Haggai Maron

Affiliations

NVIDIA Research

papers

411

total citations

papers (17)

Topological Blindspots: Understanding and Extending Topological Deep Learning Through the Lens of Expressivity

ICLR 2025arXiv

citations

Subgraphormer: Unifying Subgraph GNNs and Graph Transformers via Graph Products

ICML 2024arXiv

citations

Balancing Efficiency and Expressiveness: Subgraph GNNs with Walk-Based Centrality

ICML 2025arXiv

citations

Homomorphism Expressivity of Spectral Invariant Graph Neural Networks

ICLR 2025arXiv

citations

GradMetaNet: An Equivariant Architecture for Learning on Gradients

NEURIPS 2025arXiv

citations

Beyond Token Probes: Hallucination Detection via Activation Tensors with ACT-ViT

NEURIPS 2025arXiv

citations

Position: Future Directions in the Theory of Graph Machine Learning

ICML 2024

citations

Haggai Maron

Affiliations

papers (17)

Understanding and Extending Subgraph GNNs by Rethinking Their Symmetries

Norm-guided latent space exploration for text-to-image generation

Set2Graph: Learning Graphs From Sets

Equivariant Deep Weight Space Alignment

Deep Permutation Equivariant Structure From Motion

Expressive Sign Equivariant Networks for Spectral Geometric Learning

Improved Generalization of Weight Space Networks via Augmentations

Efficient Subgraph GNNs by Learning Effective Selection Policies

Lightning-Fast Image Inversion and Editing for Text-to-Image Diffusion Models

On the Expressive Power of Spectral Invariant Graph Neural Networks

Topological Blindspots: Understanding and Extending Topological Deep Learning Through the Lens of Expressivity

Subgraphormer: Unifying Subgraph GNNs and Graph Transformers via Graph Products

Balancing Efficiency and Expressiveness: Subgraph GNNs with Walk-Based Centrality

Homomorphism Expressivity of Spectral Invariant Graph Neural Networks

GradMetaNet: An Equivariant Architecture for Learning on Gradients

Beyond Token Probes: Hallucination Detection via Activation Tensors with ACT-ViT

Position: Future Directions in the Theory of Graph Machine Learning

papers (17)

Understanding and Extending Subgraph GNNs by Rethinking Their Symmetries

Norm-guided latent space exploration for text-to-image generation

Set2Graph: Learning Graphs From Sets

Equivariant Deep Weight Space Alignment

Deep Permutation Equivariant Structure From Motion

Expressive Sign Equivariant Networks for Spectral Geometric Learning

Improved Generalization of Weight Space Networks via Augmentations

Efficient Subgraph GNNs by Learning Effective Selection Policies

Lightning-Fast Image Inversion and Editing for Text-to-Image Diffusion Models

On the Expressive Power of Spectral Invariant Graph Neural Networks

Topological Blindspots: Understanding and Extending Topological Deep Learning Through the Lens of Expressivity

Subgraphormer: Unifying Subgraph GNNs and Graph Transformers via Graph Products

Balancing Efficiency and Expressiveness: Subgraph GNNs with Walk-Based Centrality

Homomorphism Expressivity of Spectral Invariant Graph Neural Networks

GradMetaNet: An Equivariant Architecture for Learning on Gradients

Beyond Token Probes: Hallucination Detection via Activation Tensors with ACT-ViT

Position: Future Directions in the Theory of Graph Machine Learning