Picture for Stephan Günnemann

Stephan Günnemann

Accurate Ab-initio Neural-network Solutions to Large-Scale Electronic Structure Problems

Add code
Apr 08, 2025
Viaarxiv icon

Prior2Former -- Evidential Modeling of Mask Transformers for Assumption-Free Open-World Panoptic Segmentation

Add code
Apr 07, 2025
Viaarxiv icon

LipShiFT: A Certifiably Robust Shift-based Vision Transformer

Add code
Mar 18, 2025
Viaarxiv icon

LLM-Safety Evaluations Lack Robustness

Add code
Mar 04, 2025
Viaarxiv icon

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

Add code
Mar 04, 2025
Viaarxiv icon

REINFORCE Adversarial Attacks on Large Language Models: An Adaptive, Distributional, and Semantic Objective

Add code
Feb 24, 2025
Viaarxiv icon

The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence

Add code
Feb 24, 2025
Viaarxiv icon

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

Add code
Feb 17, 2025
Viaarxiv icon

Generative Modeling with Bayesian Sample Inference

Add code
Feb 11, 2025
Viaarxiv icon

Rethinking Link Prediction for Directed Graphs

Add code
Feb 08, 2025
Viaarxiv icon