Felix Friedrich

Felix Friedrich

Researcher 🌲 · Black Forest Labs Black Forest Labs · Freiburg, Germany 🇩🇪

About Me

I'm a Researcher at Black Forest Labs 🌲, where I do fundamental research on generative multimodal models, including RL post-training and safety research.

As these systems become more powerful and widely deployed, ensuring they behave responsibly and do not produce harmful or biased outputs is critical. My research addresses both the advancement and the responsible deployment of generative AI.

Research Topics: Generative Multimodal (World) Models · Inference | RL | Post-Training · AI Safety

News

May 2026
🌲 Joined Black Forest Labs as a Researcher, working on the fundamentals of generative multimodal models.
June 2026
Presenting our work on Inference-time Physics Alignment of Video Generative Models with Latent World Models at CVPR 2026 (Spotlight) in Denver.
2025
Measuring and Guiding Monosemanticity accepted as a NeurIPS 2025 Spotlight.
2025
Wrapped up a postdoc at Meta FAIR in Montreal — working on RL post-training for generative models and V-JEPA as a physics reward model.

Timeline

2026 – present
Black Forest Labs Researcher at Black Forest Labs 🌲, Freiburg, Germany. Fundamental research on generative multimodal models, including RL post-training and safety research, with Andreas Blattmann, Robin Rombach, Axel Sauer, Jonas Müller, and the team.
2025 – 2026
Meta Postdoctoral Researcher at Meta FAIR, Montreal, Canada. Worked with Michal Drozdzal, Adriana Romero-Soriano, Nicolas Ballas, and Luke Zettlemoyer on RL post-training for generative models and V-JEPA as a physics reward model.
2024 – 2025
Aleph Alpha × TU Darmstadt Researcher and Co-lead at Lab1141, AlephAlpha × TU Darmstadt, Germany.
2021 – 2025
TU Darmstadt × Hessian.AI PhD student with Prof. Kristian Kersting at Machine Learning Lab, TU Darmstadt, and 3AI, hessian.AI, Germany.
2020
Chalmers Erasmus+ at Chalmers University of Technology, Gothenburg, Sweden.
2019 – 2021
TU Darmstadt M.Sc. in Computer Science (minor in Psychology), TU Darmstadt, Germany.
2018 – 2021
TU Darmstadt M.Sc. (with honors) in Autonomous Systems, TU Darmstadt, Germany.
2017
IAV Research internship on intelligent autonomous driving systems at IAV, Volkswagen Group, Germany.
2014 – 2017
TU Dortmund B.Sc. in Electrical Engineering, TU Dortmund, Germany.

Selected Publications

For a full list, see my Google Scholar profile.

Inference-time Physics Alignment of Video Generative Models with Latent World Models
J Yuan, X Zhang*, F Friedrich*, N Beltran-Velez*, M Hall, R Askari-Hemmat, ...
CVPR 2026 (Spotlight)
Measuring and Guiding Monosemanticity
R Härle*, F Friedrich*, M Brack, S Wäldchen, B Deiseroth, P Schramowski, ...
NeurIPS 2025 (Spotlight)
Multilingual Text-to-Image Generation Magnifies Gender Stereotypes and Prompt Engineering May Not Help You
F Friedrich, K Hämmerl, P Schramowski, M Brack, J Libovicky, K Kersting, ...
ACL 2025
Evaluating the Social Impact of Generative AI Systems in Systems and Society
I Solaiman, Z Talat, W Agnew, L Ahmad, D Baker, SL Blodgett, C Chen, ...
Oxford Handbook on the Foundations and Regulation of Generative AI 2025
LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and Models
L Helff*, F Friedrich*, M Brack*, K Kersting, P Schramowski
ICML 2025
Aurora-M: Open Source Continual Pre-training for Multilingual Language and Code
T Nakamura, M Mishra, S Tedeschi, Y Chai, JT Stillerman, F Friedrich, ...
COLING 2025
FairDiffusion: Auditing and Instructing Text-to-Image Generation Models on Fairness
F Friedrich, M Brack, L Struppek, D Hintersdorf, P Schramowski, ...
AI and Ethics 2024
LEdits++: Limitless Image Editing using Text-to-Image Models
M Brack*, F Friedrich*, K Kornmeier*, L Tsaban, P Schramowski, ...
CVPR 2024
ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teaming
S Tedeschi, F Friedrich, P Schramowski, K Kersting, R Navigli, H Nguyen, ...
Online Workshop on Red Teaming Generative AI Models 2024
Learning by Self-Explaining
W Stammer, F Friedrich, D Steinmann, M Brack, H Shindo, K Kersting
TMLR 2024
SEGA: Instructing Text-to-Image Models using Semantic Guidance
M Brack, F Friedrich, D Hintersdorf, L Struppek, P Schramowski, ...
NeurIPS 2023
MultiFusion: Fusing Pre-trained Models for Multi-lingual, Multi-modal Image Generation
M Bellagente, M Brack, H Teufel, F Friedrich, B Deiseroth, C Eichenberg, ...
NeurIPS 2023
Exploiting Cultural Biases via Homoglyphs in Text-to-Image Synthesis
L Struppek, D Hintersdorf, F Friedrich, P Schramowski, K Kersting
JAIR 2023
A Typology for Exploring the Mitigation of Shortcut Behaviour
F Friedrich, W Stammer, P Schramowski, K Kersting
Nature Machine Intelligence 2023

Teaching

Supervised courses at TU Darmstadt with Prof. Dr. Kristian Kersting:

SemesterCourse
WS 2024Probabilistic Graphical Models
WS 2023Probabilistic Graphical Models
SS 2022Data Mining and Machine Learning
WS 2021Introduction to AI
SS 2021Deep Learning: Architectures and Methods
SS 2020Statistical Machine Learning