mlsanityData to 7 Oct 2026

Diagnosing and Correcting Concept Omission in Multimodal Diffusion Transformers

arXiv 2605.14270 ↗First posted 14 May 2026cs.CVcited by 1

On the map: Diffusion models → Robustness, privacy and adversarial aspects

Abstract (arXiv)

Multimodal Diffusion Transformers (MM-DiTs) have achieved remarkable progress in text-to-image generation, yet they frequently suffer from concept omission, where specified objects or attributes fail to emerge in the generated image. By performing linear probing on text tokens, we demonstrate that text embeddings can distinguish a characteristic `omission signal' representing the absence of target concepts. Leveraging this insight, we propose Omission Signal Intervention (OSI), which amplifies the omission signal to actively catalyze the generation of missing concepts. Comprehensive experiments on FLUX.1-Dev and SD3.5-Medium demonstrate that OSI significantly alleviates concept omission even in extreme scenarios.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models. Builds on 39 of its 44 references that are in the map. First posted on arXiv 14 May 2026.

Builds on

39 of 44 references.

References · 39

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  6. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  7. 2023Visual Instruction Tuningcited by 7,792
  8. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  9. 2022Classifier-Free Diffusion Guidancecited by 5,717
  10. 2022Flow Matching for Generative Modelingcited by 5,426
  11. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,310
  12. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
27 more
  1. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  2. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  3. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,338
  4. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
  5. 2016Understanding intermediate layers using linear classifier probescited by 1,279
  6. 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Modelcited by 1,259
  7. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,058
  8. 2023GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignmentcited by 946
  9. 2022In-context Learning and Induction Headscited by 930
  10. 2023Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Modelscited by 696
  11. 2022Perception Prioritized Training of Diffusion Modelscited by 301
  12. 2023BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusioncited by 280
  13. 2023Linguistic Binding in Diffusion Models: Enhancing Attribute Correspondence through Attention Map Alignmentcited by 169
  14. 2024Towards Understanding Cross and Self-Attention in Stable Diffusion for Text-Guided Image Editingcited by 134
  15. 2023A-STAR: Test-time Attention Segregation and Retention for Text-to-image Synthesiscited by 78
  16. 2024CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matchingcited by 60
  17. 2025Seg4Diff: Unveiling Open-Vocabulary Segmentation in Text-to-Image Diffusion Transformerscited by 24
  18. 2024A Cat Is A Cat (Not A Dog!): Unraveling Information Mix-ups in Text-to-Image Encoders through Causal Analysis and Embedding Optimizationcited by 19
  19. 2025Rethinking Cross-Modal Interaction in Multimodal Diffusion Transformerscited by 19
  20. 2025Exploring Multimodal Diffusion Transformers for Enhanced Prompt-based Image Editingcited by 16
  21. 2025ReFlex: Text-Guided Editing of Real Images in Rectified Flow via Mid-Step Feature Extraction and Attention Adaptationcited by 15
  22. 2024Toward Interactive Regional Understanding in Vision-Large Language Modelscited by 9
  23. 2025PLADIS: Pushing the Limits of Attention in Diffusion Models at Inference Time by Leveraging Sparsitycited by 7
  24. 2025Enhancing Text-to-Image Diffusion Transformer via Split-Text Conditioningcited by 7
  25. 2024Style-Friendly SNR Sampler for Style-Driven Generationcited by 5
  26. 2025Guiding What Not to Generate: Automated Negative Prompting for Text-Image Alignmentcited by 4
  27. 2026FlowFixer: Towards Detail-Preserving Subject-Driven Generationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026The Truth Stays in the Family: Enhancing Contextual Grounding via Inherited Truthful Heads in Model Lineagescited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026Semantic Steering for Controllable Generation: Tuning-Free Concept Erasure in Multimodal Diffusion Transformers
  2. 2026Prompt Reinjection: Alleviating Prompt Forgetting in Multimodal Diffusion Transformers for Text-to-Image Generation
  3. 2023The Hidden Language of Diffusion Models
  4. 2024EraseAnything: Enabling Concept Erasure in Rectified Flow Transformers
  5. 2026TexTailor: Inference-Time Textual Guidance Tailoring for Multimodal Diffusion Transformers
  6. 2026CoreUnlearn: Rethinking Concept Unlearning through Disentangled Component-Level Erasure in Text-guided Diffusion Models
  7. 2025Rare Text Semantics Were Always There in Your Diffusion Transformer
  8. 2025ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features