Scholar
Matej Jusup
Google Scholar ID: gXzUTZ8AAAAJ
Doctoral researcher at ETH Zurich
Citations & Impact
Citations
47
H-index
4
i10-index
2
Publications
9
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- - Published papers: 'Mastering Board Games by External and Internal Planning with Language Models' (ICML 2025), 'Ride-Sourcing Vehicle Rebalancing with Service Accessibility Guarantees via Constrained Mean-Field Reinforcement Learning' (arXiv preprint), 'Safe Model-Based Multi-Agent Mean-Field Reinforcement Learning' (AAMAS 2024)
- - Invited talks at multiple international conferences and meetups including CroAI ML Pub Meetup, ETH Zurich AI Center Associated Researchers Meetup, etc.
Research Experience
- - Student Researcher at Google DeepMind –– Gemini Post-Training Team, April 2024 – September 2024. Key Contribution: Co-developed the first LLM that plays chess at the world champion level - Gemini Chess Gem; First co-author of a spotlight paper at ICML 2025; Enhanced LLMs with search-based planning techniques to improve multi-step reasoning.
- - Machine Learning Researcher at Morgan Stanley
- - Senior Machine Learning Researcher leading a team of four at Cantab Predictive Intelligence, a tech startup
Education
- - PhD in Artificial Intelligence, ETH Zurich, supervised by Prof. Francesco Corman and Prof. Andreas Krause
- - MSc in Mathematical Statistics, University of Zagreb
- - Visiting Student, University of Bielefeld
- - BSc in Mathematics, University of Zagreb
Background
- Research Interests: Artificial Intelligence, Reinforcement Learning, Large Language Models (LLMs), Planning and Reasoning (with LLMs), Inference Time Methods, Sequential Decision Making, Multi-Agent Systems, Probabilistic Learning, Safe Learning, Data-Driven Algorithms, AI in Board Games, Mean-Field Control. Professional Area: Safe and Scalable Multi-Agent Reinforcement Learning.
Miscellany
- Silver medalist at the Croatian junior (under 20 years) chess championship; Ranked in the 99.999th percentile among over 100 million registered users on www.chess.com; Participated in the Gemini Chess Challenge hosted by Google DeepMind.
Co-authors