| CARVIEW |
Select Language
HTTP/2 200
content-type: text/html
x-ws-ratelimit-limit: 1000
x-ws-ratelimit-remaining: 999
date: Mon, 29 Dec 2025 13:31:13 GMT
server: Apache
last-modified: Fri, 05 Jan 2024 10:21:30 GMT
etag: W/"adfc-60e303628c1e3"
content-encoding: gzip
Florian Wenzel
Biography
I am the CTO and co-founder of Mirelo AI. We are building generative foundation models for music and applications. We are hiring! Before I was an Applied Scientist at Amazon AWS AI working on robust computer vision and large language models (2021 - 2023). From 2019 - 2021, I was a postdoctoral researcher at Google Brain Berlin working on reliable deep learning. I received my PhD in machine learning from Humboldt-Universität zu Berlin in 2019, working with my advisors Marius Kloft (TU Kaiserslautern and USC), Manfred Opper (TU Berlin) and Stephan Mandt (UCI).
Interests
- Generative Music Models
- Foundation Models
- Reliable Deep Learning
- Transformers
Education
-
PhD in Machine Learning, 2019
Humboldt-Universität zu Berlin and TU Kaiserslautern
-
MSc in Mathematics, 2015
Humboldt-Universität zu Berlin
Selected Publications
A data augmentation perspective on diffusion models and retrieval
Max F Burg, Florian Wenzel, Dominik Zietlow, Max Horn, Osama Makansi, Francesco Locatello, Chris Russell
TMLR,
2023
Leveraging sparse and shared feature activations for disentangled representation learning
Marco Fumero, Florian Wenzel, Luca Zancato, Alessandro Achille, Emanuele Rodolà, Stefano Soatto, Bernhard Schölkopf, Francesco Locatello
NeurIPS,
2023
Multi-Symmetry Ensembles: Improving Diversity and Generalization via Opposing Symmetries
Charlotte Loh, Seungwook Han, Shivchander Sudalairaj, Rumen Dangovski, Kai Xu, Florian Wenzel, Marin Soljacic, Akash Srivastava
ICML,
2023
Evaluating the fairness of discriminative foundation models in computer vision
Junaid Ali, Matthaeus Kleindessner, Florian Wenzel, Kailash Budhathoki, Volkan Cevher, Chris Russell
AIES,
2023
Are Multimodal Models Robust to Image and Text Perturbations?
Jielin Qiu, Yi Zhu, Xingjian Shi, Florian Wenzel, Zhiqiang Tang, Ding Zhao, Bo Li, Mu Li
arXiv,
2022
Assaying out-of-distribution generalization in transfer learning
Florian Wenzel, Andrea Dittadi, Peter Vincent Gehler, Carl-Johann Simon-Gabriel, Max Horn, Dominik Zietlow, David Kernert, Chris Russell, Thomas Brox, Bernt Schiele, Bernhard Schölkopf, Francesco Locatello
NeurIPS,
2022
Deep classifiers with label noise modeling and distance awareness
Vincent Fortuin, Mark Collier, Florian Wenzel, James Allingham, Jeremiah Liu, Dustin Tran, Balaji Lakshminarayanan, Jesse Berent, Rodolphe Jenatton, Effrosyni Kokiopoulou
TMLR,
2021
Sparse moes meet efficient ensembles
James Urquhart Allingham, Florian Wenzel, Zelda E Mariet, Basil Mustafa, Joan Puigcerver, Neil Houlsby, Ghassen Jerfel, Vincent Fortuin, Balaji Lakshminarayanan, Jasper Snoek, Dustin Tran, Carlos Riquelme Ruiz, Rodolphe Jenatton
TMLR,
2021
Uncertainty baselines: Benchmarks for uncertainty & robustness in deep learning
Zachary Nado, Neil Band, Mark Collier, Josip Djolonga, Michael W Dusenberry, Sebastian Farquhar, Qixuan Feng, Angelos Filos, Marton Havasi, Rodolphe Jenatton, Ghassen Jerfel, Jeremiah Liu, Zelda Mariet, Jeremy Nixon, Shreyas Padhy, Jie Ren, Tim GJ Rudner, Faris Sbahi, Yeming Wen, Florian Wenzel, Kevin Murphy, D Sculley, Balaji Lakshminarayanan, Jasper Snoek, Yarin Gal, Dustin Tran
arXiv,
2021
Bayesian Neural Network Priors Revisited
V. Fortuin, A. Garriga-Alonso, Florian Wenzel, G. Rätsch, R. Turner, M. v.d. Wilk, L. Aitchison
ICRL,
2021
Hyperparameter Ensembles for Robustness and Uncertainty Quantification
F. Wenzel, J. Snoek, D. Tran, R. Jenatton
NeurIPS,
2020
Oral Presentation (short)
How Good is the Bayes Posterior in Deep Neural Networks Really?
F. Wenzel*, K. Roth*, B. Veeling*, J. Świątkowski, L. Tran, S. Mandt, J. Snoek, T. Salimans, R. Jenatton, S. Nowozin
(* = equal contribution)
ICML,
2020
Oral Presentation (long)
Automated Augmented Conjugate Inference for Non-conjugate Gaussian Process Models
T. Galy-Fajou, F. Wenzel, M. Opper
AISTATS,
2020
Oral Presentation
Multi-Class Gaussian Process Classification Made Conjugate: Efficient Inference via Data Augmentation
T. Galy-Fajou*, F. Wenzel*, C. Donner, M. Opper
(* = equal contribution)
UAI,
2019
Efficient Gaussian Process Classification Using Polya-Gamma Data Augmentation
F. Wenzel*, T. Galy-Fajou*, C. Donner, M. Kloft, M. Opper
(* = equal contribution)
AAAI,
2019
Oral Presentation
Quasi-Monte Carlo Variational Inference
A. Buchholz*, F. Wenzel*, S. Mandt
(* = equal contribution)
ICML,
2018
Oral Presentation
Scalable Generalized Dynamic Topic Models
P. Jähnichen*, F. Wenzel*, M. Kloft, S. Mandt
(* = equal contribution)
AISTATS,
2018
Sparse Probit Linear Mixed Model
S. Mandt*, F. Wenzel*, S. Nakajima, J. P. Cunningham, C. Lippert, M. Kloft
(* = equal contribution)
Machine Learning,
2017
Bayesian Nonlinear Support Vector Machines for Big Data
F. Wenzel, T. Galy-Fajou, M. Deutsch, M. Kloft
ECML,
2017
Best Student Paper Award Nomination
Oral Presentation
Recent & Upcoming Talks
Teaching
Supervised Students
- Lorenz Vaitl: Master’s thesis (TU Berlin, 2018)
- Scalable Inference for Correlated Noise Classification Models
- Eren Sezener: Lab rotation project (TU Berlin, 2018)
- Multi-armed bandits and knowledge gradients
Courses
- Probabilistic Machine Learning (Supervision of student projects, TU Berlin, Winter 18 / 19)
Past Courses
- Machine Learning II (Lecture and exercise, HU Berlin, Winter 16 / 17)
- Hot Topics in ML (Master seminar, HU Berlin, Winter 16 / 17)
- Machine Learning I (Lecture, exercise and project seminar, HU Berlin, Summer 2016)
- Hot Topics in ML (Master seminar, HU Berlin, Summer 16)
- Machine Learning II (Lecture and exercise, HU Berlin, Winter 15 / 16)
- Machine Learning I (Exercise, HU Berlin, Summer 15)