Stephan Günnemann

Joint Out-of-Distribution Filtering and Data Discovery Active Learning CVPR 2025 Finding Dino: A Plug-and-Play Framework for Zero-Shot Detection of Out-of-Distribution Objects using Prototypes WACV 2025 The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence ICML 2025 Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting ICML 2025 Enforcing Latent Euclidean Geometry in Single-Cell VAEs for Manifold Interpolation ICML 2025 UnHiPPO: Uncertainty-aware Initialization for State Space Models ICML 2025 Efficient Time Series Processing for Transformers and State-Space Models through Token Merging ICML 2025 REINFORCE Adversarial Attacks on Large Language Models: An Adaptive, Distributional, and Semantic Objective ICML 2025 Uncertainty Estimation for Heterophilic Graphs Through the Lens of Information Theory ICML 2025 A Probabilistic Perspective on Unlearning and Alignment for Large Language Models ICLR 2025 Learning Equivariant Non-Local Electron Density Functionals ICLR 2025 MAGNet: Motif-Agnostic Generation of Molecules from Scaffolds ICLR 2025 Graph Neural Networks for Edge Signals: Orientation Equivariance and Invariance ICLR 2025 Flow Matching with Gaussian Process Priors for Probabilistic Time Series Forecasting ICLR 2025 Provably Reliable Conformal Prediction Sets in the Presence of Data Poisoning ICLR 2025 Exact Certification of (Graph) Neural Networks Against Label Poisoning ICLR 2025 Lift Your Molecules: Molecular Graph Generation in Latent Euclidean Space ICLR 2025 Unlocking Point Processes through Point Set Diffusion ICLR 2025 GeoDiffusion: A Training-Free Framework for Accurate 3D Geometric Conditioning in Image Generation ICCV 2025 Prior2Former - Evidential Modeling of Mask Transformers for Assumption-Free Open-World Panoptic Segmentation ICCV 2025 Expressivity and Generalization: Fragment-Biases for Molecular GNNs ICML 2024 Efficient Adversarial Training in LLMs with Continuous Attacks NIPS 2024 Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space NIPS 2024 Expected Probabilistic Hierarchies NIPS 2024 Shaving Weights with Occam's Razor: Bayesian Sparsification for Neural Networks using the Marginal Likelihood NIPS 2024 Energy-based Epistemic Uncertainty for Graph Neural Networks NIPS 2024 Spatio-Spectral Graph Neural Networks NIPS 2024 Unified Mechanism-Specific Amplification by Subsampling and Group Privacy Amplification NIPS 2024 Neural Pfaffians: Solving Many Many-Electron Schrödinger Equations NIPS 2024 Unified Guidance for Geometry-Conditioned Molecular Generation NIPS 2024 From Zero to Turbulence: Generative Modeling for 3D Flow Simulation ICLR 2024 Uncertainty for Active Learning on Graphs ICML 2024 Guaranteeing Robustness Against Real-World Perturbations In Time Series Classification Using Conformalized Randomized Smoothing UAI 2024 Transformers Meet Directed Graphs ICML 2023 Provable Adversarial Robustness for Group Equivariant Tasks: Graphs, Point Clouds, Molecules, and More NIPS 2023 Adversarial Training for Graph Neural Networks: Pitfalls, Solutions, and New Directions NIPS 2023 Uncertainty Estimation for Molecules: Desiderata and Methods ICML 2023 Ewald-based Long-Range Message Passing for Molecular Graphs ICML 2023 Generalizing Neural Wave Functions ICML 2023 Unveiling the sampling density in non-uniform geometric graphs ICLR 2023 Revisiting Robustness in Graph Machine Learning ICLR 2023 Sampling-free Inference for Ab-Initio Potential Energy Surface Networks ICLR 2023 Localized Randomized Smoothing for Collective Robustness Certification ICLR 2023 Hierarchical Randomized Smoothing NIPS 2023 Modeling Temporal Data as Continuous Functions with Stochastic Process Diffusion ICML 2023 Topology-Matching Normalizing