mlsanityData to 7 Oct 2026

Weight Space Representation Learning via Neural Field Adaptation

arXiv 2512.01759 ↗First posted 1 Dec 2025cs.LG cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

We investigate the potential of weights to serve as effective representations, focusing on neural fields. Our key insight is that constraining the optimization space through a pre-trained base model and low-rank adaptation (LoRA) can induce structure in weight space. Across reconstruction, generation, and analysis tasks on 2D and 3D data, we find that multiplicative LoRA weights achieve high representation quality while exhibiting distinctiveness and semantic structure. When used with latent diffusion models, multiplicative LoRA weights enable higher-quality generation than existing weight-space methods.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 39 of its 47 references that are in the map. First posted on arXiv 1 Dec 2025.

Builds on

39 of 47 references.

References · 39

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  3. 2022Scalable Diffusion Models with Transformerscited by 5,931
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  5. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  6. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  7. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  8. 2018Demystifying MMD GANscited by 1,268
  9. 2021Alias-Free Generative Adversarial Networkscited by 1,181
  10. 2016HyperNetworkscited by 1,003
  11. 2020Meta-Learning in Neural Networks: A Surveycited by 944
  12. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 734
27 more
  1. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  2. 2019Linear Mode Connectivity and the Lottery Ticket Hypothesiscited by 627
  3. 2022LION: Latent Point Diffusion Models for 3D Shape Generationcited by 552
  4. 2021Neural Fields in Visual Computing and Beyondcited by 539
  5. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  6. 2023Rethinking FID: Towards a Better Evaluation Metric for Image Generationcited by 303
  7. 2024Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunitiescited by 247
  8. 2021COIN: COmpression with Implicit Neural representationscited by 232
  9. 2019Model Fusion via Optimal Transportcited by 217
  10. 2022From data to functa: Your data point is a function and you can treat it like onecited by 183
  11. 2023HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusioncited by 152
  12. 2023Equivariant Architectures for Learning in Deep Weight Spacescited by 106
  13. 2020Image Generators with Conditionally-Independent Pixel Synthesiscited by 105
  14. 2021A Structured Dictionary Perspective on Implicit Neural Representationscited by 100
  15. 2022Learning to Learn with Generative Models of Neural Network Checkpointscited by 85
  16. 2022Transformers as Meta-Learners for Implicit Neural Representationscited by 79
  17. 2023Permutation Equivariant Neural Functionalscited by 69
  18. 2019Hypernetwork functional image representationcited by 65
  19. 2024Graph Neural Networks for Learning Equivariant Representations of Neural Networkscited by 59
  20. 2023Neural Functional Transformerscited by 50
  21. 2024Where Do We Stand with Implicit Neural Representations? A Technical and Performance Surveycited by 41
  22. 2024Neural Network Diffusioncited by 39
  23. 2024Interpreting the Weight Space of Customized Diffusion Modelscited by 35
  24. 2025Symmetry in Neural Network Parameter Spacescited by 31
  25. 2024The Empirical Impact of Neural Parameter Symmetries, or Lack Thereofcited by 21
  26. 2024Learning on LoRAs: GL-Equivariant Processing of Low-Rank Weight Spaces for Large Finetuned Modelscited by 21
  27. 2024Learning Transferable Features for Implicit Neural Representationscited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026CrossGMN: Graph Metanetworks for Cross-Architecture Weight-Space Transformationscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025LoRAtorio: An intrinsic approach to LoRA Skill Composition
  2. 2023The Expressive Power of Low-Rank Adaptation
  3. 2026Not All Layers Are Created Equal: Adaptive LoRA Ranks for Personalized Image Generation
  4. 2024LoRA Diffusion: Zero-Shot LoRA Synthesis for Diffusion Model Personalization
  5. 2026ChimeraLoRA: Multi-Head LoRA-Guided Synthetic Datasets
  6. 2024Mixture-of-Subspaces in Low-Rank Adaptation
  7. 2024Flat-LoRA: Low-Rank Adaptation over a Flat Loss Landscape
  8. 2026Filtering Memorization from Parameter-Space in Diffusion Models