mlsanityData to 14 Oct 2026

Rewriting a Deep Generative Model

arXiv 2007.15646 ↗First posted 30 Jul 2020cs.CV cs.GR cs.LGcited by 107

Not on the map. Why?

Abstract (arXiv)

A deep generative model such as a GAN learns to model a rich set of semantic and physical rules about the target distribution, but up to now, it has been obscure how such rules are encoded in the network, or how a rule could be changed. In this paper, we introduce a new problem setting: manipulation of specific rules encoded by a deep generative model. To address the problem, we propose a formulation in which the desired rule is changed by manipulating a layer of a deep network as a linear associative memory. We derive an algorithm for modifying one entry of the associative memory, and we demonstrate that several interesting structural rules can be located and modified within the layers of state-of-the-art generative models. We present a user interface to enable users to interactively change the rules of a generative model to achieve desired effects, and we show several proof-of-concept applications. Finally, results on multiple datasets demonstrate the advantage of our method against standard fine-tuning methods and edit transfer algorithms.

Key facts. Cited by 107 papers in the map (data through 14 Oct 2026). First posted on arXiv 30 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 16; 2022: 23; 2023: 26; 2024: 20; 2025: 11; 2026: 11.

107 papers.

Sort:

By area:

  1. 2022Locating and Editing Factual Associations in GPTcited by 2,691
  2. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,937
  3. 2021Alias-Free Generative Adversarial Networkscited by 1,184
  4. 2022Multi-Concept Customization of Text-to-Image Diffusioncited by 1,106
  5. 2023Towards Automated Circuit Discovery for Mechanistic Interpretabilitycited by 724
  6. 2023Erasing Concepts from Diffusion Modelscited by 539
  7. 2023Unified Concept Editing in Diffusion Modelscited by 388
  8. 2021GAN Inversion: A Surveycited by 367
  9. 2023SVDiff: Compact Parameter Space for Diffusion Fine-Tuningcited by 338
  10. 2023Ablating Concepts in Text-to-Image Diffusion Modelscited by 317
  11. 2024MACE: Mass Concept Erasure in Diffusion Modelscited by 307
  12. 2022Post-hoc Concept Bottleneck Modelscited by 293
38 more
  1. 2022VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidancecited by 285
  2. 2023Label-Free Concept Bottleneck Modelscited by 285
  3. 2023Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Modelscited by 243
  4. 2021Editing Conditional Radiance Fieldscited by 222
  5. 2023Key-Locked Rank One Editing for Text-to-Image Personalizationcited by 194
  6. 2023Knowledge Editing for Large Language Models: A Surveycited by 194
  7. 2023Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Modelscited by 177
  8. 2021EditGAN: High-Precision Semantic Image Editingcited by 156
  9. 2023Editing Implicit Assumptions in Text-to-Image Diffusion Modelscited by 130
  10. 2023Generalizing Dataset Distillation via Deep Generative Priorcited by 126
  11. 2021Editing a classifier by rewriting its prediction rulescited by 65
  12. 2024MyVLM: Personalizing VLMs for User-Specific Queriescited by 58
  13. 2021Adversarial Text-to-Image Synthesis: A Reviewcited by 52
  14. 2025From Flat to Hierarchical: Extracting Sparse Representations with Matching Pursuitcited by 49
  15. 2023Codebook Features: Sparse and Discrete Interpretability for Neural Networkscited by 48
  16. 2021Sketch Your Own GANcited by 37
  17. 2024Customizing Text-to-Image Models with a Single Image Paircited by 36
  18. 2022BlobGAN: Spatially Disentangled Scene Representationscited by 35
  19. 2022State-of-the-Art in the Architecture, Methods and Applications of StyleGANcited by 34
  20. 2022Using Language to Extend to Unseen Domainscited by 34
  21. 2024Needle in the Haystack for Memory Based Large Language Modelscited by 34
  22. 2023How Do Large Language Models Capture the Ever-changing World Knowledge? A Review of Recent Advancescited by 33
  23. 2022DL4SciVis: A State-of-the-Art Survey on Deep Learning for Scientific Visualizationcited by 32
  24. 2023ReFACT: Updating Text-to-Image Models by Editing the Text Encodercited by 32
  25. 2024Corrective Machine Unlearningcited by 29
  26. 2022Cross-Modal 3D Shape Generation and Manipulationcited by 28
  27. 2023Disentangling Neuron Representations with Concept Vectorscited by 28
  28. 2023Editing Common Sense in Transformerscited by 28
  29. 2021Linear Semantics in Generative Adversarial Networkscited by 25
  30. 2022Rewriting Geometric Rules of a GANcited by 25
  31. 2021CreativeGAN: Editing Generative Adversarial Networks for Creative Design Synthesiscited by 24
  32. 2022Region-Based Semantic Factorization in GANscited by 22
  33. 2024Visual Concept Connectome (VCC): Open World Concept Discovery and their Interlayer Connections in Deep Modelscited by 22
  34. 2023Deep Learning in Deterministic Computational Mechanicscited by 21
  35. 2025Representation Engineering for Large-Language Models: Survey and Research Challengescited by 21
  36. 2022FairStyle: Debiasing StyleGAN2 with Style Channel Manipulationscited by 20
  37. 2022PandA: Unsupervised Learning of Parts and Appearances in the Feature Maps of GANscited by 20
  38. 2024Decomposing and Editing Predictions by Modeling Model Computationcited by 19

50 most cited of 107 All 107 (JSON)