Matěj Kripner
Main Research Interests
reasoning in AI (especially in math), deep learning, reinforcement learning, automated theorem proving, Lean
Projects
Ph.D. topic: Advancing Reasoning Capabilities of Statistical Systems (2024 - now)
Curriculum Vitae
- 2024-now Ph.D. in Computational Linguistics, ÚFAL MFF UK
- 2022-2024 Mgr. in Artificial Intelligence, MFF UK
- 2019-2022 Bc. in Computer Science (specialization: Theoretical Computer Science), MFF UK
Selected Bibliography
- Google Scholar
- ORCID: 0009-0006-9530-3670
- Researcher ID: LMN-4478-2024
- SAM3RL: Memory Control via Reinforcement Learning for Visual Object Tracking. In: PTA: From Pretrained Representations to Acting Agents - Bridging Pretraining, Planning, and Test-Time Decision Making, pp. 1-28, Neural Information Processing Systems Foundation (bibtex)
- VLA Adaptation with Real and Simulated Data: A Case Study on Robotic Chess. In: Pretrain to Adapt: What Makes a Pretrained Policy Adaptable? (CoRL 2026 Workshop), pp. 1-15, Conference on Robot Learning (CoRL) (local PDF, bibtex)
- OpenProver: Agentic and Interactive Theorem Proving with Lean 4. In: Intelligent Computer Mathematics: 19th International Conference, pp. 340-346, Springer Nature Switzerland, Cham, Switzerland, ISBN 978-3-032-38214-6 (local PDF, bibtex)
- Bolzano: From Expert-Guided Proof Search to Automated Open-Problem Solving. In: The 6th Workshop on Mathematical Reasoning and AI (MATH-AI 2026), pp. 1-5, Neural Information Processing Systems Foundation (bibtex)
- Symbolic World Models in Lean 4 for Reinforcement Learning. In: Proceedings of the RLC 2025 Workshop on Programmatic Reinforcement Learning, pp. 8-18, Reinforcement Learning Journal (RLJ), Edmonton, Canada (url, local PDF, bibtex)
- LeanTree: Accelerating White-Box Proof Search with Factorized States in Lean 4. In: Proceedings of the Second AI for Math Workshop, pp. 67-79, International Machine Learning Society (IMLS), Geneva, Switzerland (url, local PDF, bibtex)
- Self-Supervised Summarization via Reinforcement Learning (masters thesis). In: (bibtex)
- Emergence of Novelty in Evolutionary Algorithms. In: Proceedings of the ALIFE 2022: The 2022 Conference on Artificial Life, pp. 146-154, MIT Press, Cambridge, MA, USA (pdf, obd, bibtex)


