Research Group Vincent Fortuin
Vincent Fortuin
Dr.
Collaborating PI
Vincent Fortuin
His research focuses on reliable and data-efficient AI approaches leveraging Bayesian deep learning, deep generative modeling, meta-learning, and PAC-Bayesian theory.
Team members @MCML
PostDocs
James Odgers
Dr.
→ Group Vincent Fortuin
Bayesian Deep Learning
PhD Students
Blagovest Gospodinov
→ Group Vincent Fortuin
Bayesian Deep Learning
Michal Kmicikiewicz
→ Group Vincent Fortuin
Bayesian Deep Learning
Ben Riegler
→ Group Vincent Fortuin
Bayesian Deep Learning
Thomas Rochussen
→ Group Vincent Fortuin
Bayesian Deep Learning
Annika Schneider
→ Group Vincent Fortuin
Bayesian Deep Learning
Arsen Sheverdin
→ Group Vincent Fortuin
Bayesian Deep Learning
Recent News @MCML
Publications @MCML
2026
[19]
P. Mortimer • C. Diaconu • T. Rochussen • B. Mlodozeniec • R. E. Turner
Incremental Transformer Neural Processes.
ICML 2026 - 43rd International Conference on Machine Learning. Seoul, South Korea, Jul 06-11, 2026. To be published. Preprint available. URL GitHub
Incremental Transformer Neural Processes.
ICML 2026 - 43rd International Conference on Machine Learning. Seoul, South Korea, Jul 06-11, 2026. To be published. Preprint available. URL GitHub
[18]
M. Możejko • A. Bielecki • J. Prądzyński • H.-S. Lee • A. Janowski • M. Kmicikiewicz • P. Szymczak • K. Jurasz • M. Traskowski • M. Kucharczyk • M. Der Torossian Torres • C. de la Fuente-Nunez • E. Szczurek
PepCompass: Navigating Peptide Embedding Spaces Using Riemannian Geometry.
ICML 2026 - 43rd International Conference on Machine Learning. Seoul, South Korea, Jul 06-11, 2026. To be published. Preprint available. URL GitHub
PepCompass: Navigating Peptide Embedding Spaces Using Riemannian Geometry.
ICML 2026 - 43rd International Conference on Machine Learning. Seoul, South Korea, Jul 06-11, 2026. To be published. Preprint available. URL GitHub
[17]
J. Odgers • B. Riegler • S. Swaroop • V. Fortuin
Gaussian Mean Field Variational Inference can Overestimate Predictive Variance.
ICML 2026 - 43rd International Conference on Machine Learning. Seoul, South Korea, Jul 06-11, 2026. To be published. Preprint available. URL GitHub
Gaussian Mean Field Variational Inference can Overestimate Predictive Variance.
ICML 2026 - 43rd International Conference on Machine Learning. Seoul, South Korea, Jul 06-11, 2026. To be published. Preprint available. URL GitHub
[16]
T. Papamarkou • P. Alquier • M. Bauer • W. Buntine • A. Davison • G. K. Dziugaite • M. Filippone • A. Y. K. Foong • V. Fortuin • D. Fouskakis • J. Frellsen • E. Hüllermeier • T. Karaletsos • M. E. Khan • N. Kotelevskii • S. Lahlou • Y. Li • F. Liu • C. Lyle • T. Möllenhoff • K. Palla • M. Panov • Y. Sale • K. Schweighofer • A. Shelmanov • S. Swaroop • M. Trapp • W. Waegeman • A. G. Wilson • A. Zaytsev
Position: Agentic AI Orchestration Should Be Bayes-Consistent.
ICML 2026 - 43rd International Conference on Machine Learning. Seoul, South Korea, Jul 06-11, 2026. To be published. Preprint available. URL
Position: Agentic AI Orchestration Should Be Bayes-Consistent.
ICML 2026 - 43rd International Conference on Machine Learning. Seoul, South Korea, Jul 06-11, 2026. To be published. Preprint available. URL
[15]
A. Schneider • T. Rochussen • J. Stiller • V. Fortuin
Decision-Aligned Evaluation of Uncertainty Quantification.
