Haggai Maron

Latest

• Beyond Token Probes: Hallucination Detection via Activation Tensors with ACT-ViT
• GradMetaNet: An Equivariant Architecture for Learning on Gradients
• Balancing Efficiency and Expressiveness: Subgraph GNNs with Walk-Based Centrality
• Foldable SuperNets: Scalable Neural Merging with Different Initialization and Tasks
• Analyzing Large Language Models by Learning on Token Distribution Sequences
• GradMetaNet: An Equivariant Architecture for Learning on Gradients
• Learning on LoRAs: GL-Equivariant Processing of Low-Rank Weight Spaces for Large Finetuned Models
• Directed Graph Generation with Diffusion Kernels
• Lightning-Fast Image Inversion and Editing for Text-to-Image Diffusion Models
• Topological Blindspots: Understanding and Extending Topological Deep Learning Through the Lens of Expressivity
• GL-Equivariant Processing of Low-Rank Weight Spaces
• Homomorphism Expressivity of Spectral Invariant Graph Neural Networks
• A Flexible, Equivariant Framework for Subgraph GNNs via Graph Products and Graph Coarsening
• Fast Encoder-Based 3D from Casual Videos via Point Track Processing
• GRANOLA: Adaptive Normalization for Graph Neural Networks
• The Empirical Impact of Neural Parameter Symmetries, or Lack Thereof
• Equivariant Deep Weight Space Alignment
• Future Directions in Foundations of Graph Machine Learning
• Improved Generalization of Weight Space Networks via Augmentationss
• On the Expressive Power of Spectral Invariant Graph Neural Networks
• Subgraphormer: Unifying Subgraph GNNs and Graph Transformers via Graph Products
• Efficient Subgraph GNNs by Learning Effective Selection Policies
• Graph Metanetworks for Processing Diverse Neural Architectures
• Expressive Sign Equivariant Networks for Spectral Geometric Learning
• Norm-guided latent space exploration for text-to-image generation
• Equivariant Architectures for Learning in Deep Weight Spaces
• Equivariant Polynomials for Graph Neural Networks
• Graph Positional Encoding via Random Feature Propagation
• A Simple and Universal Rotation Equivariant Point-cloud Network
• Sign and Basis Invariant Networks for Spectral Graph Representation Learning
• Understanding and Extending Subgraph GNNs by Rethinking Their Symmetries
• Equivariant Subgraph Aggregation Networks
• Federated Learning with Heterogeneous Architectures using Graph HyperNetworks
• Multi-Task Learning as a Bargaining Game
• Optimizing Tensor Network Contraction Using Reinforcement Learning
• StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators
• From Local Structures to Size Generalization in Graph Neural Networks
• How to Stop Epidemics: Controlling Graph Dynamics with Reinforcement Learning and Graph Neural Networks
• Auxiliary Learning by Implicit Differentiation
• Self-Supervised Learning for Domain Adaptation on Point-Clouds
• On the Universality of Rotation Equivariant Point Cloud Networks
• On Learning Sets of Symmetric Elements