Our Research

At the MAI Lab, our team of >10 dedicated PhD researchers delves into a diverse array of topics and domains, pushing the boundaries of knowledge and innovation. Explore our research areas below.

For the most up-to-date snapshot of our lab’s research topics, see also the lab leads’ Google Scholar (Prof. Anna Rohrbach, Prof. Marcus Rohrbach).

Research Project Areas

Selective Prediction

Selective Prediction, as a sub-field of reliable Artificial Intelligence, aims to develop methods and techniques to identify uncertain model predictions. Instead of having a model produce an output for every sample, an abstention mechanism is implemented that recognizes instances where predictions are likely inaccurate. Accordingly, the model only makes predictions for samples that are not filtered out by this mechanism and abstains from the others. Colloquially, with Selective Prediction, we are "creating models that know what they don't know."

Learn more

Multimodal Fact-Checking

Disinformation is arguably one of the biggest threats for society and democracy. Multimodal fact-checking aims to verify claims (e.g. from social media posts) that, beyond text, also include images or videos. It is a broad discipline, spanning from raw content interpretation and claim extraction over credible evidence retrieval to accurate veracity prediction. We advance the field by, for example, proposing new, explainable methods—like InFact and DEFAME.

Learn more

Modularity

Modular AI systems are designed with a modular architecture, where complex tasks are broken down into smaller, more manageable components or modules. Each module handles specific aspects like perception, reasoning, or decision-making. With current end-to-end models growing into monolithic black boxes, there's a clear argument for more modular systems composed of smaller, manageable components.

Learn more

Multimodal Deepfake Detection

Deepfake technology poses a significant risk to societal trust and democracy. Multimodal deepfake detection focuses on identifying falsified content (e.g., videos, audio, and images) that manipulate both visual and auditory elements. The detection process involves analyzing the suspicious media, extracting relevant features from both visual and audio data, and applying advanced algorithms to determine authenticity. Our goal is to enhance current multimodal approaches to deepfake detection, making it more accurate and scalable to counteract the growing threat of synthetic media.

Learn more