Tristan Cinquin

PhD student, Computer science, Eberhard-Karls-Universität Tübingen

Joined

September 2021

Names

Tristan Cinquin (Preferred)

Emails

****@yahoo.fr (Confirmed)

,

****@gmail.com (Confirmed)

,

****@uni-tuebingen.de (Confirmed)

Personal Links

Career & Education History

PhD student

Computer science, Eberhard-Karls-Universität Tübingen (uni-tuebingen.de)

2023 – Present

MS student

Computer science, Swiss Federal Institute of Technology (ethz.ch)

2019 – 2022

Advisors, Relations & Conflicts

PhD Advisor

Vincent Fortuin

2024 – Present

PhD Advisor

2023 – Present

Expertise

Bayesian machine learning

Present

Bayesian deep learning

Present

Publications

Limits of PRM-Guided Tree Search for Mathematical Reasoning with LLMs
Tristan Cinquin, Geoff Pleiss, Agustinus Kristiadi
- MATH-AI 2025 Poster
- Readers: Everyone
Language Models For PDDL Planning: Generating Sound and Programmatic Policies
Dillon Ze Chen, Johannes Zenn, Tristan Cinquin, Sheila A. McIlraith
- RLC 2025 Workshop PRL
- Readers: Everyone
Language Models For PDDL Planning: Generating Sound and Programmatic Policies
Dillon Ze Chen, Johannes Zenn, Tristan Cinquin, Sheila A. McIlraith
- EWRL 2025 Poster
- Readers: Everyone
What Actually Matters for Materials Discovery: Pitfalls and Recommendations in Bayesian Optimization
Tristan Cinquin, Stanley Lo, Felix Strieth-Kalthoff, Alan Aspuru-Guzik, Geoff Pleiss, Robert Bamler, Tim G. J. Rudner, Vincent Fortuin, Agustinus Kristiadi
- AABI 2025 Workshop Track
- Readers: Everyone
Well-Defined Function-Space Variational Inference in Bayesian Neural Networks via Regularized KL-Divergence
Tristan Cinquin, Robert Bamler
- UAI 2025 Poster
- Readers: Everyone
What Actually Matters for Materials Discovery: Pitfalls and Recommendations in Bayesian Optimization
Tristan Cinquin, Stanley Lo, Felix Strieth-Kalthoff, Alan Aspuru-Guzik, Geoff Pleiss, Robert Bamler, Tim G. J. Rudner, Vincent Fortuin, Agustinus Kristiadi
- AI4MAT-ICLR-2025 Poster
- Readers: Everyone
Regularized KL-Divergence for Well-Defined Function-Space Variational Inference in Bayesian Neural Networks
Tristan Cinquin, Robert Bamler
- 2nd SPIGM @ ICML Poster
- Readers: Everyone
FSP-Laplace: Function-Space Priors for the Laplace Approximation in Bayesian Deep Learning
Tristan Cinquin, Marvin Pförtner, Vincent Fortuin, Philipp Hennig, Robert Bamler
- NeurIPS 2024 poster
- Readers: Everyone
Regularized KL-Divergence for well-defined function space variational inference in BNNs
Tristan Cinquin, Robert Bamler
- Submitted to ICLR 2024
- Readers: Everyone
Variational boosted soft trees
Tristan Cinquin, Tammo Rukat, Philipp Schmidt, Martin Wistuba, Artur Bekasov
- 15 Mar 2023
- OpenReview Archive Direct Upload
- Readers: Everyone

View all 12 publications

Co-Authors