Flows for Out-of-Distribution Detection in Robot Learning CORL 2023 Add and Thin: Diffusion for Temporal Point Processes NIPS 2023 Predicting Cellular Responses to Novel Drug Perturbations at a Single-Cell Resolution NIPS 2022 Intriguing Properties of Input-Dependent Randomized Smoothing ICML 2022 3D Infomax improves GNNs for Molecular Property Prediction ICML 2022 Winning the Lottery Ahead of Time: Efficient Early Network Pruning ICML 2022 Domain Reconstruction for UWB Car Key Localization Using Generative Adversarial Networks AAAI 2022 Differentiable DAG Sampling ICLR 2022 End-to-End Learning of Probabilistic Hierarchies on Graphs ICLR 2022 Generalization of Neural Combinatorial Solvers Through the Lens of Adversarial Robustness ICLR 2022 Ab-Initio Potential Energy Surfaces by Pairing GNNs with Neural Wave Functions ICLR 2022 Natural Posterior Network: Deep Bayesian Predictive Uncertainty for Exponential Family Distributions ICLR 2022 Learning the Dynamics of Physical Systems from Sparse Observations with Finite Element Networks ICLR 2022 Invariance-Aware Randomized Smoothing Certificates NIPS 2022 Randomized Message-Interception Smoothing: Gray-box Certificates for Graph Neural Networks NIPS 2022 Are Defenses for Graph Neural Networks Robust? NIPS 2022 Scalable Normalizing Flows for Permutation Invariant Densities ICML 2021 Completing the Picture: Randomized Smoothing Suffers from the Curse of Dimensionality for a Large Family of Distributions AISTATS 2021 Collective Robustness Certificates: Exploiting Interdependence in Graph Neural Networks ICLR 2021 Language-Agnostic Representation Learning of Source Code from Structure and Context ICLR 2021 Neural Temporal Point Processes: A Review IJCAI 2021 Neural Flows: Efficient Alternative to Neural ODEs NIPS 2021 Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification NIPS 2021 Directional Message Passing on Molecular Graphs via Synthetic Coordinates NIPS 2021 Detecting Anomalous Event Sequences with Temporal Point Processes NIPS 2021 Robustness of Graph Neural Networks at Scale NIPS 2021 Scalable Optimal Transport in High Dimensions for Graph Distances, Embedding Alignment, and More ICML 2021 Evaluating Robustness of Predictive Uncertainty Estimation: Are Dirichlet-based Models Reliable? ICML 2021 GemNet: Universal Directional Graph Neural Networks for Molecules NIPS 2021 Fast and Flexible Temporal Point Processes with Triangular Maps NIPS 2020 Directional Message Passing for Molecular Graphs ICLR 2020 Efficient Robustness Certificates for Discrete Data: Sparsity-Aware Randomized Smoothing for Graphs, Images and More ICML 2020 Deep Rao-Blackwellised Particle Filters for Time Series Forecasting NIPS 2020 Reliable Graph Neural Networks via Robust Aggregation NIPS 2020 Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Counts NIPS 2020 Intensity-Free Learning of Temporal Point Processes ICLR 2020 Continual Learning with Bayesian Neural Networks for Non-Stationary Data ICLR 2020 Multi-Source Neural Variational Inference AAAI 2019 Adversarial Attacks on Graph Neural Networks via Meta Learning ICLR 2019 Predict then Propagate: Graph Neural Networks meet Personalized PageRank ICLR 2019 Uncertainty on Asynchronous Time Event Prediction NIPS 2019 Diffusion Improves Graph Learning NIPS 2019 Adversarial Attacks on Node Embeddings via Graph Poisoning ICML 2019 Certifiable Robustness to Graph Perturbations NIPS 2019 Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift NIPS 2019 Adversarial Attacks on Neural Networks for Graph Data IJCAI 2019 Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking ICLR 2018 NetGAN: Generating Graphs via Random Walks ICML 2018 Preferential Attachment in Graphs with Affinities AISTATS 2015