Carola-Bibiane Schönlieb

Bridging Input Feature Spaces Towards Graph Foundation Models

Towards Improved Sentence Representations using Token Graphs

A Sensitivity Analysis of State-Space Models on Graphs

Mind the Gap: Transferring Labels Across Datasets with Divergent Annotation Protocols

Flow Matching on Unordered Sets

Graph Neural Dynamics via Learned Energy and Tangential Flows

GeoSplat: A Deep Dive into Geometry-Constrained Gaussian Splatting

Adaptive Correction Mechanism for Ensuring Conservation Laws in Neural Operators

PDE Solvers Should Be Local: Fast, Stable Rollouts with Learned Local Stencils

Return of ChebNet: Understanding and Improving an Overlooked GNN on Long Range Tasks

Approximation theory for 1-Lipschitz ResNets

D2SA: Dual-Stage Distribution and Slice Adaptation for Efficient Test-Time Adaptation in MRI Reconstruction

Estimation of single-cell and tissue perturbation effect in spatial transcriptomics via Spatial Causal Disentanglement

Score-based Pullback Riemannian Geometry: Extracting the Data Manifold Geometry using Anisotropic Flows

Graph Adaptive Autoregressive Moving Average Models

Lie Algebra Canonicalization: Equivariant Neural Operators under arbitrary Lie Groups

GRAMA: Adaptive Graph Autoregressive Moving Average Models

G-Adaptivity: optimised graph-based mesh relocation for finite element methods

Blessing of Dimensionality for Approximating Sobolev Classes on Manifolds

Score-based pullback Riemannian geometry

FedMAP: Unlocking Potential in Personalized Federated Learning through Bi-Level MAP Optimization

Bellman Diffusion: Generative Modeling as Learning a Linear Operator in the Distribution Space

Pullback Flow Matching on Data Manifolds

Mamba Neural Operator: Who Wins? Transformers vs. State-Space Models for PDEs