Stephan Günnemann

14

Papers

93

Total Citations

Papers (14)

From Zero to Turbulence: Generative Modeling for 3D Flow Simulation

A Probabilistic Perspective on Unlearning and Alignment for Large Language Models

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

Enforcing Latent Euclidean Geometry in Single-Cell VAEs for Manifold Interpolation

Unlocking Point Processes through Point Set Diffusion

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

Exact Certification of (Graph) Neural Networks Against Label Poisoning

Provably Reliable Conformal Prediction Sets in the Presence of Data Poisoning

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

MAGNet: Motif-Agnostic Generation of Molecules from Scaffolds

Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting

GeoDiffusion: A Training-Free Framework for Accurate 3D Geometric Conditioning in Image Generation

Expressivity and Generalization: Fragment-Biases for Molecular GNNs

Uncertainty for Active Learning on Graphs