Search Results - "Schwinn, Leo"

xLength: Predicting Expected Ski Jump Length Shortly after Take-Off Using Deep Learning by Link, Johannes, Schwinn, Leo, Pulsmeyer, Falk, Kautz, Thomas, Eskofier, Bjoern M.

“…With tracking systems becoming more widespread in sports research and regular training and competitions, more data are available for sports analytics and…”
Get full text

System Design for a Data-Driven and Explainable Customer Sentiment Monitor Using IoT and Enterprise Data by Nguyen, An, Foerstel, Stefan, Kittler, Thomas, Kurzyukov, Andrey, Schwinn, Leo, Zanca, Dario, Hipp, Tobias, Da Jun, Sun, Schrapp, Michael, Rothgang, Eva, Eskofier, Bjoern

“…The most important goal of customer service is to keep the customer satisfied. However, service resources are always limited and must prioritize specific…”
Get full text

Exploring the interrelationship between the skin microbiome and skin volatiles: A pilot study by Haertl, Tobias, Owsienko, Diana, Schwinn, Leo, Hirsch, Cathrin, Eskofier, Bjoern M., Lang, Roland, Wirtz, Stefan, Loos, Helene M.

“…Unravelling the interplay between a human’s microbiome and physiology is a relevant task for understanding the principles underlying human health and disease…”
Get full text

Exploring misclassifications of robust neural networks to enhance adversarial attacks by Schwinn, Leo, Raab, René, Nguyen, An, Zanca, Dario, Eskofier, Bjoern

“…Progress in making neural networks more robust against adversarial attacks is mostly marginal, despite the great efforts of the research community. Moreover,…”
Get full text

Detection, Quantification, and Mitigation of Robustness Vulnerabilities in Deep Neural Networks by Schwinn, Leo

“…Machine learning (ML) has made enormous progress in the last two decades. Specifically, Deep Neural Networks (DNNs) have led to several breakthroughs. The…”
Get full text

Generalized Synchronized Active Learning for Multi-Agent-Based Data Selection on Mobile Robotic Systems by Schmidt, Sebastian, Stappen, Lukas, Schwinn, Leo, Gunnemann, Stephan

“…In mobile robotics, perception in uncontrolled environments like autonomous driving is a central hurdle. Existing active learning frameworks can help enhance…”
Get full text

Sensory evaluation of axillary odour samples of younger and older adults by a trained panel by Owsienko, Diana, Schwinn, Leo, Eskofier, Bjoern M., Kiesswetter, Eva, Loos, Helene M.

“…It has been reported that a distinct ‘old person smell’ can develop with advancing age, however, this odour has not yet been sufficiently described in previous…”
Get full text

Can you smell my stress? Influence of stress chemosignals on empathy and emotion recognition in depressed individuals and healthy controls by Wunder, Annkatrin, Ludwig, Janina, Haertl, Tobias, Arnhardt, Sally, Schwinn, Leo, Chellapandian, Deepak Charles, Weinmair, Elisabeth, Mühle, Christiane, Thürauf, Norbert, Kornhuber, Johannes, Rohleder, Nicolas, Loos, Helene M., Freiherr, Jessica

“…•Stress chemosignals partly improve emotional perspective taking in depressed individuals.•Stress chemosignals partly enhance affective responsiveness in…”
Get full text

Artificial intelligence trend analysis in German business and politics: a web mining approach by Dumbach, Philipp, Schwinn, Leo, Löhr, Tim, Elsberger, Tassilo, Eskofier, Bjoern M.

“…Current research on trend detection in artificial intelligence (AI) mainly concerns academic data sources and industrial applications of AI. However, we argue…”
Get full text

Artificial intelligence trend analysis on healthcare podcasts using topic modeling and sentiment analysis: a data-driven approach by Dumbach, Philipp, Schwinn, Leo, Löhr, Tim, Do, Phi Long, Eskofier, Bjoern M.

“…Over the past few decades, the topic of artificial intelligence (AI) has gained considerable attention in both research and industry. In particular, the…”
Get full text

Revisiting the Robust Alignment of Circuit Breakers by Schwinn, Leo, Geisler, Simon

“…Over the past decade, adversarial training has emerged as one of the few reliable methods for enhancing model robustness against adversarial attacks [Szegedy…”
Get full text

A Probabilistic Perspective on Unlearning and Alignment for Large Language Models by Scholten, Yan, Günnemann, Stephan, Schwinn, Leo

“…Comprehensive evaluation of Large Language Models (LLMs) is an open research problem. Existing evaluations rely on deterministic point estimates generated via…”
Get full text

Extracting Unlearned Information from LLMs with Activation Steering by Seyitoğlu, Atakan, Kuvshinov, Aleksei, Schwinn, Leo, Günnemann, Stephan

“…An unintended consequence of the vast pretraining of Large Language Models (LLMs) is the verbatim memorization of fragments of their training data, which may…”
Get full text

Flow Matching with Gaussian Process Priors for Probabilistic Time Series Forecasting by Kollovieh, Marcel, Lienen, Marten, Lüdke, David, Schwinn, Leo, Günnemann, Stephan

“…Recent advancements in generative modeling, particularly diffusion models, have opened new directions for time series modeling, achieving state-of-the-art…”
Get full text

Relaxing Graph Transformers for Adversarial Attacks by Foth, Philipp, Gosch, Lukas, Geisler, Simon, Schwinn, Leo, Günnemann, Stephan

“…Existing studies have shown that Graph Neural Networks (GNNs) are vulnerable to adversarial attacks. Even though Graph Transformers (GTs) surpassed…”
Get full text

Large-Scale Dataset Pruning in Adversarial Training through Data Importance Extrapolation by Nieth, Björn, Altstidl, Thomas, Schwinn, Leo, Eskofier, Björn

“…Their vulnerability to small, imperceptible attacks limits the adoption of deep learning models to real-world systems. Adversarial training has proven to be…”
Get full text

Efficient Time Series Processing for Transformers and State-Space Models through Token Merging by Götz, Leon, Kollovieh, Marcel, Günnemann, Stephan, Schwinn, Leo

“…Transformer architectures have shown promising results in time series processing. However, despite recent advances in subquadratic attention mechanisms or…”
Get full text

Efficient Adversarial Training in LLMs with Continuous Attacks by Xhonneux, Sophie, Sordoni, Alessandro, Günnemann, Stephan, Gidel, Gauthier, Schwinn, Leo

“…Large language models (LLMs) are vulnerable to adversarial attacks that can bypass their safety guardrails. In many domains, adversarial training has proven to…”
Get full text

A Unified Approach Towards Active Learning and Out-of-Distribution Detection by Schmidt, Sebastian, Schenk, Leonard, Schwinn, Leo, Günnemann, Stephan

“…When applying deep learning models in open-world scenarios, active learning (AL) strategies are crucial for identifying label candidates from a nearly infinite…”
Get full text

Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space by Schwinn, Leo, Dobre, David, Xhonneux, Sophie, Gidel, Gauthier, Gunnemann, Stephan

“…Current research in adversarial robustness of LLMs focuses on discrete input manipulations in the natural language space, which can be directly transferred to…”
Get full text