Leo Schwinn

Orcid: 0000-0003-3967-2202

According to our database¹, Leo Schwinn authored at least 52 papers between 2020 and 2025.

Collaborative distances:

Dijkstra number² of five.
Erdős number³ of four.

Timeline

Legend:

Book

In proceedings

Article

PhD thesis

Dataset

Other

Bibliography

2025

Artificial intelligence trend analysis in German business and politics: a web mining approach.

[BibT_eX]

[DOI]

Int. J. Data Sci. Anal., August, 2025

Investigating the Robustness of Retrieval-Augmented Generation at the Query Level.

[BibT_eX]

[DOI]

CoRR, July, 2025

Tail-aware Adversarial Attacks: A Distributional Approach to Efficient LLM Jailbreaking.

[BibT_eX]

[DOI]

CoRR, July, 2025

Model Collapse Is Not a Bug but a Feature in Machine Unlearning for LLMs.

[BibT_eX]

[DOI]

CoRR, July, 2025

FOCUS: Internal MLLM Representations for Efficient Fine-Grained Visual Question Answering.

[BibT_eX]

[DOI]

CoRR, June, 2025

Effective Data Pruning through Score Extrapolation.

[BibT_eX]

[DOI]

CoRR, June, 2025

Joint Relational Database Generation via Graph-Conditional Diffusion Models.

[BibT_eX]

[DOI]

CoRR, May, 2025

Byte Pair Encoding for Efficient Time Series Forecasting.

[BibT_eX]

[DOI]

CoRR, May, 2025

Understanding Cross-Model Perceptual Invariances Through Ensemble Metamers.

[BibT_eX]

[DOI]

CoRR, April, 2025

LLM-Safety Evaluations Lack Robustness.

[BibT_eX]

[DOI]

CoRR, March, 2025

A generative approach to LLM harmfulness detection with special red flag tokens.

[BibT_eX]

[DOI]

CoRR, February, 2025

Adversarial Alignment for LLMs Requires Simpler, Reproducible, and More Measurable Objectives.

[BibT_eX]

[DOI]

CoRR, February, 2025

Fast Proxies for LLM Robustness Evaluation.

[BibT_eX]

[DOI]

CoRR, February, 2025

A Unified Approach Towards Active Learning and Out-of-Distribution Detection.

[BibT_eX]

[DOI]

Trans. Mach. Learn. Res., 2025

A Probabilistic Perspective on Unlearning and Alignment for Large Language Models.

[BibT_eX]

[DOI]

Yan Scholten

Stephan Günnemann

Leo Schwinn

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Flow Matching with Gaussian Process Priors for Probabilistic Time Series Forecasting.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Joint Out-of-Distribution Filtering and Data Discovery Active Learning.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

2024

Generalized Synchronized Active Learning for Multi-Agent-Based Data Selection on Mobile Robotic Systems.

[BibT_eX]

[DOI]

IEEE Robotics Autom. Lett., October, 2024

Artificial intelligence trend analysis on healthcare podcasts using topic modeling and sentiment analysis: a data-driven approach.

[BibT_eX]

[DOI]

Evol. Intell., August, 2024

Assessing Robustness via Score-Based Adversarial Image Generation.

[BibT_eX]

[DOI]

Trans. Mach. Learn. Res., 2024

Extracting Unlearned Information from LLMs with Activation Steering.

[BibT_eX]

[DOI]

CoRR, 2024

Caption-Driven Explorations: Aligning Image and Text Embeddings through Human-Inspired Foveated Vision.

[BibT_eX]

[DOI]

Mark A. Turban Ndjeuha

Leo Schwinn

Björn M. Eskofier

CoRR, 2024

Revisiting the Robust Alignment of Circuit Breakers.

[BibT_eX]

[DOI]

Leo Schwinn

Simon Geisler

CoRR, 2024

Relaxing Graph Transformers for Adversarial Attacks.

[BibT_eX]

[DOI]

CoRR, 2024

Large-Scale Dataset Pruning in Adversarial Training through Data Importance Extrapolation.

[BibT_eX]

[DOI]

CoRR, 2024

Efficient Time Series Processing for Transformers and State-Space Models through Token Merging.

