Metraipolis › archive › dc_23f285014bc7
VidForensics-M1: Meta-Detection Reinforcement Learning with Verifiable Temporal Grounding for AI-Generated Video Forensics — arXiv:2608.11201
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.11201
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T06:30:42.179Z
- SHA-256 of the archived text
d5a2254a2cfec011d51ad8e95b6805c680db5d5ebc699ba37211059bb33bb86e- Stable URL of this page
https://metraipolis.com/documento/dc_23f285014bc7
How to cite
VidForensics-M1: Meta-Detection Reinforcement Learning with Verifiable Temporal Grounding for AI-Generated Video Forensics — arXiv:2608.11201 — arXiv (en), https://arxiv.org/abs/2608.11201 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_23f285014bc7 (Metraipolis archive dc_23f285014bc7, sha256 d5a2254a2cfec011d51ad8e95b6805c680db5d5ebc699ba37211059bb33bb86e)
BibTeX
@misc{dc23f285014bc7,
title = {VidForensics-M1: Meta-Detection Reinforcement Learning with Verifiable Temporal Grounding for AI-Generated Video Forensics — arXiv:2608.11201},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.11201},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_23f285014bc7; sha256 d5a2254a2cfec011d51ad8e95b6805c680db5d5ebc699ba37211059bb33bb86e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.11201. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Recent advances in video generation models have significantly improved the realism of synthetic videos, blurring the boundary between generated and authentic content and raising concerns about misinformation. Existing MLLM-based detectors mainly rely on supervised fine-tuning or label-level reinforcement learning, where coarse supervision limits generalization to unseen scenarios and emerging video generators. To overcome these limitations, we are the first to introduce \textbf{meta-detection} into AI-generated video detection, enabling reliable forgery detection by jointly optimizing predicted labels and supporting evidence within reinforcement learning. This paradigm requires reliable evidence signals and effective mechanisms to integrate them into label-level optimization. Textual rationales provide semantic descriptions of forgery artifacts, but their generation and verification depend on external models, making supervision vulnerable to hallucinations and semantic biases. In contrast, temporal grounding provides more objective and verifiable evidence, as manipulated intervals can be precisely controlled during forgery construction. Based on this insight, we propose an automated data construction pipeline that generates paired real-fake videos by replacing temporal segments with boundary-frame-conditioned video generation models. Furthermore, we introduce \textbf{Evidence-Guided Reward Redistribution}, which performs evidence-aware credit assignment by redistributing rewards among label-correct responses according to evidence quality. This preserves reliable label supervision while encouraging detectors to acquire fine-grained and verifiable forgery localization capabilities. Extensive experiments demonstrate that \textbf{VidForensics-M1} effectively leverages verifiable temporal evidence to achieve robust and generalizable AI-generated video detection.
Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-12 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.11201 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T06:25:27.325Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).