on June 3rd! I'll discuss how, during my time at DeepMind, we taught LLMs to play chess at a GM level and the broader implications for strategic AI. If you're in Zagreb, join us at Mažuranićev trg 13 at 6 PM! More info & RSVP: lu.ma/erjji5it

ML Pub Club #22: Superhuman Planning with LLMs · Luma

What happens when a chess champion meets cutting-edge AI? Join us for an evening with Matej Jusup, as he unpacks how large language models (LLMs) can go from…

lu.ma

A paper from my time at Google was accepted for a spotlight presentation at ICML! In “Mastering Board Games by External and Internal Planning with Language Models”, we show how language models can achieve grandmaster-level play using a search budget on par with humans. arxiv.org/abs/2412.12119

Mastering Board Games by External and Internal Planning with Language Models

Advancing planning and reasoning capabilities of Large Language Models (LLMs) is one of the key prerequisites towards unlocking their potential for performing reliably in complex and impactful domains...

arxiv.org

Hive (and all of its expansions) has been added to OpenSpiel! 🎉🤩🐝🐜🕷️🐞🦟🪲 From Gen42: "Hive is an award-winning board game with a difference. There is no board. The pieces are added to the playing area thus creating the board. As more and more pieces are added the game becomes a fight to ... 🧵1/5

Bild

Sim agents are key for developing autonomous systems for safety-critical systems, like self-driving cars. We're open-sourcing sim agents that achieve a 99.8% success rate with < 0.8% failures on the Waymo Dataset. These agents are built through scaling self-play.

We've released our lecture notes for the course Probabilistic AI at ETH Zurich, covering uncertainty in ML and its importance for sequential decision making. Thanks a lot to @jonhue.bsky.social for his amazing effort and to everyone who contributed! We hope this resource is useful to you!

Jonas Hübotter@jonhue.bsky.social · 2y ago

I'm very excited to share notes on Probabilistic AI that I have been writing with @arkrause.bsky.social 🥳 arxiv.org/pdf/2502.05244 These notes aim to give a graduate-level introduction to probabilistic ML + sequential decision-making. I'm super glad to be able to share them with all of you now!

LLMs Mastering Board Games: ZurichNLP Meetup - Feb 20th! Excited to share insights from my student research at Google DeepMind at the upcoming ZurichNLP meetup! I'll present how we achieved high-level play in board games using LLMs with a search budget comparable to human chess grandmasters.

Bild

I've been talking about writing this paper to anyone who would listen since 2020. I bombed a bunch of job talks trying to convince companies to work on this. It's so nice to finally just be able to say, yes, self-play RL in a diverse world gives you immense capabilities arxiv.org/abs/2502.03349

Robust Autonomy Emerges from Self-Play

Self-play has powered breakthroughs in two-player and multi-player games. Here we show that self-play is a surprisingly effective strategy in another domain. We show that robust and naturalistic drivi...

arxiv.org

Demis Hassabis, James Manyika, and I wrote up an overview of the AI research work & advances across Google in 2024 (Gemini, NotebookLM, robotics, ML for science, & advances in responsible AI+more). 🎊 Given it a read or paste it into NotebookLM to listen, if you prefer! blog.google/technology/a...

2024: A year of extraordinary progress and advancement in AI

As we move into 2025, we’re looking back at the astonishing progress in AI in 2024.

blog.google

I was honored to present our demo on “Mastering Chess With Language Models” at the @GoogleDeepMind booth at @NeurIPSConf right before an inspiring talk by Jeff Dean Thanks to everyone who dropped by and made it a memorable session! ♟️

Bild