[BibT_eX]

[DOI]

CoRR, 2024

Efficient Adversarial Training in LLMs with Continuous Attacks.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

On the Scalability of Certified Adversarial Robustness with Generated Data.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

2023

Exploring misclassifications of robust neural networks to enhance adversarial attacks.

[BibT_eX]

[DOI]

Appl. Intell., September, 2023

Detektion, Quantifikation und Mitigation von Robustheitsanfälligkeiten in Tiefen Neuronalen Netzen.

[BibT_eX]

[DOI]

Leo Schwinn

PhD thesis, 2023

Contrastive Language-Image Pretrained Models are Zero-Shot Human Scanpath Predictors.

[BibT_eX]

[DOI]

Mark A. Turban Ndjeuha

Leo Schwinn

Bjoern M. Eskofier

CoRR, 2023

Raising the Bar for Certified Adversarial Robustness with Diffusion Models.

[BibT_eX]

[DOI]

CoRR, 2023

Just a Matter of Scale? Reevaluating Scale Equivariance in Convolutional Neural Networks.

[BibT_eX]

[DOI]

Christopher Mutschler

Björn M. Eskofier

Dario Zanca

Proceedings of the International Joint Conference on Neural Networks, 2023

Adversarial Attacks and Defenses in Large Language Models: Old and New Threats.

[BibT_eX]

[DOI]

Proceedings of the Proceedings on "I Can't Believe It's Not Better: Failure Modes in the Age of Foundation Models" at NeurIPS 2023 Workshops, 2023

FastAMI - a Monte Carlo Approach to the Adjustment for Chance in Clustering Comparison Metrics.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023

2022

Scaled and Translated Image Recognition (STIR) Source Data.

[BibT_eX]

[DOI]

Christopher Mutschler

Björn M. Eskofier

Dario Zanca

Dataset, November, 2022

Scaled and Translated Image Recognition (STIR).

[BibT_eX]

[DOI]

Christopher Mutschler

Björn M. Eskofier

Dario Zanca

Dataset, November, 2022

Behind the Machine's Gaze: Neural Networks with Biologically-inspired Constraints Exhibit Human-like Visual Attention.

[BibT_eX]

[DOI]

Trans. Mach. Learn. Res., 2022

xLength: Predicting Expected Ski Jump Length Shortly after Take-Off Using Deep Learning.

[BibT_eX]

[DOI]

Sensors, 2022

Simulating Human Gaze with Neural Visual Attention.

[BibT_eX]

[DOI]

CoRR, 2022

Behind the Machine's Gaze: Biologically Constrained Neural Networks Exhibit Human-like Visual Attention.

[BibT_eX]

[DOI]

CoRR, 2022

Improving Robustness against Real-World and Worst-Case Distribution Shifts through Decision Region Quantification.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

2021

System Design for a Data-driven and Explainable Customer Sentiment Monitor.

[BibT_eX]

[DOI]

CoRR, 2021

System Design for a Data-Driven and Explainable Customer Sentiment Monitor Using IoT and Enterprise Data.

[BibT_eX]

[DOI]

IEEE Access, 2021

Identifying untrustworthy predictions in neural networks by geometric gradient analysis.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence, 2021

CLIP: Cheap Lipschitz Training of Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the Scale Space and Variational Methods in Computer Vision, 2021

Dynamically Sampled Nonlocal Gradients for Stronger Adversarial Attacks.

[BibT_eX]

[DOI]

Proceedings of the International Joint Conference on Neural Networks, 2021

2020

Sampled Nonlocal Gradients for Stronger Adversarial Attacks.

[BibT_eX]

[DOI]

CoRR, 2020

Conformance Checking for a Medical Training Process Using Petri net Simulation and Sequence Alignment.

[BibT_eX]

[DOI]

CoRR, 2020

Fast and Stable Adversarial Training through Noise Injection.

[BibT_eX]

[DOI]

Leo Schwinn

Björn M. Eskofier

CoRR, 2020

Time Matters: Time-Aware LSTMs for Predictive Business Process Monitoring.

[BibT_eX]

[DOI]

Proceedings of the Process Mining Workshops, 2020

Leo Schwinn

Timeline

Legend:

Links

Online presence:

On csauthors.net:

Bibliography

Loading...