B | Perception, Vision, and Natural Language Processing

forms a dynamic research domain at the intersection of computer science and cognitive sciences. This field explores the synergies between diverse sensory inputs, visual information processing, and language understanding.

B1 | Computer Vision

In the thriving era of Computer Vision, MCML researchers tackle key challenges by innovating beyond convolutional neural networks. They focus on novel models capturing both pixel relationships and high-level interactions, explore unsupervised learning techniques, and extend analysis beyond 2D to understand the 3D world observed through cameras.

Link to Daniel Cremers

Prof. Dr. Daniel Cremers

TU München

Computer Vision & Artificial Intelligence

Link to Angela Dai

Prof. Dr. Angela Dai

TU München

Machine Learning of 3D Scene Geometry

Link to Matthias Nießner

Prof. Dr. Matthias Nießner

TU München

Visual Computing

Link to Björn Ommer

Prof. Dr. Björn Ommer

LMU München

Machine Vision & Learning

Link to Nils Thuerey

Prof. Dr. Nils Thuerey

TU München

Physics-based Simulation

Link to Rüdiger Westermann

Prof. Dr. Rüdiger Westermann

TU München

Computer Graphics & Visualization

B2 | Natural Language Processing

Natural Language Processing (NLP) focuses on understanding and generating natural language text, greatly influenced by recent advances in deep learning. Despite substantial progress, our MCML researchers address key challenges like enhancing deep language understanding through structural biases, developing common sense in models through experimental environments, and improving sample efficiency for more effective learning from large datasets.

Link to Alexander Fraser

Prof. Dr. Alexander Fraser

LMU München

Machine Translation and Multilingual NLP

Link to Barbara Plank

Prof. Dr. Barbara Plank

LMU München

Artificial Intelligence and Computational Linguistics

Link to Hinrich Schütze

Prof. Dr. Hinrich Schütze

LMU München

Statistical NLP and Deep Learning

B3 | Multimodal Perception

The ability for an intelligent, mobile actor to understand ego­motion as well as the surroundings are a fundamental pre­requisite for the choice of actions to take. However, vast challenges remain to achieve the necessary levels of safety, which are deeply rooted in research that MCML aims to carry out: Multi­sensor ego­motion estimation and environment mapping, scene representations suitable for interaction in an open­-ended environment, understanding and forecasting motion and events, and the the role of uncertainty in ML blocks as modular elements.

Link to Matthias Althoff

Prof. Dr. Matthias Althoff

TU München

Cyber Physical Systems

Link to Stefan Leutenegger

Prof. Dr. Stefan Leutenegger

TU München

Machine Learning for Robotics

Link to Angela P. Schoellig

Prof. Dr. Angela P. Schoellig

TU München

Safety, Performance and Reliability of Learning Systems

A | Foundations of Machine Learning

aims at strengthening the competence in Statistical Foundations and Explainability, Mathematical Foundations, and Computational Methods. These fields form the basis for all methodological advances.

C | Domain­-specific Machine Learning

shows an immense potential, as both universities have several highly visible scientific domains with internationally renowned experts. This area facilitates translating ML concepts and technologies to many different domains.


Check out the publications by our members.