mlsanityData to 7 Oct 2026

Alignment of Diffusion Models: Fundamentals, Challenges, and Future

arXiv 2409.07253 ↗First posted 11 Sep 2024cs.LG cs.CVcited by 34

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Diffusion models have emerged as the leading paradigm in generative modeling, excelling in various applications. Despite their success, these models often misalign with human intentions and generate results with undesired properties or even harmful content. Inspired by the success and popularity of alignment in tuning large language models, recent studies have investigated aligning diffusion models with human expectations and preferences. This work mainly reviews alignment of diffusion models, covering advancements in fundamentals of alignment, alignment techniques of diffusion models, preference benchmarks, and evaluation for diffusion models. Moreover, we discuss key perspectives on current challenges and promising future directions on solving the remaining challenges in alignment of diffusion models. To the best of our knowledge, our work is the first comprehensive review paper for researchers and engineers to comprehend, practice, and research alignment of diffusion models.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 173 of its 273 references that are in the map. First posted on arXiv 11 Sep 2024.

Builds on

173 of 273 references.

Closest ancestors · 13

Same direction, newest first

  1. 2024Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-Based Decoding15 Aug
  2. 2024Not All Noises Are Created Equally:Diffusion Noise Selection and Optimization19 Jul
  3. 2024Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation18 Mar
  4. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesis5 Mar
  5. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis4 Jul
  6. 2023Common Diffusion Noise Schedules and Sample Steps are Flawed15 May
  7. 2022Improving Sample Quality of Diffusion Models Using Self-Attention Guidance3 Oct
  8. 2022A Survey on Generative Diffusion Model6 Sep
  9. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  10. 2021Improved Denoising Diffusion Probabilistic Models18 Feb
  11. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  12. 2020Denoising Diffusion Implicit Models6 Oct
1 more
  1. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 160

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2022Training language models to follow instructions with human feedbackcited by 15,712
  4. 2017Proximal Policy Optimization Algorithmscited by 14,441
  5. 2024The Llama 3 Herd of Modelscited by 14,192
  6. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  7. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  8. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  9. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  10. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  11. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  12. 2022Generative Adversarial Networkscited by 5,603
38 more
  1. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  2. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  3. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  4. 2017Deep reinforcement learning from human preferencescited by 3,846
  5. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  6. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  7. 2016Improved Techniques for Training GANscited by 2,938
  8. 2020Learning to summarize from human feedbackcited by 2,562
  9. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,409
  10. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  11. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,928
  12. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,873
  13. 2019Invariant Risk Minimizationcited by 1,832
  14. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,765
  15. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  16. 2017Understanding Black-box Predictions via Influence Functionscited by 1,714
  17. 2015Microsoft COCO Captions: Data Collection and Evaluation Servercited by 1,447
  18. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,339
  19. 2023Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!cited by 1,106
  20. 2023LIMA: Less Is More for Alignmentcited by 1,080
  21. 2022Scaling Laws for Reward Model Overoptimizationcited by 1,056
  22. 2021A General Language Assistant as a Laboratory for Alignmentcited by 1,023
  23. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,020
  24. 2023ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generationcited by 1,010
  25. 2024SimPO: Simple Preference Optimization with a Reference-Free Rewardcited by 951
  26. 2023Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generationcited by 950
  27. 2023GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignmentcited by 946
  28. 2023Training Diffusion Models with Reinforcement Learningcited by 939
  29. 2023A General Theoretical Paradigm to Understand Learning from Human Preferencescited by 906
  30. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 860
  31. 2016Training Deep Nets with Sublinear Memory Costcited by 825
  32. 2022PaLI: A Jointly-Scaled Multilingual Language-Image Modelcited by 762
  33. 2023AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedbackcited by 738
  34. 2023Discrete Diffusion Modeling by Estimating the Ratios of the Data Distributioncited by 712
  35. 2023Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Modelscited by 696
  36. 2023RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignmentcited by 672
  37. 2024Self-Rewarding Language Modelscited by 654
  38. 2020AWAC: Accelerating Online Reinforcement Learning with Offline Datasetscited by 647

50 most cited of 160 All 160 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 11; 2025: 11; 2026: 12.

34 papers.

