Mathias Niepert

papers

740

total citations

papers (18)

PDEBench: An Extensive Benchmark for Scientific Machine Learning

NEURIPS 2022arXiv

352

citations

Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions

NEURIPS 2021arXiv

109

citations

LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matching

NEURIPS 2023arXiv

citations

Adaptive Message Passing: A General Framework to Mitigate Oversmoothing, Oversquashing, and Underreaching

ICML 2025arXiv

citations

Learning to Discretize Denoising Diffusion ODEs

ICLR 2025arXiv

citations

Vectorized Conditional Neural Fields: A Framework for Solving Time-dependent Parametric Partial Differential Equations

ICML 2024arXiv

citations

Structure-Aware E(3)-Invariant Molecular Conformer Aggregation Networks

ICML 2024arXiv

citations

ExGra-Med: Extended Context Graph Alignment for Medical Vision-Language Models

NEURIPS 2025arXiv

citations

Efficient Learning of Discrete-Continuous Computation Graphs

NEURIPS 2021arXiv

citations

Learning (Approximately) Equivariant Networks via Constrained Optimization

NEURIPS 2025arXiv

citations

CALM-PDE: Continuous and Adaptive Convolutions for Latent Space Modeling of Time-dependent PDEs

NEURIPS 2025arXiv

citations

Rao-Blackwell Gradient Estimators for Equivariant Denoising Diffusion

NEURIPS 2025arXiv

citations

How Many Tokens Do 3D Point Cloud Transformer Architectures Really Need?

NEURIPS 2025arXiv

citations

Physics-Informed Weakly Supervised Learning For Interatomic Potentials

ICML 2025arXiv

citations

Tractable Transformers for Flexible Conditional Generation

ICML 2025arXiv

citations

Mathias Niepert

papers (18)

PDEBench: An Extensive Benchmark for Scientific Machine Learning

Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions

LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matching

Ordered Subgraph Aggregation Networks

Image Inpainting via Tractable Steering of Diffusion Models

Probabilistically Rewired Message-Passing Neural Networks

Adaptive Message Passing: A General Framework to Mitigate Oversmoothing, Oversquashing, and Underreaching

Learning to Discretize Denoising Diffusion ODEs

Vectorized Conditional Neural Fields: A Framework for Solving Time-dependent Parametric Partial Differential Equations

Structure-Aware E(3)-Invariant Molecular Conformer Aggregation Networks

ExGra-Med: Extended Context Graph Alignment for Medical Vision-Language Models

Efficient Learning of Discrete-Continuous Computation Graphs

Learning (Approximately) Equivariant Networks via Constrained Optimization

CALM-PDE: Continuous and Adaptive Convolutions for Latent Space Modeling of Time-dependent PDEs

Rao-Blackwell Gradient Estimators for Equivariant Denoising Diffusion

How Many Tokens Do 3D Point Cloud Transformer Architectures Really Need?

Physics-Informed Weakly Supervised Learning For Interatomic Potentials

Tractable Transformers for Flexible Conditional Generation

papers (18)

PDEBench: An Extensive Benchmark for Scientific Machine Learning

Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions

LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matching

Ordered Subgraph Aggregation Networks

Image Inpainting via Tractable Steering of Diffusion Models

Probabilistically Rewired Message-Passing Neural Networks

Adaptive Message Passing: A General Framework to Mitigate Oversmoothing, Oversquashing, and Underreaching

Learning to Discretize Denoising Diffusion ODEs

Vectorized Conditional Neural Fields: A Framework for Solving Time-dependent Parametric Partial Differential Equations

Structure-Aware E(3)-Invariant Molecular Conformer Aggregation Networks

ExGra-Med: Extended Context Graph Alignment for Medical Vision-Language Models

Efficient Learning of Discrete-Continuous Computation Graphs

Learning (Approximately) Equivariant Networks via Constrained Optimization

CALM-PDE: Continuous and Adaptive Convolutions for Latent Space Modeling of Time-dependent PDEs

Rao-Blackwell Gradient Estimators for Equivariant Denoising Diffusion

How Many Tokens Do 3D Point Cloud Transformer Architectures Really Need?

Physics-Informed Weakly Supervised Learning For Interatomic Potentials

Tractable Transformers for Flexible Conditional Generation