HM
Haggai Maron
cs.LGcs.AIstat.MLcs.CVcs.NEcs.CLcs.GRcs.DMcs.DScs.SI
On Valency
published · living versionsW_pe7z2qpq·v1 · currentpublished
Positional Encoding is All You Need for Scalable Equivariance Constraint Relaxation
with Hagay Michaeli, Daniel Soudry
1 version
W_b2n7tdwu·v1published
W_7u7j69c3·v1published
Preprints & journals
82 papers in the corpus · 2017–2026Joints, Camera, Action! Co-Generating 3D Motion and Video for Arbitrary Rigs2610.28632v1 · Noam Rotstein, Yoad Tewel, Chen Tessler et al.2026 · 0 citationsarXivon Valency
Improving the Expressive Power of Hybrid Sequence Models via Multi-Hop Retrieval2610.25250v1 · Yam Eitan, Gilad Yehudai, Haggai Maron2026 · 0 citationsarXivon Valency
LEMON: Equivariant Learning over Attention Maps for Zero-Shot Misbehavior Monitoring on New LLMs2610.22723v1 · Guy Bar-Shalom, Mor Geva, Fabrizio Frasca et al.2026 · 0 citationsarXiv
Gray-Box Hallucination Detection in LLMs with Token Identities2610.19996v1 · Shaked Goldshtein, Yitzchak Grunbaum, Fabrizio Frasca et al.2026 · 0 citationsarXiv
Graph Metanetworks for Transformer Based Language Models2610.18471v1 · Yonathan Wolanowsky, Guy Bar-Shalom, Fabrizio Frasca et al.2026 · 0 citationsarXiv
Learning Cross-Model Activation Alignments with Explicit Many-to-Many Layer Maps2610.09058v1 · Alina Sudakov, Guy Bar-Shalom, Fabrizio Frasca et al.2026 · 0 citationsarXiv
CrossGMN: Graph Metanetworks for Cross-Architecture Weight-Space Transformations2610.01649v1 · Adir Dayan, Yam Eitan, Haggai Maron2026 · 0 citationsarXiv
Transferable Graph Metanetworks2610.00420v1 · Yuxin Ma, Adir Dayan, Yam Eitan et al.2026 · 0 citationsarXiv
Finite Probes Suffice: Identifiability and Universality for Weight-Space Learning2609.33901v2 · Soutrik Sarangi, Yonatan Sverdlov, Adir Dayan et al.2026 · 0 citationsarXiv
Permutation-Equivariant Flow Matching for Alignment-Free Neural Weight Generation2609.32833v1 · Arkadi Piven, Yam Eitan, Guy Bar-Shalom et al.2026 · 0 citationsarXiv
UniProbe: A Learnable Token-Level Hallucination Detector for Large VLMs using Multi-Structural Internal Representations2608.10835v1 · Dvir Samuel, Guy Bar-Shalom, Fabrizio Frasca et al.2026 · 0 citationsarXiv
Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning2606.15007v1 · NVIDIA: Aaron Blakeman, Aaron Thomas, Aastha Jhunjhunwala et al.2026 · 0 citationsarXiv
Training Transformers for KV Cache Compressibility2605.05971v2 · Yoav Gelberg, Yam Eitan, Michael Bronstein et al.2026 · 0 citationsarXiv
A Survey of Weight Space Learning: Understanding, Representation, and Generation2603.10090v1 · Xiaolong Han, Zehong Wang, Bo Zhao et al.2026 · 0 citationsarXiv
A Graph Meta-Network for Learning on Kolmogorov-Arnold Networks2602.16316v2 · Guy Bar-Shalom, Ami Tavory, Itay Evron et al.2026 · 0 citationsarXiv
Spanning the Visual Analogy Space with a Weight Basis of LoRAs2602.15727v2 · Hila Manor, Rinon Gal, Haggai Maron et al.2026 · 0 citationsarXiv
SHINE: A Scalable In-Context Hypernetwork for Mapping Context to LoRA in a Single Pass2602.06358v4 · Yewei Liu, Xiyuan Wang, Yansheng Mao et al.2026 · 0 citationsarXiv
On the Expressive Power of Permutation-Equivariant Weight-Space Networks2602.01083v2 · Adir Dayan, Yam Eitan, Haggai Maron2026 · 0 citationsarXiv
Learning from Historical Activations in Graph Neural Networks2601.01123v2 · Yaniv Galron, Hadar Sinai, Haggai Maron et al.2026 · 0 citationsarXiv
On The Expressive Power of GNN Derivatives2510.02565v1 · Yam Eitan, Moshe Eliasof, Yoav Gelberg et al.2025 · 0 citationsarXiv
Beyond Token Probes: Hallucination Detection via Activation Tensors with ACT-ViT2510.00296v1 · Guy Bar-Shalom, Fabrizio Frasca, Yaniv Galron et al.2025 · 0 citationsarXiv
FS-KAN: Permutation Equivariant Kolmogorov-Arnold Networks via Function Sharing2509.24472v3 · Ran Elbaz, Guy Bar-Shalom, Yam Eitan et al.2025 · 0 citationsarXiv
Neural Message-Passing on Attention Graphs for Hallucination Detection2509.24770v2 · Fabrizio Frasca, Guy Bar-Shalom, Yftah Ziser et al.2025 · 0 citationsarXiv
GradMetaNet: An Equivariant Architecture for Learning on Gradients2507.01649v2 · Yoav Gelberg, Yam Eitan, Aviv Navon et al.2025 · 0 citationsarXiv
Understanding and Improving Laplacian Positional Encodings For Temporal GNNs2506.01596v1 · Yaniv Galron, Fabrizio Frasca, Haggai Maron et al.2025 · 2 citationsarXiv
