Image de couverture de livre

Unlocking the Forgery Detection Potential of Vanilla MLLMs: A Novel Training-Free Pipeline

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zuo, Rui, Tong, Qinyue, Lu, Zhe-Ming, Lu, Ziqian
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

MediRound: Multi-Round Entity-Level Reasoning Segmentation in Medical Images
par: Tong, Qinyue, et autres
Publié: (2025)

MediSee: Reasoning-based Pixel-level Perception in Medical Images
par: Tong, Qinyue, et autres
Publié: (2025)

Improving Skeleton-based Action Recognition with Interactive Object Information
par: Wen, Hao, et autres
Publié: (2025)

MedVeriSeg: Teaching MLLM-Based Medical Segmentation Models to Verify Query Validity Without Extra Training
par: Lu, Ziqian, et autres
Publié: (2026)

From Training-Free to Adaptive: Empirical Insights into MLLMs' Understanding of Detection Information
par: Jiao, Qirui, et autres
Publié: (2024)

Bee: A High-Quality Corpus and Full-Stack Suite to Unlock Advanced Fully Open MLLMs
par: Zhang, Yi, et autres
Publié: (2025)

Unlocking the Potential of MLLMs in Referring Expression Segmentation via a Light-weight Mask Decoder
par: Wang, Jingchao, et autres
Publié: (2025)

Enhancing Frequency Forgery Clues for Diffusion-Generated Image Detection
par: Zhang, Daichi, et autres
Publié: (2025)

ForgeryGPT: A Multimodal LLM for Interpretable Image Forgery Detection and Localization
par: Zhang, Fanrui, et autres
Publié: (2024)

Diffusion Facial Forgery Detection
par: Cheng, Harry, et autres
Publié: (2024)

Enhancing Self-Supervised Talking Head Forgery Detection via a Training-Free Dual-System Framework
par: Liu, Ke, et autres
Publié: (2026)

360° Image Perception with MLLMs: A Comprehensive Benchmark and a Training-Free Method
par: Tran, Huyen T. T., et autres
Publié: (2026)

Video Forgery Detection for Surveillance Cameras: A Review
par: Tayfor, Noor B., et autres
Publié: (2025)

STEVE: A Step Verification Pipeline for Computer-use Agent Training
par: Lu, Fanbin, et autres
Publié: (2025)

Med-Scout: Curing MLLMs' Geometric Blindness in Medical Perception via Geometry-Aware RL Post-Training
par: Liu, Anglin, et autres
Publié: (2026)

Turning Generators into Retrievers: Unlocking MLLMs for Natural Language-Guided Geo-Localization
par: Chen, Yuqi, et autres
Publié: (2026)

Lifting the Veil on Visual Information Flow in MLLMs: Unlocking Pathways to Faster Inference
par: Yin, Hao, et autres
Publié: (2025)

Loupe: A Generalizable and Adaptive Framework for Image Forgery Detection
par: Jiang, Yuchu, et autres
Publié: (2025)

Taming Hallucinations: Boosting MLLMs' Video Understanding via Counterfactual Video Generation
par: Huang, Zhe, et autres
Publié: (2025)

Weakly-Supervised Image Forgery Localization via Vision-Language Collaborative Reasoning Framework
par: Sheng, Ziqi, et autres
Publié: (2025)

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs
par: Zhang, Qizhe, et autres
Publié: (2025)

Digital Image Forgery Detection Using Transfer Learning
par: Buyuk, Fatma Betul, et autres
Publié: (2026)

Signature Forgery Detection: Improving Cross-Dataset Generalization
par: Parracho, Matheus Ramos
Publié: (2025)

Field-Localized Forgery Detection for Digital Identity Documents
par: Kumar, Abhishek, et autres
Publié: (2026)

Suppressing Forgery-Specific Shortcuts for Generalizable Deepfake Detection
par: Wang, Yihui, et autres
Publié: (2026)

A Large-scale Universal Evaluation Benchmark For Face Forgery Detection
par: Bei, Yijun, et autres
Publié: (2024)

SUMI-IFL: An Information-Theoretic Framework for Image Forgery Localization with Sufficiency and Minimality Constraints
par: Sheng, Ziqi, et autres
Publié: (2024)

GTR-Turbo: Merged Checkpoint is Secretly a Free Teacher for Agentic VLM Training
par: Wei, Tong, et autres
Publié: (2025)

CAM-VFD: Cross-Attention Multimodal Video Forgery Detection
par: Elkhodary, Hoda Osama, et autres
Publié: (2026)

Training-Free Consistency Pipeline for Fashion Repose
par: Aghilar, Potito, et autres
Publié: (2025)

Preserving Forgery Artifacts: AI-Generated Video Detection at Native Scale
par: Li, Zhengcen, et autres
Publié: (2026)

FakeRadar: Probing Forgery Outliers to Detect Unknown Deepfake Videos
par: Li, Zhaolun, et autres
Publié: (2025)

CorrDetail: Visual Detail Enhanced Self-Correction for Face Forgery Detection
par: Zhou, Binjia, et autres
Publié: (2025)

MME-Reasoning: A Comprehensive Benchmark for Logical Reasoning in MLLMs
par: Yuan, Jiakang, et autres
Publié: (2025)

Order within Chaos: Capturing Intrinsic Energy Anomalies for AI-Manipulated Image Forgery Localization
par: Wang, Yiming, et autres
Publié: (2026)

Band-Attention Modulated RetNet for Face Forgery Detection
par: Zhang, Zhida, et autres
Publié: (2024)

UniShield: An Adaptive Multi-Agent Framework for Unified Forgery Image Detection and Localization
par: Huang, Qing, et autres
Publié: (2025)

AIFIND: Artifact-Aware Interpreting Fine-Grained Alignment for Incremental Face Forgery Detection
par: Wang, Hao, et autres
Publié: (2026)

FINER: MLLMs Hallucinate under Fine-grained Negative Queries
par: Xiao, Rui, et autres
Publié: (2026)

DMGD: Train-Free Dataset Distillation with Semantic-Distribution Matching in Diffusion Models
par: Wang, Qichao, et autres
Publié: (2026)