mlsanityData to 7 Oct 2026

REVEAL: Reference-Grounded Reasoning for Multimodal Manipulation Detection

arXiv 2605.28459 ↗First posted 27 May 2026cs.CVcited by 1

On the map: Mixture-of-experts → Multimodal MoE models

Abstract (arXiv)

Multimodal manipulation detection aims to simultaneously identify forged image--text pairs and localize tampered regions, yet existing methods typically rely on memorizing isolated artifacts and struggle with imperceptible manipulation traces or domain shifts. Inspired by human comparative reasoning, we reformulate this task as a reference-grounded verification problem, where authenticity is assessed by comparing a query against retrieved authentic evidence. We propose REVEAL Reference-Enabled Verification for Evidence Analysis and Localization), a framework explicitly designed for this comparative paradigm. To support this paradigm, we construct a large-scale reference library comprising 170K authentic news image--text pairs featuring over 40K public figures. Technically, REVEAL employs a difference-aware fusion mechanism to capture fine-grained discrepancies between the query and retrieved evidence. Furthermore, we introduce a task-decoupled Mixture-of-Experts (MoE) architecture to jointly execute instance-level detection and fine-grained grounding, effectively mitigating optimization conflicts between these heterogeneous objectives. Extensive experiments demonstrate that REVEAL significantly outperforms state-of-the-art methods, and notably enables training-free domain adaptation by simply updating the reference library, offering a robust and practical solution for detecting evolving misinformation. Code is available at https://anonymous.4open.science/r/REVEAL-Reference-A006.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Multimodal MoE models, one of 12 directions in Mixture-of-experts. Builds on 31 of its 41 references that are in the map. First posted on arXiv 27 May 2026.

Builds on

31 of 41 references.

References · 31

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  3. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
  4. 2017Billion-scale similarity search with GPUscited by 2,477
  5. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  6. 2020GShard: Scaling Giant Models with Conditional Computation and Automatic Shardingcited by 1,601
  7. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,361
  8. 2021ViLT: Vision-and-Language Transformer Without Convolution or Region Supervisioncited by 1,224
  9. 2019FaceForensics++: Learning to Detect Manipulated Facial Imagescited by 1,095
  10. 2019Face X-ray for More General Face Forgery Detectioncited by 469
  11. 2022On the detection of synthetic images generated by diffusion modelscited by 282
  12. 2022MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Textcited by 216
19 more
  1. 2024RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMscited by 200
  2. 2023Raising the Bar of AI-generated Image Detection with CLIPcited by 163
  3. 2023Transcending Forgery Specificity with Latent Space Augmentation for Generalizable Deepfake Detectioncited by 126
  4. 2020Visual News: Benchmark and Challenges in News Image Captioningcited by 121
  5. 2022Towards the Detection of Diffusion Model Deepfakescited by 111
  6. 2023Detecting and Grounding Multi-Modal Media Manipulationcited by 98
  7. 2024Wiki-LLaVA: Hierarchical Retrieval-Augmented Generation for Multimodal LLMscited by 79
  8. 2021Deepfake Detection by Human Crowds, Machines, and Machine-informed Crowdscited by 58
  9. 2023Detecting and Grounding Multi-Modal Media Manipulation and Beyondcited by 55
  10. 2024IM-RAG: Multi-Round Retrieval-Augmented Generation Through Learning Inner Monologuescited by 40
  11. 2024FKA-Owl: Advancing Multimodal Fake News Detection through Knowledge-Augmented LVLMscited by 38
  12. 2023Read it Twice: Towards Faithfully Interpretable Fact Verification by Revisiting Evidencecited by 17
  13. 2024MiRAGeNews: Multimodal Realistic AI-Generated News Detectioncited by 15
  14. 2024ASAP: Advancing Semantic Alignment Promotes Multi-Modal Manipulation Detecting and Groundingcited by 15
  15. 2023Unified Frequency-Assisted Transformer Framework for Detecting and Grounding Multi-Modal Manipulationcited by 14
  16. 2024Multimodal Misinformation Detection by Learning from Synthetic Data with Multimodal LLMscited by 13
  17. 2025TRUST-VL: An Explainable News Assistant for General Multimodal Misinformation Detectioncited by 10
  18. 2025The Coherence Trap: When MLLM-Crafted Narratives Exploit Manipulated Visual Contextscited by 8
  19. 2025Beyond Artificial Misalignment: Detecting and Grounding Semantic-Coordinated Multimodal Manipulationscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Mandela-Bench: Multimodal Models Remember Canonical Images Instead of Seeing Themcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Evidence-Grounded Forensic Reasoning for Detecting and Grounding Multi-Modal Media Manipulation
  2. 2024ForgerySleuth: Empowering Multimodal Large Language Models for Image Manipulation Detection
  3. 2025ManipShield: A Unified Framework for Image Manipulation Detection, Localization and Explanation
  4. 2026CORE: Conflict-Oriented Reasoning for General Multimodal Manipulation Detection
  5. 2025SGS: Segmentation-Guided Scoring for Global Scene Inconsistencies
  6. 2025Propose and Rectify: A Forensics-Driven MLLM Framework for Image Manipulation Localization
  7. 2024EditScout: Locating Forged Regions from Diffusion-based Edited Images with Multimodal LLM
  8. 2025REVEAL -- Reasoning and Evaluation of Visual Evidence through Aligned Language