It Takes a Graph to Know a Graph: Rewiring for Homophily with a Reference Graph2505.12411v1 · Harel Mendelman, Haggai Maron, Ronen Talmon2025 · 1 citationarXiv
Efficient GNN Training Through Structure-Aware Randomized Mini-Batching2504.18082v1 · Vignesh Balaji, Christos Kozyrakis, Gal Chechik et al.2025 · 0 citationsarXiv
Beyond Next Token Probabilities: Learnable, Fast Detection of Hallucinations and Data Contamination on LLM Output Distributions2503.14043v3 · Guy Bar-Shalom, Fabrizio Frasca, Derek Lim et al.2025 · 0 citationsarXiv
Homomorphism Expressivity of Spectral Invariant Graph Neural Networks2503.00485v1 · Jingchu Gai, Yiheng Du, Bohang Zhang et al.2025 · 0 citationsICLR 2025 Oral
Balancing Efficiency and Expressiveness: Subgraph GNNs with Walk-Based Centrality2501.03113v2 · Joshua Southern, Yam Eitan, Guy Bar-Shalom et al.2025 · 0 citationsarXiv
Towards Foundation Models on Graphs: An Analysis on Cross-Dataset Transfer of Pretrained GNNs2412.17609v1 · Fabrizio Frasca, Fabian Jogl, Moshe Eliasof et al.2024 · 0 citationsarXiv
On the Reconstruction of Training Data from Group Invariant Networks2411.16458v1 · Ran Elbaz, Gilad Yehudai, Meirav Galun et al.2024 · 0 citationsarXiv
Learning on LoRAs: GL-Equivariant Processing of Low-Rank Weight Spaces for Large Finetuned Models2410.04207v2 · Theo Putterman, Derek Lim, Yoav Gelberg et al.2024 · 0 citationsarXiv
Foldable SuperNets: Scalable Merging of Transformers with Different Initializations and Tasks2410.01483v2 · Edan Kinderman, Itay Hubara, Haggai Maron et al.2024 · 0 citationsTransactions on Machine Learning Research, 2025
Topological Blindspots: Understanding and Extending Topological Deep Learning Through the Lens of Expressivity2408.05486v2 · Yam Eitan, Yoav Gelberg, Guy Bar-Shalom et al.2024 · 0 citationsarXiv
A Flexible, Equivariant Framework for Subgraph GNNs via Graph Products and Graph Coarsening2406.09291v4 · Guy Bar-Shalom, Yam Eitan, Fabrizio Frasca et al.2024 · 2 citationsarXiv
On the Expressive Power of Spectral Invariant Graph Neural Networks2406.04336v1 · Bohang Zhang, Lingxiao Zhao, Haggai Maron2024 · 1 citationarXiv
The Empirical Impact of Neural Parameter Symmetries, or Lack Thereof2405.20231v3 · Derek Lim, Theo Moe Putterman, Robin Walters et al.2024 · 0 citationsarXiv
GRANOLA: Adaptive Normalization for Graph Neural Networks2404.13344v2 · Moshe Eliasof, Beatrice Bevilacqua, Carola-Bibiane Schonlieb et al.2024 · 2 citationsarXiv
Fast Encoder-Based 3D from Casual Videos via Point Track Processing2404.07097v2 · Yoni Kasten, Wuyue Lu, Haggai Maron2024 · 4 citationsarXiv
Subgraphormer: Unifying Subgraph GNNs and Graph Transformers via Graph Products2402.08450v2 · Guy Bar-Shalom, Beatrice Bevilacqua, Haggai Maron2024 · 1 citationarXiv
Improved Generalization of Weight Space Networks via Augmentations2402.04081v2 · Aviv Shamsian, Aviv Navon, David W. Zhang et al.2024 · 1 citationarXiv
Future Directions in the Theory of Graph Machine Learning2402.02287v4 · Christopher Morris, Fabrizio Frasca, Nadav Dym et al.2024 · 0 citationsarXiv
Graph Metanetworks for Processing Diverse Neural Architectures2312.04501v2 · Derek Lim, Haggai Maron, Marc T. Law et al.2023 · 2 citationsarXiv
Expressive Sign Equivariant Networks for Spectral Geometric Learning2312.02339v1 · Derek Lim, Joshua Robinson, Stefanie Jegelka et al.2023 · 4 citationsarXiv
Data Augmentations in Deep Weight Spaces2311.08851v1 · Aviv Shamsian, David W. Zhang, Aviv Navon et al.2023 · 0 citationsarXiv
Efficient Subgraph GNNs by Learning Effective Selection Policies2310.20082v2 · Beatrice Bevilacqua, Moshe Eliasof, Eli Meirom et al.2023 · 2 citationsarXiv
Equivariant Deep Weight Space Alignment2310.13397v4 · Aviv Navon, Aviv Shamsian, Ethan Fetaya et al.2023 · 0 citationsarXiv
Norm-guided latent space exploration for text-to-image generation2306.08687v3 · Dvir Samuel, Rami Ben-Ari, Nir Darshan et al.2023 · 6 citationsarXiv
Hierarchical Graph Neural Network with Cross-Attention for Cross-Device User Matching2304.03215v2 · Ali Taghibakhshi, Mingyuan Ma, Ashwath Aithal et al.2023 · 1 citationarXiv
Career total: 95 works. 82 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.