AI research
● for the solutions of the future

We apply transformative AI research to real-world challenges, collaborating closely with partners from academia, business, and industry.

Our approach

Request research partnership

Our research partners:

Our mission

What drives our research?

AI for the future

We research for the future viability of our partners

We conduct cutting-edge research to develop new solutions to unsolved problems with our partners and customers
Horizontal application of machine learning in real-world challenges from all sectors of business and society.

The potential of data

We open up unlabeled data with methodology

Impactful research outcomes through a combination of data-centric approaches and methodological excellence
Integrate results into established and emerging systems through experience in scaling and operationalizing AI

Our approach

FOrschung project request

Our approach

First-class research is created in partnership.

In all our research projects, we deal with state-of-the-art machine learning methods and apply them agnostically in all relevant application areas. During the operational project phase, we staff the projects with a diverse team of experts in research, machine learning engineering, and project management.

As industry-independent developers, we strive to develop generalizable methods that we can easily apply in other domains. We leverage our broad background in methodologies and industries to quickly adapt and deliver meaningful results for new challenges.

At Merantix Momentum, we initiate and participate in a variety of collaborative partnerships across different sectors and funding programs. Our dedicated research management team has more than 30 years of experience in designing and managing research projects, with a particular focus on German and EU-funded collaborative research projects.

We carefully tailor our engagement with a new research project by considering its unique challenge and all partners involved. Our team is able to establish effective consortia and create compelling proposal documents that ensure successful project funding.

We see collaboration as the foundation for our success. As part of the AI Campus ecosystem in Berlin, connecting bright minds and new ideas is essential to our identity. This self-image as an innovative and forward-looking team player is also reflected in the campus, which is an ideal place for stimulating project meetings and inspiring events.

Our goal is to contribute to the scientific community by publishing our results in research papers and presenting them at conferences. The driving motivation here is always to generate added value for the entire research community and thus advance research in AI and machine learning as a whole.

Request research project

Our research projects

What we are currently working on

Our research pushes boundaries. We bring our excellence in machine learning to pioneering projects that span all industrial domains to solve real-world challenges.

In our partnerships, we explore breakthrough solutions, discover new approaches, and apply them to known and emerging domains. We create the conditions for transformative research.

Active

Language models

Publications

To the research blog

About ResearchGate

SECREDAS: Safe and (Cyber-)Secure Cooperative and Automated Mobility (2023)

Sebastian Gerres

IFAC 2023 - Full PDF at arxiv.org

Uncovering the Inner Workings of STEGO for Safe Unsupervised Semantic Segmentation (2023).

Alexander Koenig, Maximilian Schambach, Johannes S. Otterbach

CVPR 2023 - Full PDF at arxiv.org

Interpretable Reinforcement Learning via Neural Additive Models for Inventory Management (2023).

Julien Siems, Maximilian Schambach, Sebastian Schulze, Johannes S. Otterbach

ICLR 2023 - Full PDF at arxiv.org

‍

Learning the Solution Operator of Boundary Value Problems using Graph Neural Networks (2022).

Winfried Lötzsch, Simon Ohler, Johannes S. Otterbach

ICML 2022 - Full PDF at arxiv.org

Scalable Flow Optimization for Small Satellite Networks using Benders Decomposition (2022).

Olga Kondrateva, Stefan Dietzel, Björn Scheuermann

IEEE WoWMoM 2022 - Full PDF at ieee.org

Towards Learning Self-Organized Criticality of Rydberg Atoms using Graph Neural Networks (2022).

Simon Ohler, Daniel Steven Brady, Winfried Lötzsch, Michael Fleischhauer, Johannes Otterbach

AI4Science Workshop at ICML 2022 - Full PDF at arxiv.org

Auto-Compressing Subset Pruning for Semantic Image Segmentation (2022)

Konstantin Ditschuneit, Johannes S. Otterbach

GCPR 2022 - Full PDF at arxiv.org

MEAL: Manifold Embedding-based Active Learning (2021).

Deepthi Sreenivasaiah, Johannes Otterbach, Thomas Wollmann

CPVR 2021 - Full PDF at arxiv.org

DAAIN: Detection of Anomalous and Adversarial Input using Normalizing Flows (2021).

Samuel von Baußnern, Johannes Otterbach, Adrian Loy, Mathieu Salzmann, Thomas Wollmann

Full PDF at arxiv.org

Chameleon: A Semi-AutoML framework targeting quick and scalable development and deployment of production-ready ML systems for SMEs (2021)

Johannes Otterbach, Thomas Wollmann

Full PDF at arxiv.org