Permutation-Equivariant Flow Matching for Alignment-Free Neural Weight Generation
cs.LG
Submitted: 2026-09-26
Updated: 2026-09-26
Terminology
Sources
- Git Re-Basin: Merging Models modulo Permutation Symmetries
- A Graph Meta-Network for Learning on Kolmogorov-Arnold Networks
- Does equivariance matter at scale?
- On the Expressive Power of Permutation-Equivariant Weight-Space Networks
- Geometric Flow Models over Neural Network Weights
- DeepWeightFlow: Re-Basined Flow Matching for Generating Neural Network Weights
- HyperNetworks
- A Survey of Weight Space Learning: Understanding, Representation, and Generation
- Classifier-Free Diffusion Guidance
- NNiT: Width-Agnostic Neural Network Generation with Structurally Aligned Weight Spaces
- Learning to Learn with Generative Models of Neural Network Checkpoints
- Learning on LoRAs: GL-Equivariant Processing of Low-Rank Weight Spaces for Large Finetuned Models
- Predicting Neural Network Accuracy from Weights
- Neural Network Diffusion
- Position: Weight Space Should Be a First-Class Generative AI Modality
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks