Leo Schwinn - RankMe

75 papers A* 10A 1B 2Journal 58Unranked 3

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustness. CoRR Leo Schwinn, Moritz Ladenburger, Tim Beyer, Mehrnaz Mofakhami, Gauthier Gidel, Stephan Günnemann
2026	J	`jnl`	A Foundation Model for Virtual Sensors. CoRR Leon Götz, Lars Frederik Peiss, Erik Sauer, Andreas Udo Sass, Thorsten Bagdonat, Stephan Günnemann, Leo Schwinn
2026	J	`jnl`	Closing the Distribution Gap in Adversarial Training for LLMs. CoRR Chengzhi Hu, Jonas Dornbusch, David Lüdke, Stephan Günnemann, Leo Schwinn
2026	J	`jnl`	Contrastive Language-Image Pretrained Models are Zero-Shot Human Scanpath Predictors. IEEE Trans. Artif. Intell. Dario Zanca, Andrea Zugarini, Simon Dietz, Thomas R. Altstidl, Mark A. Turban Ndjeuha, Moumita Chakraborty, Naga Venkata Sai Jitin Jami, Leo Schwinn, Bjoern M. Eskofier
2025	A*	`conf`	A Probabilistic Perspective on Unlearning and Alignment for Large Language Models. ICLR Yan Scholten, Stephan Günnemann, Leo Schwinn
2025	J	`jnl`	A Unified Approach Towards Active Learning and Out-of-Distribution Detection. Trans. Mach. Learn. Res. Sebastian Schmidt, Leonard Schenk, Leo Schwinn, Stephan Günnemann
2025	J	`jnl`	A generative approach to LLM harmfulness detection with special red flag tokens. CoRR Sophie Xhonneux, David Dobre, Mehrnaz Mohfakhami, Leo Schwinn, Gauthier Gidel
2025	J	`jnl`	AdversariaLLM: A Unified and Modular Toolbox for LLM Robustness Research. CoRR Tim Beyer, Jonas Dornbusch, Jakob Steimle, Moritz Ladenburger, Leo Schwinn, Stephan Günnemann
2025	J	`jnl`	Adversarial Alignment for LLMs Requires Simpler, Reproducible, and More Measurable Objectives. CoRR Leo Schwinn, Yan Scholten, Tom Wollschläger, Sophie Xhonneux, Stephen Casper, Stephan Günnemann, Gauthier Gidel
2025	J	`jnl`	Adversarial Robustness of Graph Transformers. Trans. Mach. Learn. Res. Philipp Foth, Lukas Gosch, Simon Geisler, Leo Schwinn, Stephan Günnemann
2025	J	`jnl`	Artificial intelligence trend analysis in German business and politics: a web mining approach. Int. J. Data Sci. Anal. Philipp Dumbach, Leo Schwinn, Tim Löhr, Tassilo Elsberger, Bjoern M. Eskofier
2025	J	`jnl`	Byte Pair Encoding for Efficient Time Series Forecasting. CoRR Leon Götz, Marcel Kollovieh, Stephan Günnemann, Leo Schwinn
2025	J	`jnl`	Diffusion LLMs are Natural Adversaries for any LLM. CoRR David Lüdke, Tom Wollschläger, Paul Ungermann, Stephan Günnemann, Leo Schwinn
2025	J	`jnl`	Effective Data Pruning through Score Extrapolation. CoRR Sebastian Schmidt, Prasanga Dhungel, Christoffer Löffler, Björn Nieth, Stephan Günnemann, Leo Schwinn
2025	A*	`conf`	Efficient Time Series Processing for Transformers and State-Space Models through Token Merging. ICML Leon Götz, Marcel Kollovieh, Stephan Günnemann, Leo Schwinn
2025	J	`jnl`	FOCUS: Internal MLLM Representations for Efficient Fine-Grained Visual Question Answering. CoRR Liangyu Zhong, Fabio Rosenthal, Joachim Sicking, Fabian Hüger, Thorsten Bagdonat, Hanno Gottschalk, Leo Schwinn
2025	J	`jnl`	Fast Proxies for LLM Robustness Evaluation. CoRR Tim Beyer, Jan Schuchardt, Leo Schwinn, Stephan Günnemann
2025	A*	`conf`	Flow Matching with Gaussian Process Priors for Probabilistic Time Series Forecasting. ICLR Marcel Kollovieh, Marten Lienen, David Lüdke, Leo Schwinn, Stephan Günnemann
