Metric-Aligned Group Relative Policy Optimization for Explainable Deepfake Detection
cs.CV
Submitted: 2026-11-10
Updated: 2026-11-10
Project page: https://explainable-deepfake-detection.github.io
Terminology
Sources
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Rethinking VLMs for Image Forgery Detection and Localization
- Rethinking Vision-Language Model in Face Forensics: Multi-Modal Interpretable Forged Face Detector
- Multiverse Through Deepfakes: The MultiFakeVerse Dataset of Person-Centric Visual and Conceptual Manipulations
- NTIRE 2026 Challenge on Robust AI-Generated Image Detection in the Wild
- SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Model
- Are Training Resources Insufficient? Predict First Then Explain!
- VIGIL: Part-Grounded Structured Reasoning for Generalizable Deepfake Detection
- Detecting Multimedia Generated by Large AI Models: A Survey
- OpenFake: An Open Dataset and Platform Toward Real-World Deepfake Detection
- XPlainVerse: A Million-Scale Benchmark for Explainable Deepfake Detection
- Explainable Deepfake Detection Challenge
- Training language models to follow instructions with human feedback
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- LLMs Are Not Yet Ready for Deepfake Image Detection
- DFBench: Benchmarking Deepfake Image Detection Capability of Large Multimodal Models
- Fully AI-Generated Image Detection: Definition, Recent Advances and Challenges
- DINOv3 Beats Specialized Detectors: A Simple Foundation Model Baseline for Image Forensics
- Simplicity Prevails: The Emergence of Generalizable AIGI Detection in Visual Foundation Models
- Brought a Gun to a Knife Fight: Modern VFM Baselines Outgun Specialized Detectors on In-the-Wild AI Image Detection
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs