mlsanityData to 7 Oct 2026

CoDe: Blockwise Control for Denoising Diffusion Models

arXiv 2502.00968 ↗First posted 3 Feb 2025cs.CV cs.LGcited by 14

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Aligning diffusion models to downstream tasks often requires finetuning new models or gradient-based guidance at inference time to enable sampling from the reward-tilted posterior. In this work, we explore a simple inference-time gradient-free guidance approach, called controlled denoising (CoDe), that circumvents the need for differentiable guidance functions and model finetuning. CoDe is a blockwise sampling method applied during intermediate denoising steps, allowing for alignment with downstream rewards. Our experiments demonstrate that, despite its simplicity, CoDe offers a favorable trade-off between reward alignment, prompt instruction following, and inference cost, achieving a competitive performance against the state-of-the-art baselines. Our code is available at: https://github.com/anujinho/code.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 61 of its 69 references that are in the map. First posted on arXiv 3 Feb 2025.

Builds on

61 of 69 references.

Closest ancestors · 17

Same direction, newest first

  1. 2024TFG: Unified Training-Free Guidance for Diffusion Models24 Sep
  2. 2024Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-Based Decoding15 Aug
  3. 2024Gradient Guidance for Diffusion Models: An Optimization Perspective23 Apr
  4. 2024Theoretical Insights for Diffusion Guidance: A Case Study for Gaussian Mixture Models3 Mar
  5. 2024A Phase Transition in Diffusion Models Reveals the Hierarchical Nature of Data26 Feb
  6. 2024Particle Denoising Diffusion Sampler9 Feb
  7. 2023Manifold Preserving Guided Diffusion28 Nov
  8. 2023CADS: Unleashing the Diversity of Diffusion Models through Condition-Annealed Sampling26 Oct
  9. 2023Spontaneous Symmetry Breaking in Generative Diffusion Models31 May
  10. 2023FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model17 Mar
  11. 2023Universal Guidance for Diffusion Models14 Feb
  12. 2022Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise19 Aug
5 more
  1. 2022Classifier-Free Diffusion Guidance26 Jul
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  3. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  4. 2020Denoising Diffusion Implicit Models6 Oct
  5. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 44

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  3. 2014Going Deeper with Convolutionscited by 4,231
  4. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  5. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  6. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,286
  7. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  8. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,388
  9. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,928
  10. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,903
  11. 2021LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairscited by 1,544
  12. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,375
32 more
  1. 2023T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Modelscited by 1,339
  2. 2022Scaling Laws for Reward Model Overoptimizationcited by 1,056
  3. 2024Large Language Monkeys: Scaling Inference Compute with Repeated Samplingcited by 946
  4. 2023Training Diffusion Models with Reinforcement Learningcited by 939
  5. 2016Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networkscited by 895
  6. 2023GLIGEN: Open-Set Grounded Text-to-Image Generationcited by 774
  7. 2023Diffusion Model Alignment Using Direct Preference Optimizationcited by 767
  8. 2022Improving Diffusion Models for Inverse Problems using Manifold Constraintscited by 501
  9. 2024Lumiere: A Space-Time Diffusion Model for Video Generationcited by 450
  10. 2023DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Modelscited by 431
  11. 2023Directly Fine-Tuning Diffusion Models on Differentiable Rewardscited by 431
  12. 2021FUDGE: Controlled Text Generation With Future Discriminatorscited by 374
  13. 2023Denoising Diffusion Models for Plug-and-Play Image Restorationcited by 335
  14. 2023Rethinking FID: Towards a Better Evaluation Metric for Image Generationcited by 303
  15. 2023Aligning Text-to-Image Diffusion Models with Reward Backpropagationcited by 284
  16. 2023Practical and Asymptotically Exact Conditional Sampling in Diffusion Modelscited by 218
  17. 2023Controlled Decoding from Language Modelscited by 133
  18. 2022RL with KL penalties is better viewed as Bayesian inferencecited by 130
  19. 2024BoNBoN Alignment for Large Language Models and the Sweetness of Best-of-n Samplingcited by 120
  20. 2024Theoretical guarantees on the best-of-n alignment policycited by 116
  21. 2024Measuring Style Similarity in Diffusion Modelscited by 106
  22. 2022Diffusion-based Molecule Generation with Informative Prior Bridgescited by 104
  23. 2024Understanding Reinforcement Learning-Based Fine-Tuning of Diffusion Models: A Tutorial and Reviewcited by 92
  24. 2023FreeControl: Training-Free Spatial Control of Any Text-to-Image Diffusion Model with Any Conditioncited by 89
  25. 2023Monte Carlo guided Diffusion for Bayesian linear inverse problemscited by 65
  26. 2023Reward-Directed Conditional Diffusion: Provable Distribution Estimation and Reward Improvementcited by 49
  27. 2024Asymptotics of Language Model Alignmentcited by 46
  28. 2022Adaptively-Realistic Image Generation from Stroke and Sketch with Diffusion Modelcited by 39
  29. 2024Diffusion-RPO: Aligning Diffusion Models through Relative Preference Optimizationcited by 30
  30. 2024Information Theoretic Guarantees For Policy Alignment In Large Language Modelscited by 22
  31. 2024Elucidating Optimal Reward-Diversity Tradeoffs in Text-to-Image Diffusion Modelscited by 13
  32. 2019Improving Style Transfer with Calibrated Metricscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 9; 2026: 5.