Preprint (Jun. 2026). arXiv GitHub
Decision-Aligned Evaluation of Uncertainty Quantification.
Preprint (Jun. 2026). arXiv GitHub
[14]
T. Rochussen • V. Fortuin
Amortising Inference and Meta-Learning Priors in Neural Networks.
ICLR 2026 - 14th International Conference on Learning Representations. Rio de Janeiro, Brazil, Apr 23-27, 2026. To be published. Preprint available. arXiv
Amortising Inference and Meta-Learning Priors in Neural Networks.
ICLR 2026 - 14th International Conference on Learning Representations. Rio de Janeiro, Brazil, Apr 23-27, 2026. To be published. Preprint available. arXiv
[13]
B. Riegler • J. Odgers • V. Fortuin
Standard Acquisition Is Sufficient for Asynchronous Bayesian Optimization.
Preprint (Mar. 2026). arXiv
Standard Acquisition Is Sufficient for Asynchronous Bayesian Optimization.
Preprint (Mar. 2026). arXiv
2025
[12]
F. Sergeev • M. Burger • P. Leshetkina • V. Fortuin • G. Rätsch • R. Kuznetsova
Data-Driven Discovery of Feature Groups in Clinical Time Series.
ML4H 2025 - Machine Learning for Health Symposium. San Diego, CA, USA, Dec 01-02, 2025. URL
Data-Driven Discovery of Feature Groups in Clinical Time Series.
ML4H 2025 - Machine Learning for Health Symposium. San Diego, CA, USA, Dec 01-02, 2025. URL
[11]
M. Kmicikiewicz • V. Fortuin • E. Szczurek
ProSpero: Active Learning for Robust Protein Design Beyond Wild-Type Neighborhoods.
NeurIPS 2025 - 39th Conference on Neural Information Processing Systems. San Diego, CA, USA, Nov 30-Dec 07, 2025. URL
ProSpero: Active Learning for Robust Protein Design Beyond Wild-Type Neighborhoods.
NeurIPS 2025 - 39th Conference on Neural Information Processing Systems. San Diego, CA, USA, Nov 30-Dec 07, 2025. URL
[10]
K. Flöge • S. Udayakumar • J. Sommer • M. Piraud • S. Kesselheim • V. Fortuin • S. Günneman • K. J. van der Weg • H. Gohlke • E. Merdivan • A. Bazarova
OneProt: Towards multi-modal protein foundation models via latent space alignment of sequence, structure, binding sites and text encoders.
PLOS Computational Biology 21.11. Nov. 2025. DOI
OneProt: Towards multi-modal protein foundation models via latent space alignment of sequence, structure, binding sites and text encoders.
PLOS Computational Biology 21.11. Nov. 2025. DOI
[9]
A. Reuter • T. G. J. Rudner • V. Fortuin • D. Rügamer
Can Transformers Learn Full Bayesian Inference in Context?
ICML 2025 - 42nd International Conference on Machine Learning. Vancouver, Canada, Jul 13-19, 2025. URL
Can Transformers Learn Full Bayesian Inference in Context?
ICML 2025 - 42nd International Conference on Machine Learning. Vancouver, Canada, Jul 13-19, 2025. URL
[8]
T. Rochussen • V. Fortuin
Sparse Gaussian Neural Processes.
AABI 2025 - 7th Symposium on Advances in Approximate Bayesian Inference collocated with the 13th International Conference on Learning Representations. Singapore, Apr 29, 2025. URL
Sparse Gaussian Neural Processes.
AABI 2025 - 7th Symposium on Advances in Approximate Bayesian Inference collocated with the 13th International Conference on Learning Representations. Singapore, Apr 29, 2025. URL
[7]
A. Reuter • T. G. J. Rudner • V. Fortuin • D. Rügamer
Can Transformers Learn Full Bayesian Inference in Context?
