mlsanityData to 7 Oct 2026

OCD: Learning to Overfit with Conditional Diffusion Models

arXiv 2210.00471 ↗First posted 2 Oct 2022cs.LGcited by 9

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

We present a dynamic model in which the weights are conditioned on an input sample x and are learned to match those that would be obtained by finetuning a base model on x and its label y. This mapping between an input sample and network weights is approximated by a denoising diffusion model. The diffusion model we employ focuses on modifying a single layer of the base model and is conditioned on the input, activations, and output of this layer. Since the diffusion model is stochastic in nature, multiple initializations generate different networks, forming an ensemble, which leads to further improvements. Our experiments demonstrate the wide applicability of the method for image classification, 3D reconstruction, tabular data, speech separation, and natural language processing. Our code is available at https://github.com/ShaharLutatiPersonal/OCD

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 43 of its 65 references that are in the map. First posted on arXiv 2 Oct 2022.

Builds on

43 of 65 references.

Closest ancestors · 8

Same direction, newest first

  1. 2021ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models6 Aug
  2. 2021Learning to Efficiently Sample from Diffusion Probabilistic Models7 Jun
  3. 2021Cascaded Diffusion Models for High Fidelity Image Generation30 May
  4. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  5. 2021Noise Estimation for Generative Diffusion Models6 Apr
  6. 2021Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed7 Jan
  7. 2020Denoising Diffusion Implicit Models6 Oct
  8. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 35

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  6. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  7. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  8. 2014Going Deeper with Convolutionscited by 4,231
  9. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  10. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,339
  11. 2016HyperNetworkscited by 1,003
  12. 2022Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learningcited by 886
23 more
  1. 2021Revisiting Deep Learning Models for Tabular Datacited by 725
  2. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 620
  3. 2021Fast Model Editing at Scalecited by 491
  4. 2021Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speechcited by 445
  5. 2022DeiT III: Revenge of the ViTcited by 417
  6. 2021Pre-Trained Models: Past, Present and Futurecited by 319
  7. 2021SegDiff: Image Segmentation with Diffusion Probabilistic Modelscited by 279
  8. 2019Continual learning with hypernetworkscited by 267
  9. 2021Personalized Federated Learning using Hypernetworkscited by 210
  10. 2017SMASH: One-Shot Model Architecture Search through HyperNetworkscited by 200
  11. 2019Neural Oblivious Decision Ensembles for Deep Learning on Tabular Datacited by 200
  12. 2021DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanismcited by 154
  13. 2022Efficient Few-Shot Learning Without Promptscited by 135
  14. 2018Graph HyperNetworks for Neural Architecture Searchcited by 131
  15. 2013Introducing LETOR 4.0 Datasetscited by 120
  16. 2018An Alternative View: When Does SGD Escape Local Minima?cited by 115
  17. 2016Learning feed-forward one-shot learnerscited by 93
  18. 2018Stochastic Hyperparameter Optimization through Hypernetworkscited by 72
  19. 2020Voice Separation with an Unknown Number of Multiple Speakerscited by 46
  20. 2022Zero-Shot Voice Conditioning for Denoising Diffusion TTS Modelscited by 20
  21. 2022SepIt: Approaching a Single Channel Speech Separation Boundcited by 16
  22. 2020Tailoring: encoding inductive biases by optimizing unsupervised objectives at prediction timecited by 13
  23. 2021Many-Speakers Single Channel Speech Separation with Optimal Permutation Trainingcited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 1; 2025: 3; 2026: 1.

9 papers.

  1. 2023ProtoDiff: Learning to Learn Prototypical Networks by Task-Guided Diffusioncited by 15
  2. 2023Focus Your Attention (with Adaptive IIR Filters)cited by 12
  3. 2023Astroformer: More Data Might not be all you need for Classificationcited by 6
  4. 2025Learning an Efficient Optimizer via Hybrid-Policy Sub-Trajectory Balancecited by 5
  5. 2025Learning to Learn Weight Generation via Local Consistency Diffusioncited by 4
  6. 2024Prompt Diffusion Robustifies Any-Modality Prompt Learningcited by 2
  7. 2023Efficient Verification-Based Face Identificationcited by 1
  8. 2025GDR-learners: Orthogonal Learning of Generative Models for Potential Outcomescited by 1
  9. 2026Multi-Sensor Matching with HyperNetworkscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Conditional Generation from Unconditional Diffusion Models using Denoiser Representations
  2. 2022Image Embedding for Denoising Generative Models
  3. 2023CADS: Unleashing the Diversity of Diffusion Models through Condition-Annealed Sampling
  4. 2025Random Conditioning with Distillation for Data-Efficient Diffusion Model Compression
  5. 2023Adaptive Training Meets Progressive Scaling: Elevating Efficiency in Diffusion Models
  6. 2025Automated Learning of Semantic Embedding Representations for Diffusion Models
  7. 2024Conditional Image Synthesis with Diffusion Models: A Survey
  8. 2025Guiding Noisy Label Conditional Diffusion Models with Score-based Discriminator Correction