mlsanityData to 7 Oct 2026

TAG: Tangential Amplifying Guidance for Hallucination-Resistant Sampling

arXiv 2510.04533 ↗First posted 6 Oct 2025cs.CVcited by 0

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

Diffusion models achieve state-of-the-art image generation but often produce semantic inconsistencies, or hallucinations. Existing inference-time guidance methods rely on external signals or architectural modifications, adding computational overhead. We propose Tangential Amplifying Guidance (TAG), a training-free, architecture-agnostic, plug-and-play guidance method that operates purely on trajectory signals. TAG uses an intermediate sample as a projection basis and amplifies the tangential components of the estimated score to correct the sampling trajectory. A first-order Taylor analysis shows that this steers the state toward higher-probability regions of the data manifold, reducing inconsistencies and improving fidelity while adding negligible overhead to existing samplers. Code is available at our Project Page (https://hyeon-cho.github.io/TAG/).

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 43 of its 55 references that are in the map. First posted on arXiv 6 Oct 2025.

Builds on

43 of 55 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Understanding Hallucinations in Diffusion Models through Mode Interpolation13 Jun

Other references · 42

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2020Denoising Diffusion Implicit Modelscited by 9,655
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  7. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  8. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  9. 2022Classifier-Free Diffusion Guidancecited by 5,717
  10. 2022Flow Matching for Generative Modelingcited by 5,426
  11. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
  12. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
30 more
  1. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  2. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  3. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  4. 2016Improved Techniques for Training GANscited by 2,938
  5. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,388
  6. 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,755
  7. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,375
  8. 2019ZeRO: Memory Optimizations Toward Training Trillion Parameter Modelscited by 1,278
  9. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,058
  10. 2023ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generationcited by 1,010
  11. 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 974
  12. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Modelscited by 924
  13. 2023UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Modelscited by 441
  14. 2023Analyzing and Improving the Training Dynamics of Diffusion Modelscited by 396
  15. 2024SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusioncited by 364
  16. 2023Rethinking FID: Towards a Better Evaluation Metric for Image Generationcited by 303
  17. 2024Guiding a Diffusion Model with a Bad Version of Itselfcited by 286
  18. 2024Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion Modelscited by 240
  19. 2023Manifold Preserving Guided Diffusioncited by 153
  20. 2022Improving Sample Quality of Diffusion Models Using Self-Attention Guidancecited by 151
  21. 2024Self-Rectifying Diffusion Sampling with Perturbed-Attention Guidancecited by 108
  22. 2024Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Modelscited by 107
  23. 2023Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Taskcited by 91
  24. 2024Smoothed Energy Guidance: Guiding Diffusion Models with Reduced Energy Curvature of Attentioncited by 55
  25. 2023Characteristic Guidance: Non-linear Correction for Diffusion Model at Large Guidance Scalecited by 26
  26. 2025Token Perturbation Guidance for Diffusion Modelscited by 14
  27. 2023SDDM: Score-Decomposed Diffusion Models on Manifolds for Unpaired Image-to-Image Translationcited by 13
  28. 2025TCFG: Tangential Damping Classifier-free Guidancecited by 12
  29. 2024Attention Overlap Is Responsible for The Entity Missing Problem in Text-to-image Diffusion Models!cited by 8
  30. 2025PLADIS: Pushing the Limits of Attention in Diffusion Models at Inference Time by Leveraging Sparsitycited by 7

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025RODS: Robust Optimization Inspired Diffusion Sampling for Detecting and Reducing Hallucination in Generative Models
  2. 2026Score-Control for Hallucination Reduction in Diffusion Models
  3. 2025Mitigating Diffusion Model Hallucinations with Dynamic Guidance
  4. 2025Laplacian Score Sharpening for Mitigating Hallucination in Diffusion Models
  5. 2026Hallucination Early Detection in Diffusion Models
  6. 2025Guided Path Sampling: Steering Diffusion Models Back on Track with Principled Path Guidance
  7. 2026OSCAR: Orchestrated Self-verification and Cross-path Refinement
  8. 2026On the Robustness of Distribution Support under Diffusion Guidance