FPI @ICLR 2025 - Workshop on Frontiers in Probabilistic Inference: Learning meets Sampling at the 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. arXiv URL
Can Transformers Learn Full Bayesian Inference in Context?
FPI @ICLR 2025 - Workshop on Frontiers in Probabilistic Inference: Learning meets Sampling at the 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. arXiv URL
[6]
A. Reuter • T. G. J. Rudner • V. Fortuin • D. Rügamer
Can Transformers Learn Full Bayesian Inference in Context?
SynthData @ICLR 2025 - Workshop SynthData: Will Synthetic Data Finally Solve the Data Access Problem? at the 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL
Can Transformers Learn Full Bayesian Inference in Context?
SynthData @ICLR 2025 - Workshop SynthData: Will Synthetic Data Finally Solve the Data Access Problem? at the 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. URL
2024
[5]
R. Dhahri • A. Immer • B. Charpentier • S. Günnemann • V. Fortuin
Shaving Weights with Occam's Razor: Bayesian Sparsification for Neural Networks Using the Marginal Likelihood.
NeurIPS 2024 - 38th Conference on Neural Information Processing Systems. Vancouver, Canada, Dec 10-15, 2024. DOI
Shaving Weights with Occam's Razor: Bayesian Sparsification for Neural Networks Using the Marginal Likelihood.
NeurIPS 2024 - 38th Conference on Neural Information Processing Systems. Vancouver, Canada, Dec 10-15, 2024. DOI
[4]
K. Bouchiat • A. Immer • H. Yèche • G. Ratsch • V. Fortuin
Improving Neural Additive Models with Bayesian Principles.
ICML 2024 - 41st International Conference on Machine Learning. Vienna, Austria, Jul 21-27, 2024. URL
Improving Neural Additive Models with Bayesian Principles.
ICML 2024 - 41st International Conference on Machine Learning. Vienna, Austria, Jul 21-27, 2024. URL
[3]
T. Papamarkou • M. Skoularidou • K. Palla • L. Aitchison • J. Arbel • D. Dunson • M. Filippone • V. Fortuin • P. Hennig • J. M. Hernández-Lobato • A. Hubin • A. Immer • T. Karaletsos • M. E. Khan • A. Kristiadi • Y. Li • S. Mandt • C. Nemeth • M. A. Osborne • T. G. J. Rudner • D. Rügamer • Y. W. Teh • M. Welling • A. G. Wilson • R. Zhang
Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI.
ICML 2024 - 41st International Conference on Machine Learning. Vienna, Austria, Jul 21-27, 2024. URL
Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI.
ICML 2024 - 41st International Conference on Machine Learning. Vienna, Austria, Jul 21-27, 2024. URL
[2]
K. Flöge • M. A. Moeed • V. Fortuin
Stein Variational Newton Neural Network Ensembles.
SPIGM @ICML 2024 - Workshop on Structured Probabilistic Inference & Generative Modeling at the 41st International Conference on Machine Learning. Vienna, Austria, Jul 21-27, 2024. URL
Stein Variational Newton Neural Network Ensembles.
SPIGM @ICML 2024 - Workshop on Structured Probabilistic Inference & Generative Modeling at the 41st International Conference on Machine Learning. Vienna, Austria, Jul 21-27, 2024. URL
[1]
F. Sergeev • P. Malsot • G. Rätsch • V. Fortuin
Towards Dynamic Feature Acquisition on Medical Time Series by Maximizing Conditional Mutual Information.
SPIGM @ICML 2024 - Workshop on Structured Probabilistic Inference & Generative Modeling at the 41st International Conference on Machine Learning. Vienna, Austria, Jul 21-27, 2024. URL
Towards Dynamic Feature Acquisition on Medical Time Series by Maximizing Conditional Mutual Information.
SPIGM @ICML 2024 - Workshop on Structured Probabilistic Inference & Generative Modeling at the 41st International Conference on Machine Learning. Vienna, Austria, Jul 21-27, 2024. URL
©all images: LMU | TUM
Back to Top
2024-12-27 - Last modified: 2026-07-03