Sort:

By area:

  1. 2024Golden Noise for Diffusion Models: A Learning Frameworkcited by 91
  2. 2025A Survey of Direct Preference Optimizationcited by 35
  3. 2024Scalable Ranked Preference Optimization for Text-to-Image Generationcited by 33
  4. 2024DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Schedulingcited by 27
  5. 2024Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample Optimizationcited by 25
  6. 2024SoPo: Text-to-Motion Generation Using Semi-Online Preference Optimizationcited by 14
  7. 2025Smoothed Preference Optimization via ReNoise Inversion for Aligning Diffusion Models with Varied Human Preferencescited by 13
  8. 2024Aligning Few-Step Diffusion Models with Dense Reward Difference Learningcited by 11
  9. 2026Conditional Diffusion Guidance under Hard Constraint: A Stochastic Analysis Approachcited by 10
  10. 2024IV-Mixed Sampler: Leveraging Image Diffusion Models for Enhanced Video Synthesiscited by 8
  11. 2025Composition and Alignment of Diffusion Models using Constrained Learningcited by 8
  12. 2024Bag of Design Choices for Inference of High-Resolution Masked Generative Transformercited by 7
22 more
  1. 2024A Simple and Efficient Baseline for Zero-Shot Generative Classificationcited by 7
  2. 2025Towards Self-Improvement of Diffusion Models via Group Preference Optimizationcited by 7
  3. 2025MIRA: Towards Mitigating Reward Hacking in Inference-Time Alignment of T2I Diffusion Modelscited by 7
  4. 2026ConsistentRFT: Reducing Visual Hallucinations in Flow-based Reinforcement Fine-Tuningcited by 5
  5. 2026HyperAlign: Hypernetwork for Efficient Test-Time Alignment of Diffusion Modelscited by 4
  6. 2026FastLightGen: Fast and Light Video Generation with Fewer Steps and Parameterscited by 4
  7. 2026Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Modelscited by 4
  8. 2025Alignment and Safety of Diffusion Models via Reinforcement Learning and Reward Modeling: A Surveycited by 3
  9. 2025Enhancing Diffusion-based Unrestricted Adversarial Attacks via Adversary Preferences Alignmentcited by 3
  10. 2026LIVEditor-14B: Lightning Unified Video Editing via In-Context Sparse Attentioncited by 3
  11. 2024Preference Alignment for Diffusion Model via Explicit Denoised Distribution Estimationcited by 2
  12. 2025DP2O-SR: Direct Perceptual Preference Optimization for Real-World Image Super-Resolutioncited by 2
  13. 2026Guidance Matters: Rethinking the Evaluation Pitfall for Text-to-Image Generationcited by 2
  14. 2026CRAFT: Aligning Diffusion Models with Fine-Tuning Is Easier Than You Thinkcited by 2
  15. 2026Inference-Time Attribute Distribution Alignment for Unconditional Diffusioncited by 2
  16. 2026When Policy Entropy Constraint Fails: Preserving Diversity in Flow-based RLHF via Perceptual Entropycited by 2
  17. 2024ArtAug: Enhancing Text-to-Image Generation through Synthesis-Understanding Interactioncited by 1
  18. 2025Inference-Time Alignment of Diffusion Models via Evolutionary Algorithmscited by 1
  19. 2025Latent Diffusion Unlearning: Protecting Against Unauthorized Personalization Through Trajectory Shifted Perturbationscited by 1
  20. 2025IPGO: Indirect Prompt Gradient Optimization for Parameter-Efficient Prompt-level Fine-Tuning on Text-to-Image Modelscited by 0
  21. 2026Boosting Text-to-Image Diffusion Models via Core Token Attention-Based Seed Selectioncited by 0
  22. 2026G3-LoRA: Organizing Reward-Weighted Video Data with Gradient-Guided Grouped LoRAcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Generative Diffusion Modeling: A Practical Handbook
  2. 2024Diffusion-RPO: Aligning Diffusion Models through Relative Preference Optimization
  3. 2026Generative Frontiers: Why Evaluation Matters for Diffusion Language Models
  4. 2025Divergence Minimization Preference Optimization for Diffusion Model Alignment
  5. 2022Diffusion Models: A Comprehensive Survey of Methods and Applications
  6. 2023Diffusion Model Alignment Using Direct Preference Optimization
  7. 2024An Overview of Diffusion Models: Applications, Guided Generation, Statistical Rates and Optimization
  8. 2023A Survey of Diffusion Models in Natural Language Processing