2025	J	`jnl`	Investigating the Robustness of Retrieval-Augmented Generation at the Query Level. CoRR Sezen Perçin, Xin Su, Syed Sha Qutub, Phillip Howard, Aleksei Kuvshinov, Leo Schwinn, Kay-Ulrich Scholl
2025	A*	`conf`	Joint Out-of-Distribution Filtering and Data Discovery Active Learning. CVPR Sebastian Schmidt, Leonard Schenk, Leo Schwinn, Stephan Günnemann
2025	J	`jnl`	Joint Out-of-Distribution Filtering and Data Discovery Active Learning. CoRR Sebastian Schmidt, Leonard Schenk, Leo Schwinn, Stephan Günnemann
2025	J	`jnl`	Joint Relational Database Generation via Graph-Conditional Diffusion Models. CoRR Mohamed Amine Ketata, David Lüdke, Leo Schwinn, Stephan Günnemann
2025	J	`jnl`	LLM-Safety Evaluations Lack Robustness. CoRR Tim Beyer, Sophie Xhonneux, Simon Geisler, Gauthier Gidel, Leo Schwinn, Stephan Günnemann
2025	J	`jnl`	Model Collapse Is Not a Bug but a Feature in Machine Unlearning for LLMs. CoRR Yan Scholten, Sophie Xhonneux, Leo Schwinn, Stephan Günnemann
2025	J	`jnl`	Tail-aware Adversarial Attacks: A Distributional Approach to Efficient LLM Jailbreaking. CoRR Tim Beyer, Yan Scholten, Leo Schwinn, Stephan Günnemann
2025	J	`jnl`	Understanding Cross-Model Perceptual Invariances Through Ensemble Metamers. CoRR Lukas Boehm, Jonas Leo Mueller, Christoffer Löffler, Leo Schwinn, Björn M. Eskofier, Dario Zanca
2025	J	`jnl`	Unexplored flaws in multiple-choice VQA evaluations. CoRR Fabio Rosenthal, Sebastian Schmidt, Thorsten Graf, Thorsten Bagodonat, Stephan Günnemann, Leo Schwinn
2025	A*	`conf`	When to retrain a machine learning model. ICML Florence Regol, Leo Schwinn, Kyle Sprague, Mark Coates, Thomas Markovich
2025	J	`jnl`	When to retrain a machine learning model. CoRR Florence Regol, Leo Schwinn, Kyle Sprague, Mark Coates, Thomas Markovich
2024	J	`jnl`	A Probabilistic Perspective on Unlearning and Alignment for Large Language Models. CoRR Yan Scholten, Stephan Günnemann, Leo Schwinn
2024	J	`jnl`	A Unified Approach Towards Active Learning and Out-of-Distribution Detection. CoRR Sebastian Schmidt, Leonard Schenk, Leo Schwinn, Stephan Günnemann
2024	J	`jnl`	Artificial intelligence trend analysis on healthcare podcasts using topic modeling and sentiment analysis: a data-driven approach. Evol. Intell. Philipp Dumbach, Leo Schwinn, Tim Löhr, Phi Long Do, Bjoern M. Eskofier
2024	J	`jnl`	Assessing Robustness via Score-Based Adversarial Image Generation. Trans. Mach. Learn. Res. Marcel Kollovieh, Lukas Gosch, Marten Lienen, Yan Scholten, Leo Schwinn, Stephan Günnemann
2024	J	`jnl`	Caption-Driven Explorations: Aligning Image and Text Embeddings through Human-Inspired Foveated Vision. CoRR Dario Zanca, Andrea Zugarini, Simon Dietz, Thomas R. Altstidl, Mark A. Turban Ndjeuha, Leo Schwinn, Björn M. Eskofier
2024	A*	`conf`	Efficient Adversarial Training in LLMs with Continuous Attacks. NeurIPS Sophie Xhonneux, Alessandro Sordoni, Stephan Günnemann, Gauthier Gidel, Leo Schwinn
2024	J	`jnl`	Efficient Adversarial Training in LLMs with Continuous Attacks. CoRR Sophie Xhonneux, Alessandro Sordoni, Stephan Günnemann, Gauthier Gidel, Leo Schwinn
2024	J	`jnl`	Efficient Time Series Processing for Transformers and State-Space Models through Token Merging. CoRR Leon Götz, Marcel Kollovieh, Stephan Günnemann, Leo Schwinn
2024	J	`jnl`	Extracting Unlearned Information from LLMs with Activation Steering. CoRR Atakan Seyitoglu, Aleksei Kuvshinov, Leo Schwinn, Stephan Günnemann
