# Generative Modeling of Weights: Generalization or Memorization?

arXiv: https://arxiv.org/abs/2506.07998 · HTML: https://mlsanity.com/paper/2506.07998/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 61 of its 90 references that are in the map.
- First posted on arXiv 9 Jun 2025.

## Builds on (most cited first, 30 of 61)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [Understanding deep learning requires rethinking generalization](https://mlsanity.com/paper/1611.03530/) (2016)
- [Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time](https://mlsanity.com/paper/2203.05482/) (2022)
- [HyperNetworks](https://mlsanity.com/paper/1609.09106/) (2016)
- [Cosmos World Foundation Model Platform for Physical AI](https://mlsanity.com/paper/2501.03575/) (2025)
- [Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think](https://mlsanity.com/paper/2410.06940/) (2024)
- [Regularizing Neural Networks by Penalizing Confident Output Distributions](https://mlsanity.com/paper/1701.06548/) (2017)
- [Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models](https://mlsanity.com/paper/2212.03860/) (2022)
- [The Expressive Power of Neural Networks: A View from the Width](https://mlsanity.com/paper/1709.02540/) (2017)
- [The Intrinsic Dimension of Images and Its Impact on Learning](https://mlsanity.com/paper/2104.08894/) (2021)
- [Skillful Precipitation Nowcasting using Deep Generative Models of Radar](https://mlsanity.com/paper/2104.00954/) (2021)
- [On the Expressive Power of Deep Neural Networks](https://mlsanity.com/paper/1606.05336/) (2016)

## Built on by (most cited first, 14 of 14)

- [Learning a Generative Meta-Model of LLM Activations](https://mlsanity.com/paper/2602.06964/) (2026)
- [Position: Weight Space Should Be a First-Class Generative AI Modality](https://mlsanity.com/paper/2605.18632/) (2026)
- [DeepWeightFlow: Re-Basined Flow Matching for Generating Neural Network Weights](https://mlsanity.com/paper/2601.05052/) (2026)
- [You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories](https://mlsanity.com/paper/2605.21468/) (2026)
- [What Linear Probes Miss: Multi-View Probing for Weight-Space Learning](https://mlsanity.com/paper/2605.23410/) (2026)
- [Scaling Linear Mode Connectivity and Merging to Billion Parameter Pretrained Transformers](https://mlsanity.com/paper/2606.23607/) (2026)
- [Flows and Diffusions on the Neural Manifold](https://mlsanity.com/paper/2507.10623/) (2025)
- [Memorization in 3D Shape Generation: An Empirical Study](https://mlsanity.com/paper/2512.23628/) (2025)
- [Delta Activations: A Representation for Finetuned Large Language Models](https://mlsanity.com/paper/2509.04442/) (2025)
- [Infinite-Parameter LLMs: Generating and Adapting Weights from Live Data](https://mlsanity.com/paper/2609.18842/) (2026)
- [Permutation-Equivariant Flow Matching for Alignment-Free Neural Weight Generation](https://mlsanity.com/paper/2609.32833/) (2026)
- [On-the-fly Weight Generation: A Hypernetwork Proof of Concept on ARC-1D](https://mlsanity.com/paper/2610.00820/) (2026)
- [WIRE: Weight Space Implicit Representation Encoding of Frozen Video LLMs](https://mlsanity.com/paper/2610.17355/) (2026)
- [Modeling and Understanding Neural Weights of Humanoid Policies with Diffusion](https://mlsanity.com/paper/2610.20606/) (2026)

## Abstract (arXiv)

Generative models have recently been explored for synthesizing neural network weights. These approaches take neural network checkpoints as training data and aim to generate high-performing weights during inference. In this work, we examine four representative, well-known methods on their ability to generate novel model weights, i.e., weights that are different from the checkpoints seen during training. Contrary to claims in prior work, we find that these methods synthesize weights largely by memorization: they produce either replicas, or, at best, simple interpolations of the training checkpoints. Moreover, they fail to outperform simple baselines, such as adding noise to the weights or taking a simple weight ensemble, in obtaining different and simultaneously high-performing models. Our further analysis suggests that this memorization might result from limited data, overparameterized models, and the underuse of structural priors specific to weight data. These findings highlight the need for more careful design and rigorous evaluation of generative models when applied to new domains. Our code is available at https://github.com/boyazeng/weight_memorization.