Below is a selection of talks, podcasts, and news articles from or about us that may be of interest to you. Click here for news about our latest activities. If you have any questions or comments, we look forward to hearing from you.
Sexism in online discussions can discourage women from participating, especially given the overwhelming volume of comments that moderators have to manage. Our method, which emulates the decisions of different moderators, was awarded 2nd place at the GermEval 2024 shared task 2, held at KONVENS in Vienna. For a detailed look at our approach, please view the presentation by our team member Patrick Gustav Blaneck below.
Our team's research on tackling data scarcity in sleep medical settings was selected for an oral presentation at the Time-Series for Health Workshop at ICLR 2024 in Vienna. Niklas presented his findings on pretraining sleep staging models without patient data—opening new doors for deep learning in settings where time series data is limited.
Anfang März 2023 fand an der FH Aachen eine hochschulweite Informationsveranstaltung zu ChatGPT und seinen möglichen Auswirkungen auf die Hochschullehre statt. Der Vortrag erläutert, wie große Sprachmodelle (large language models) wie ChatGPT trainiert werden, welche Auswirkungen solche Systeme auf die Hochschullehre haben und wie zukünftige Entwicklungen aussehen könnten.
Dieser Vortrag wurde im Rahmen der didaktischen Tafelrunde der Hochschule gehalten und zuerst auf dem ZHQ-Blog der FH Aachen veröffentlicht.
In diesem Interview in einem Podcast unserer Hochschule diskutieren wir die möglichen Auswirkungen von Systemen wie ChatGPT auf die Hochschullehre.
Dieses Podcast-Interview wurde als Teil des ZHQ-Podcasts der FH Aachen geführt und wurde zuerst ebenda veröffentlicht.
Dieser Artikel, der Anfang 2023 in der Zeitschrift Die Neue Hochschule veröffentlicht wurde, stellt die Entstehung großer Sprachmodelle wie ChatGPT vor, diskutiert ihre Risiken und Chancen und erörtert mögliche Auswirkungen auf sich verändernde Kompetenzen, Lernziele und Prüfungsformen an Hochschulen.
Stephan was invited to speak at the NetDat 2022 conference hosted by the Max Planck Institute for the Physics of Complex Systems in Dresden, Germany. His talk explained the rapid progress in Deep Learning to a non-machine learning audience, and included discussions of observations that preceded the introduction of ChatGPT, which was released two months later. You can watch his one-hour talk in the video below.
This talk was recorded by the Max-Planck Institute for the Physics of Complex Systems in Dresden, Germany.
The Aachener Zeitung reported that our research group won first place in the international GermEval 2021 competition for automatic hate speech detection. Our method outperformed all other approaches submitted by international university teams. You can read the article here (German).
🎉 We celebrate the publication of our AnySleep paper in npj Digital Medicine! Our open-source model analyzes sleep from flexible combinations of EEG and EOG signals and provides sleep-stage predictions at adjustable temporal resolutions. We trained and validated AnySleep on more than 20,000 overnight recordings across 28 datasets. 📄 Read the paper, explore the code, and try it out online.
🏆 Our team BASH won 2nd place in the call-to-action (C2A) detection subtask of the GermEval 2026 competition on harmful content in German social media! Our approach combines fine-tuned language models to identify posts requesting or encouraging specific actions. Congratulations to all team members! Explore the code.
📄 Our collaborative study on sleep spindles and cognition in bipolar disorder has been published in Translational Psychiatry. Using mobile EEG recordings and automated spindle detection, exploratory findings suggested a relationship with working memory. Read the paper.
📄 Our study on end-to-end automated sleep analysis has been published in Scientific Reports! Combining automated sleep staging with spindle detection, we reproduced key qualitative findings from an expert-led study of bipolar disorder in minutes rather than months. Read the paper and explore SomnoBot.
📄 Our collaborative study on sleep and Parkinson's disease has been published in Parkinsonism & Related Disorders. Using SUMO to detect sleep spindles, we found an association between spindle density and degeneration of the locus coeruleus, a brain region involved in sleep regulation. Read the paper.
👨🏫 Niklas presented our work on fully automated sleep analysis at DGSM 2025 in Hannover. Using sleep staging followed by spindle detection, we reproduced key findings from an expert-led study of bipolar disorder. The presentation also introduced SomnoBot as a way to use these tools without uploading patient data.
📄 Our expanded study on data-efficient sleep staging with synthetic time series pretraining has been published in Algorithms! Building on our ICLR 2024 workshop contribution, we demonstrate how learning from randomly generated signals can improve sleep staging when only a small amount of labeled patient data is available. Read the paper.
🏆 Our team won 1st place in both subtasks of the GermEval 2025 competition on detecting positive, supportive online language, known as candy speech! By training a language model to identify specific supportive passages, we improved both comment-level detection and detailed annotation. Congratulations to all team members! Read our paper.