2024	J	`jnl`	Flow Matching with Gaussian Process Priors for Probabilistic Time Series Forecasting. CoRR Marcel Kollovieh, Marten Lienen, David Lüdke, Leo Schwinn, Stephan Günnemann
2024	J	`jnl`	Generalized Synchronized Active Learning for Multi-Agent-Based Data Selection on Mobile Robotic Systems. IEEE Robotics Autom. Lett. Sebastian Schmidt, Lukas Stappen, Leo Schwinn, Stephan Günnemann
2024	J	`jnl`	Large-Scale Dataset Pruning in Adversarial Training through Data Importance Extrapolation. CoRR Björn Nieth, Thomas Altstidl, Leo Schwinn, Björn M. Eskofier
2024	A*	`conf`	On the Scalability of Certified Adversarial Robustness with Generated Data. NeurIPS Thomas Altstidl, David Dobre, Arthur Kosmala, Bjoern M. Eskofier, Gauthier Gidel, Leo Schwinn
2024	J	`jnl`	Relaxing Graph Transformers for Adversarial Attacks. CoRR Philipp Foth, Lukas Gosch, Simon Geisler, Leo Schwinn, Stephan Günnemann
2024	J	`jnl`	Revisiting the Robust Alignment of Circuit Breakers. CoRR Leo Schwinn, Simon Geisler
2024	A*	`conf`	Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space. NeurIPS Leo Schwinn, David Dobre, Sophie Xhonneux, Gauthier Gidel, Stephan Günnemann
2024	J	`jnl`	Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space. CoRR Leo Schwinn, David Dobre, Sophie Xhonneux, Gauthier Gidel, Stephan Günnemann
2023	—	`conf`	Adversarial Attacks and Defenses in Large Language Models: Old and New Threats. ICBINB Leo Schwinn, David Dobre, Stephan Günnemann, Gauthier Gidel
2023	J	`jnl`	Adversarial Attacks and Defenses in Large Language Models: Old and New Threats. CoRR Leo Schwinn, David Dobre, Stephan Günnemann, Gauthier Gidel
2023	J	`jnl`	Contrastive Language-Image Pretrained Models are Zero-Shot Human Scanpath Predictors. CoRR Dario Zanca, Andrea Zugarini, Simon Dietz, Thomas R. Altstidl, Mark A. Turban Ndjeuha, Leo Schwinn, Bjoern M. Eskofier
2023	—	`—`	Detektion, Quantifikation und Mitigation von Robustheitsanfälligkeiten in Tiefen Neuronalen Netzen. Leo Schwinn
2023	J	`jnl`	Exploring misclassifications of robust neural networks to enhance adversarial attacks. Appl. Intell. Leo Schwinn, René Raab, An Nguyen, Dario Zanca, Björn M. Eskofier
2023	A*	`conf`	FastAMI - a Monte Carlo Approach to the Adjustment for Chance in Clustering Comparison Metrics. AAAI Kai Klede, Leo Schwinn, Dario Zanca, Björn M. Eskofier
2023	J	`jnl`	FastAMI - a Monte Carlo Approach to the Adjustment for Chance in Clustering Comparison Metrics. CoRR Kai Klede, Leo Schwinn, Dario Zanca, Björn M. Eskofier
2023	B	`conf`	Just a Matter of Scale? Reevaluating Scale Equivariance in Convolutional Neural Networks. IJCNN Thomas Altstidl, An Nguyen, Leo Schwinn, Franz Köferl, Christopher Mutschler, Björn M. Eskofier, Dario Zanca
2023	J	`jnl`	Raising the Bar for Certified Adversarial Robustness with Diffusion Models. CoRR Thomas Altstidl, David Dobre, Björn M. Eskofier, Gauthier Gidel, Leo Schwinn
2022	J	`jnl`	Behind the Machine's Gaze: Biologically Constrained Neural Networks Exhibit Human-like Visual Attention. CoRR Leo Schwinn, Doina Precup, Björn M. Eskofier, Dario Zanca
2022	J	`jnl`	Behind the Machine's Gaze: Neural Networks with Biologically-inspired Constraints Exhibit Human-like Visual Attention. Trans. Mach. Learn. Res. Leo Schwinn, Doina Precup, Björn M. Eskofier, Dario Zanca
