Matej Jusup
@MatejJusup
Followers
181
Following
155
Statuses
87
A PhD in multi-agent RL at ETH Zurich and a chess enthusiast (2585 Elo @Chesscom) who developed an LM @GoogleDeepMind capable of playing the game (3200 Elo).
Zurich, Switzerland
Joined August 2020
The project I was quite honored to work on! ♟️ As a chess enthusiast, I was especially thrilled that an LLM equipped with an efficient MCTS reaches grandmaster-level strength with a search budget comparable to human players! 🤯
I'm excited to share a new paper: "Mastering Board Games by External and Internal Planning with Language Models" (also soon to be up on Arxiv, once it's been processed there)
5
40
358
RT @YiMaTweets: Also, many of my students and colleagues working in the field of AI feel that there is an unfair competition between the ac…
0
29
0
RT @Swarooprm7: Deepseek is great, but don't read too much into its lead on humanity's last exam benchmark by @DanHendrycks et. al The dat…
0
16
0
RT @polynoamial: Lots of vague AI hype on social media these days. There are good reasons to be optimistic about further progress, but plen…
0
109
0
John's talk is now available online!
Join John's talk to get insights on our paper on mastering board games with language models!
1
0
2
RT @behrouz_ali: Attention has been the key component for most advances in LLMs, but it can’t scale to long context. Does this mean we need…
0
607
0
Join John's talk to get insights on our paper on mastering board games with language models!
Title: Mastering Board Games by External and Internal Planning with Language Models Speaker: John Schultz, Deepmind Time: Jan 16, 2-3 pm EST Pls mark your calendar!
0
1
7
RT @ilijabogunovic: 10 days into the new year and some exciting ideas in LLM reasoning, rStar-Math: MCTS paired with a novel code-augmented…
0
1
0
I couldn't explain earlier why I sometimes experience increased disagreements upon presented facts while arguing with colleagues I highly value, but this perfectly captures the essence!
Ever wondered why presenting more facts can sometimes *worsen* disagreements, even among rational people? 🤔 It turns out, Bayesian reasoning has some surprising answers - no cognitive biases needed! Let's explore this fascinating paradox quickly ☺️
0
0
1
The first round was a hard-fought win against a much lower-rated opponent, but it is a testament to the increased playing quality since the recent global chess boom!
0
0
1
RT @alexandrabotez: Highly recommend playing classical chess. You are not allowed any electronics and generally play in silence for ~4 hour…
0
152
0
@ADarmouni that's a good catch. we didn't report the numbers but might compute them for the possible paper update early this year.
0
0
1