14 papers.

Sort:

By area:

  1. 2025Scaling Image and Video Generation via Test-Time Evolutionary Searchcited by 38
  2. 2025Inference-Time Scaling for Flow Models via Stochastic Generation and Rollover Budget Forcingcited by 37
  3. 2025Psi-Sampler: Initial Particle Sampling for SMC-Based Inference-Time Reward Alignment in Score Modelscited by 15
  4. 2025ImagerySearch: Adaptive Test-Time Search for Video Generation Beyond Semantic Dependency Constraintscited by 9
  5. 2025MIRA: Towards Mitigating Reward Hacking in Inference-Time Alignment of T2I Diffusion Modelscited by 7
  6. 2025Diffusion Blend: Inference-Time Multi-Preference Alignment for Diffusion Modelscited by 6
  7. 2026Tiny Inference-Time Scaling with Latent Verifierscited by 4
  8. 2025Tree Reward-Aligned Search for TReASURe in Masked Diffusion Language Modelscited by 2
  9. 2025Rethinking Test Time Scaling for Flow-Matching Generative Modelscited by 1
  10. 2026Tuning Real-World Image Restoration at Inference: A Test-Time Scaling Paradigm for Flow Matching Modelscited by 1
  11. 2025Unified Control for Inference-Time Guidance of Denoising Diffusion Modelscited by 0
  12. 2026Learnable Chernoff Baselines for Inference-Time Alignmentcited by 0
2 more
  1. 2026Step-level Denoising-time Diffusion Alignment with Multiple Objectivescited by 0
  2. 2026Test-Time Scaling in Multimodal Foundation Models: A Comprehensive Survey of Generation and Reasoningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning
  2. 2025Inference-Time Alignment in Diffusion Models with Reward-Guided Generation: Tutorial and Review
  3. 2025Fewer Denoising Steps or Cheaper Per-Step Inference: Towards Compute-Optimal Diffusion Model Deployment
  4. 2024Inference-Time Alignment of Diffusion Models with Direct Noise Optimization
  5. 2025Accelerate High-Quality Diffusion Models with Inner Loop Feedback
  6. 2026On the Robustness of Distribution Support under Diffusion Guidance
  7. 2024Inference-Time Diffusion Model Distillation
  8. 2023Selective Guidance: Are All the Denoising Steps of Guided Diffusion Important?