2022	A*	`conf`	Improving Robustness against Real-World and Worst-Case Distribution Shifts through Decision Region Quantification. ICML Leo Schwinn, Leon Bungert, An Nguyen, René Raab, Falk Pulsmeyer, Doina Precup, Bjoern M. Eskofier, Dario Zanca
2022	J	`jnl`	Improving Robustness against Real-World and Worst-Case Distribution Shifts through Decision Region Quantification. CoRR Leo Schwinn, Leon Bungert, An Nguyen, René Raab, Falk Pulsmeyer, Doina Precup, Björn M. Eskofier, Dario Zanca
2022	J	`jnl`	Just a Matter of Scale? Reevaluating Scale Equivariance in Convolutional Neural Networks. CoRR Thomas Altstidl, An Nguyen, Leo Schwinn, Franz Köferl, Christopher Mutschler, Björn M. Eskofier, Dario Zanca
2022	J	`jnl`	Simulating Human Gaze with Neural Visual Attention. CoRR Leo Schwinn, Doina Precup, Björn M. Eskofier, Dario Zanca
2022	J	`jnl`	xLength: Predicting Expected Ski Jump Length Shortly after Take-Off Using Deep Learning. Sensors Johannes Link, Leo Schwinn, Falk Pulsmeyer, Thomas Kautz, Bjoern M. Eskofier
2021	—	`conf`	CLIP: Cheap Lipschitz Training of Neural Networks. SSVM Leon Bungert, René Raab, Tim Roith, Leo Schwinn, Daniel Tenbrinck
2021	J	`jnl`	CLIP: Cheap Lipschitz Training of Neural Networks. CoRR Leon Bungert, René Raab, Tim Roith, Leo Schwinn, Daniel Tenbrinck
2021	B	`conf`	Dynamically Sampled Nonlocal Gradients for Stronger Adversarial Attacks. IJCNN Leo Schwinn, An Nguyen, René Raab, Dario Zanca, Bjoern M. Eskofier, Daniel Tenbrinck, Martin Burger
2021	J	`jnl`	Exploring Misclassifications of Robust Neural Networks to Enhance Adversarial Attacks. CoRR Leo Schwinn, René Raab, An Nguyen, Dario Zanca, Bjoern M. Eskofier
2021	J	`jnl`	Identifying Untrustworthy Predictions in Neural Networks by Geometric Gradient Analysis. CoRR Leo Schwinn, An Nguyen, René Raab, Leon Bungert, Daniel Tenbrinck, Dario Zanca, Martin Burger, Bjoern M. Eskofier
2021	A	`conf`	Identifying untrustworthy predictions in neural networks by geometric gradient analysis. UAI Leo Schwinn, An Nguyen, René Raab, Leon Bungert, Daniel Tenbrinck, Dario Zanca, Martin Burger, Björn M. Eskofier
2021	J	`jnl`	System Design for a Data-Driven and Explainable Customer Sentiment Monitor Using IoT and Enterprise Data. IEEE Access An Nguyen, Stefan Förstel, Thomas Kittler, Andrey Kurzyukov, Leo Schwinn, Dario Zanca, Tobias Hipp, Da Jun Sun, Michael Schrapp, Eva Rothgang, Björn M. Eskofier
2021	J	`jnl`	System Design for a Data-driven and Explainable Customer Sentiment Monitor. CoRR An Nguyen, Stefan Förstel, Thomas Kittler, Andrey Kurzyukov, Leo Schwinn, Dario Zanca, Tobias Hipp, Da Jun Sun, Michael Schrapp, Eva Rothgang, Bjoern M. Eskofier
2020	J	`jnl`	Conformance Checking for a Medical Training Process Using Petri net Simulation and Sequence Alignment. CoRR An Nguyen, Wenyu Zhang, Leo Schwinn, Bjoern M. Eskofier
2020	J	`jnl`	Fast and Stable Adversarial Training through Noise Injection. CoRR Leo Schwinn, Björn M. Eskofier
2020	J	`jnl`	Sampled Nonlocal Gradients for Stronger Adversarial Attacks. CoRR Leo Schwinn, Daniel Tenbrinck, An Nguyen, René Raab, Martin Burger, Bjoern M. Eskofier
2020	—	`conf`	Time Matters: Time-Aware LSTMs for Predictive Business Process Monitoring. ICPM Workshops An Nguyen, Srijeet Chatterjee, Sven Weinzierl, Leo Schwinn, Martin Matzner, Bjoern M. Eskofier
2020	J	`jnl`	Time Matters: Time-Aware LSTMs for Predictive Business Process Monitoring. CoRR An Nguyen, Srijeet Chatterjee, Sven Weinzierl, Leo Schwinn, Martin Matzner, Bjoern M. Eskofier