mlsanityData to 14 Oct 2026

CFG-OEC: Classifier Free Guidance with Orthogonal Error Correction

arXiv 2511.14075 ↗First posted 18 Nov 2025cs.LG cs.AIcited by 0

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Classifier free guidance is a standard method for conditional sampling in diffusion models, but its sampling rule is not aligned with the objective used in training. This mismatch induces a structural sampling error through the interaction of conditional and unconditional prediction errors. We analyze this issue by decomposing the sampling error into a base term and a cross term determined by the alignment of the two errors. Based on this analysis we propose CFG with orthogonal error correction (CFG-OEC), a structural modification that reduces the interaction term. For practical settings where ground truth noise is not observable, we introduce a proxy computed from model predictions and a dynamic method that stabilizes correction across diffusion timesteps. Experiments in a controlled environment validate our theoretical error decomposition and proxy construction. Image generation on Stable Diffusion v1.5 and Stable Diffusion XL show that CFG-OEC improves FID and CLIP scores over CFG and CFG++ across multiple samplers and guidance regimes.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 28 of its 30 references that are in the map. First posted on arXiv 18 Nov 2025.

Builds on

28 of 30 references.

Closest ancestors · 14

Same direction, newest first

  1. 2025CFG-Zero*: Improved Classifier-Free Guidance for Flow Matching Models24 Mar
  2. 2024CFG++: Manifold-constrained Classifier Free Guidance for Diffusion Models12 Jun
  3. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis4 Jul
  4. 2023UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models9 Feb
  5. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models2 Nov
  6. 2022Improving Sample Quality of Diffusion Models Using Self-Attention Guidance3 Oct
  7. 2022A Survey on Generative Diffusion Model6 Sep
  8. 2022Classifier-Free Diffusion Guidance26 Jul
  9. 2022Elucidating the Design Space of Diffusion-Based Generative Models1 Jun
  10. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  11. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  12. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
2 more
  1. 2020Denoising Diffusion Implicit Models6 Oct
  2. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 14

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  4. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  5. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  6. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  7. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,614
  8. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  9. 2022Video Diffusion Modelscited by 2,305
  10. 2022Planning with Diffusion for Flexible Behavior Synthesiscited by 1,061
  11. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoiserscited by 931
  12. 2023Text-to-image Diffusion Models in Generative AI: A Surveycited by 265
2 more
  1. 2023SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Predictioncited by 233
  2. 2023Motion Planning Diffusion: Learning and Planning of Robot Motions with Diffusion Modelscited by 161

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Conditional Diffusion Models with Classifier-Free Gibbs-like Guidance
  2. 2025Improving Classifier-Free Guidance in Masked Diffusion: Low-Dim Theoretical Insights with High-Dim Impact
  3. 2024Rectified Diffusion Guidance for Conditional Generation
  4. 2025Learn to Guide Your Diffusion Model
  5. 2024Classifier-Free Guidance is a Predictor-Corrector
  6. 2024Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Models
  7. 2024No Training, No Problem: Rethinking Classifier-Free Guidance for Diffusion Models
  8. 2025Diffusion Sampling Path Tells More: An Efficient Plug-and-Play Strategy for Sample Filtering