mlsanityData to 7 Oct 2026

Truncated Diffusion Probabilistic Models and Diffusion-based Adversarial Auto-Encoders

arXiv 2202.09671 ↗First posted 19 Feb 2022stat.ML cs.LGcited by 42

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Employing a forward diffusion chain to gradually map the data to a noise distribution, diffusion-based generative models learn how to generate the data by inferring a reverse diffusion chain. However, this approach is slow and costly because it needs many forward and reverse steps. We propose a faster and cheaper approach that adds noise not until the data become pure random noise, but until they reach a hidden noisy data distribution that we can confidently learn. Then, we use fewer reverse steps to generate data by starting from this hidden distribution that is made similar to the noisy data. We reveal that the proposed model can be cast as an adversarial auto-encoder empowered by both the diffusion process and a learnable implicit prior. Experimental results show even with a significantly smaller number of reverse diffusion steps, the proposed truncated diffusion probabilistic models can provide consistent improvements over the non-truncated ones in terms of performance in both unconditional and text-guided image generations.

Key facts. Cited by 42 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 71 of its 101 references that are in the map. First posted on arXiv 19 Feb 2022.

Builds on

71 of 101 references.

Closest ancestors · 18

Same direction, newest first

  1. 2022DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latents2 Jan
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  3. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANs15 Dec
  4. 2021Structured Denoising Diffusion Models in Discrete State-Spaces7 Jul
  5. 2021Variational Diffusion Models1 Jul
  6. 2021Score-based Generative Modeling in Latent Space10 Jun
  7. 2021A Variational Perspective on Diffusion-Based Generative Models and Score Matching5 Jun
  8. 2021On Fast Sampling of Diffusion Probabilistic Models31 May
  9. 2021Gotta Go Fast When Generating Data with Score-Based Models28 May
  10. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  11. 2021Noise Estimation for Generative Diffusion Models6 Apr
  12. 2021Improved Denoising Diffusion Probabilistic Models18 Feb
6 more
  1. 2021Maximum Likelihood Training of Score-Based Diffusion Models22 Jan
  2. 2021Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed7 Jan
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  4. 2020Denoising Diffusion Implicit Models6 Oct
  5. 2020Denoising Diffusion Probabilistic Models19 Jun
  6. 2020Improved Techniques for Training Score-Based Generative Models16 Jun

Other references · 53

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  5. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  6. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  7. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  8. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  9. 2017Neural Discrete Representation Learningcited by 4,650
  10. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  11. 2013Auto-Encoding Variational Bayescited by 3,980
  12. 2014Deep Learning Face Attributes in the Wildcited by 3,679
38 more
  1. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  2. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  3. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  4. 2017Improved Training of Wasserstein GANscited by 2,223
  5. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  6. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  7. 2021LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairscited by 1,544
  8. 2016Variational Inference: A Review for Statisticianscited by 1,466
  9. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,376
  10. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  11. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,339
  12. 2018Demystifying MMD GANscited by 1,268
  13. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  14. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 925
  15. 2016Conditional Image Generation with PixelCNN Decoderscited by 859
  16. 2020NVAE: A Deep Hierarchical Variational Autoencodercited by 635
  17. 2019MaskGAN: Towards Diverse and Interactive Facial Image Manipulationcited by 624
  18. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 620
  19. 2016f-GAN: Training Generative Neural Samplers using Variational Divergence Minimizationcited by 504
  20. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 489
  21. 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 460
  22. 2020Differentiable Augmentation for Data-Efficient GAN Trainingcited by 361
  23. 2015Adversarial Autoencoderscited by 359
  24. 2017VAE with a VampPriorcited by 247
  25. 2016Learning in Implicit Generative Modelscited by 124
  26. 2020Learning Energy-Based Models by Diffusion Recovery Likelihoodcited by 122
  27. 2020Image Generators with Conditionally-Independent Pixel Synthesiscited by 105
  28. 2020VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Modelscited by 103
  29. 2020Adversarial score matching and improved sampling for image generationcited by 95
  30. 2019AutoGAN: Neural Architecture Search for Generative Adversarial Networkscited by 94
  31. 2019COCO-GAN: Generation by Parts via Conditional Coordinatingcited by 67
  32. 2018Semi-Implicit Variational Inferencecited by 55
  33. 2018Implicit Maximum Likelihood Estimationcited by 52
  34. 2020Refining Deep Generative Models via Discriminator Gradient Flowcited by 45
  35. 2017Variational Inference using Implicit Distributionscited by 39
  36. 2017Variational Walkback: Learning a Transition Operator as a Stochastic Recurrent Netcited by 30
  37. 2020Exploiting Chain Rule and Bayes' Theorem to Compare Probability Distributionscited by 22
  38. 2021Improved Autoregressive Modeling with Distribution Smoothingcited by 18

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year

Citing papers per year: 2022: 11; 2023: 14; 2024: 12; 2025: 5.

