mlsanityData to 7 Oct 2026

Going beyond Compositions, DDPMs Can Produce Zero-Shot Interpolations

arXiv 2405.19201 ↗First posted 29 May 2024cs.CV cs.AI cs.NEcited by 5

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Denoising Diffusion Probabilistic Models (DDPMs) exhibit remarkable capabilities in image generation, with studies suggesting that they can generalize by composing latent factors learned from the training data. In this work, we go further and study DDPMs trained on strictly separate subsets of the data distribution with large gaps on the support of the latent factors. We show that such a model can effectively generate images in the unexplored, intermediate regions of the distribution. For instance, when trained on clearly smiling and non-smiling faces, we demonstrate a sampling procedure which can generate slightly smiling faces without reference images (zero-shot interpolation). We replicate these findings for other attributes as well as other datasets. Our code is available at https://github.com/jdeschena/ddpm-zero-shot-interpolation.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 50 of its 69 references that are in the map. First posted on arXiv 29 May 2024.

Builds on

50 of 69 references.

Closest ancestors · 7

Same direction, newest first

  1. 2023Generalization in diffusion models arises from geometry-adaptive harmonic representations4 Oct
  2. 2022Understanding Diffusion Models: A Unified Perspective25 Aug
  3. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  4. 2021Improved Denoising Diffusion Probabilistic Models18 Feb
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  6. 2020Denoising Diffusion Probabilistic Models19 Jun
  7. 2020Improved Techniques for Training Score-Based Generative Models16 Jun

Other references · 43

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  4. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  5. 2017On Calibration of Modern Neural Networkscited by 4,860
  6. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  7. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  8. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  9. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  10. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  11. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  12. 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,507
31 more
  1. 2016CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoningcited by 1,445
  2. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,127
  3. 2016Conditional Image Generation with PixelCNN Decoderscited by 859
  4. 2022Compositional Visual Generation with Composable Diffusion Modelscited by 619
  5. 2020GANSpace: Discovering Interpretable GAN Controlscited by 612
  6. 2023Scaling up GANs for Text-to-Image Synthesiscited by 492
  7. 2018Assessing Generative Models via Precision and Recallcited by 401
  8. 2020The Pitfalls of Simplicity Bias in Neural Networkscited by 349
  9. 2020Deep Structural Causal Models for Tractable Counterfactual Inferencecited by 210
  10. 2017GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibriumcited by 208
  11. 2016A Theory of Generative ConvNetcited by 174
  12. 2020Improved Contrastive Divergence Training of Energy Based Modelscited by 127
  13. 2022Adaptive Diffusion Priors for Accelerated MRI Reconstructioncited by 117
  14. 2022Denoising diffusion models for out-of-distribution detectioncited by 102
  15. 2021GAN-Control: Explicitly Controllable GANscited by 91
  16. 2018Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizercited by 87
  17. 2018Bias and Generalization in Deep Generative Models: An Empirical Studycited by 83
  18. 2016Deep Feature Interpolation for Image Content Changescited by 80
  19. 2021Learning to Compose Visual Relationscited by 72
  20. 2021Unsupervised Learning of Compositional Energy Conceptscited by 71
  21. 2022Agree to Disagree: Diversity through Disagreement for Better Transferabilitycited by 69
  22. 2018Excessive Invariance Causes Adversarial Vulnerabilitycited by 66
  23. 2020Improving the Fairness of Deep Generative Models without Retrainingcited by 46
  24. 2023Interpolating between Images with Diffusion Modelscited by 37
  25. 2024Exploring Diffusion Time-steps for Unsupervised Representation Learningcited by 36
  26. 2020Compositional Visual Generation and Inference with Energy Based Modelscited by 25
  27. 2023Unsupervised 3D out-of-distribution detection with latent diffusion modelscited by 22
  28. 2023A Call to Reflect on Evaluation Practices for Age Estimation: Comparative Analysis of the State-of-the-Art and a Unified Benchmarkcited by 19
  29. 2020A theory of independent mechanisms for extrapolation in generative modelscited by 17
  30. 2020Multilinear Latent Conditioning for Generating Unseen Attribute Combinationscited by 14
  31. 2022Leveraging Off-the-shelf Diffusion Model for Multi-attribute Fashion Image Manipulationcited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 2.

5 papers.

  1. 2026Making Reconstruction FID Predictive of Diffusion Generation FIDcited by 12
  2. 2025Mitigating Diffusion Model Hallucinations with Dynamic Guidancecited by 5
  3. 2025Image Interpolation with Score-based Riemannian Metrics of Diffusion Modelscited by 4
  4. 2025Concept Reachability in Diffusion Models: Beyond Dataset Constraintscited by 0
  5. 2026Grokking of Diffusion Models: Case Study on Modular Additioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2020Denoising Diffusion Implicit Models
  2. 2022Few-Shot Diffusion Models
  3. 2024Denoising Diffusion Probabilistic Models in Six Simple Steps
  4. 2022Unite and Conquer: Plug & Play Multi-Modal Synthesis using Diffusion Models
  5. 2023Improving Denoising Diffusion Probabilistic Models via Exploiting Shared Representations
  6. 2023Gradpaint: Gradient-Guided Inpainting with Diffusion Models
  7. 2023Star-Shaped Denoising Diffusion Probabilistic Models
  8. 2024The Uncanny Valley: A Comprehensive Analysis of Diffusion Models