{"total":17,"rows":[{"id":"2506.13018","title":"Symmetry in Neural Network Parameter Spaces","created":"2025-06-16","cited_by_count":36,"area":null},{"id":"2502.00264","title":"Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion","created":"2025-02-01","cited_by_count":16,"area":null},{"id":"2605.03601","title":"Most ReLU Networks Admit Identifiable Parameters","created":"2026-05-05","cited_by_count":6,"area":null},{"id":"2503.11050","title":"Distance-Based Tree-Sliced Wasserstein Distance","created":"2025-03-14","cited_by_count":4,"area":null},{"id":"2503.00687","title":"Transformer Meets Twicing: Harnessing Unattended Residual Information","created":"2025-03-02","cited_by_count":3,"area":null},{"id":"2505.00968","title":"Tree-Sliced Wasserstein Distance with Nonlinear Projection","created":"2025-05-02","cited_by_count":3,"area":null},{"id":"2503.11249","title":"Spherical Tree-Sliced Wasserstein Distance","created":"2025-03-14","cited_by_count":2,"area":null},{"id":"2506.12041","title":"Meta Pruning via Graph Metanetworks : A Universal Meta Learning Framework for Network Pruning","created":"2025-05-24","cited_by_count":2,"area":null},{"id":"2602.16316","title":"A Graph Meta-Network for Learning on Kolmogorov-Arnold Networks","created":"2026-02-18","cited_by_count":2,"area":null},{"id":"2608.03294","title":"Provably Learning Multi-Head Attention with Queries","created":"2026-08-04","cited_by_count":2,"area":null},{"id":"2604.23720","title":"Quasi-Equivariant Metanetworks","created":"2026-04-26","cited_by_count":1,"area":null},{"id":"2511.12601","title":"Symmetry-Aware Graph Metanetwork Autoencoders: Model Merging through Parameter Canonicalization","created":"2025-11-16","cited_by_count":0,"area":null},{"id":"2512.15469","title":"Metanetworks as Regulatory Operators: Learning to Edit for Requirement Compliance","created":"2025-12-17","cited_by_count":0,"area":null},{"id":"2609.33901","title":"Finite Probes Suffice: Identifiability and Universality for Weight-Space Learning","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.34549","title":"On Parameter Symmetries and Conservation Laws in Gradient Flow","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.01649","title":"CrossGMN: Graph Metanetworks for Cross-Architecture Weight-Space Transformations","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.18471","title":"Graph Metanetworks for Transformer Based Language Models","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}