42 papers.

Sort:

By area:

  1. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  2. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,107
  3. 2022Diffusion Models in Vision: A Surveycited by 1,008
  4. 2023Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inferencecited by 826
  5. 2023ModelScope Text-to-Video Technical Reportcited by 651
  6. 2023I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Modelscited by 343
  7. 2022A Survey on Generative Diffusion Modelcited by 238
  8. 2023A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPTcited by 221
  9. 2022Diffusion-GAN: Training GANs with Diffusioncited by 203
  10. 2023PTQD: Accurate Post-Training Quantization for Diffusion Modelscited by 167
  11. 2023Diffusion Models for Image Restoration and Enhancement: A Comprehensive Surveycited by 108
  12. 2022CARD: Classification and Regression Diffusion Modelscited by 102
30 more
  1. 2022Accelerating Diffusion Models via Early Stop of the Diffusion Processcited by 100
  2. 2024Align Your Steps: Optimizing Sampling Schedules in Diffusion Modelscited by 91
  3. 2023TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Modelscited by 67
  4. 2024A Survey on Diffusion Models for Time Series and Spatio-Temporal Datacited by 66
  5. 2022Conditional Simulation Using Diffusion Schr"odinger Bridgescited by 58
  6. 2022Efficient Diffusion Models for Vision: A Surveycited by 50
  7. 2024Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One Stepcited by 47
  8. 2024Efficient Diffusion Models: A Comprehensive Survey from Principles to Practicescited by 39
  9. 2022How Much is Enough? A Study on Diffusion Times in Score-based Generative Modelscited by 35
  10. 2023Multi-Architecture Multi-Expert Diffusion Modelscited by 34
  11. 2024Foundation Models for Music: A Surveycited by 34
  12. 2022ResGrad: Residual Denoising Diffusion Probabilistic Models for Text to Speechcited by 21
  13. 2024Optimizing Diffusion Models for Joint Trajectory Prediction and Controllable Generationcited by 18
  14. 2025Ditto: Accelerating Diffusion Model via Temporal Value Similaritycited by 18
  15. 2025Few-Step Diffusion via Score identity Distillationcited by 10
  16. 2023Fast Inference in Denoising Diffusion Models via MMD Finetuningcited by 8
  17. 2023SMaRt: Improving GANs with Score Matching Regularitycited by 6
  18. 2024Multi-scale Latent Point Consistency Models for 3D Shape Generationcited by 6
  19. 2025Score Distillation of Flow Matching Modelscited by 6
  20. 2023UDPM: Upsampling Diffusion Probabilistic Modelscited by 5
  21. 2023A Recycling Training Strategy for Medical Image Segmentation with Diffusion Denoising Modelscited by 5
  22. 2024Temporal Feature Matters: A Framework for Diffusion Model Quantizationcited by 5
  23. 2024SF-Speech: Straightened Flow for Zero-Shot Voice Clonecited by 4
  24. 2025TD-BFR: Truncated Diffusion Model for Efficient Blind Face Restorationcited by 4
  25. 2023Diffusion Models for Interferometric Satellite Aperture Radarcited by 2
  26. 2024Theoretical research on generative diffusion models: an overviewcited by 2
  27. 2023Synthesis of Batik Motifs using a Diffusion -- Generative Adversarial Networkcited by 1
  28. 2024Solutions to Deepfakes: Can Camera Hardware, Cryptography, and Deep Learning Verify Real Images?cited by 1
  29. 2024Accelerated Image-Aware Generative Diffusion Modelingcited by 0
  30. 2025A Generative Framework for Causal Estimation via Importance-Weighted Diffusion Distillationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Unified Generation, Reconstruction, and Representation: Generalized Diffusion with Adaptive Latent Encoding-Decoding
  2. 2025Diffusion Models: A Mathematical Introduction
  3. 2024E2ED^2:Direct Mapping from Noise to Data for Enhanced Diffusion Models
  4. 2025Stochastic Forward-Backward Deconvolution: Training Diffusion Models with Finite Noisy Datasets
  5. 2022Image Embedding for Denoising Generative Models
  6. 2021Diffusion Autoencoders: Toward a Meaningful and Decodable Representation
  7. 2025ADT: Tuning Diffusion Models with Adversarial Supervision
  8. 2022Enhancing Diffusion-Based Image Synthesis with Robust Classifier Guidance