WeVisForensics:用於全方位 AI 生成影片檢測的自我演進智能體
WeVisForensics: Self-Evolving Agent for Omni AI-Generated Video Detection
WeVisForensics 提出自我演進的智能體框架,協調視覺及音訊取證檢查,以局部證據檢測 AI 生成影片,平均準確率達 95.2%。框架透過雙時間尺度強化學習優化調查智能體及取證檢查智能體,並整理出 ForenCue-30K。其準確率較最強的先前檢測器高 9.0%。
Abstract
WeVisForensics coordinates self-evolving visual and audio forensic inspector agents under a dual-timescale reinforcement learning policy to detect generated-video artifacts with localized evidence and high accuracy.
Recent advances in video generation call for reliable detection grounded in explicit forensic evidence. However, current methods primarily depend on single-pass chain-of-thought reasoning that overlooks brief or localized artifacts, or on predefined multi-agent workflows that offer limited flexibility in selecting relevant inspections. Even with adaptive investigation, optimizing the investigation policy alone does not directly improve the forensic capabilities of fixed experts. We introduce WeVisForensics, an agentic framework in which a main investigator agent coordinates a self-evolving library of forensic inspector sub-agents spanning visual and audio cues. The investigator learns which artifact type to examine, over which window, and when to conclude, and these interactions provide shared feedback for both levels of agents. Our dual-timescale policy optimization strategy, DTPO, closes this loop through fast reinforcement learning of the investigator and slower refinement of the inspectors, guided by annotated artifact intervals, to report subtle artifacts they once dismissed. Furthermore, we curate ForenCue-30K, combining role-specific forensic annotations and interaction trajectories to supervise individual inspections and their coordination, with an accompanying reinforcement-learning pool. Experiments show that WeVisForensics averages 95.2% detection accuracy across in-domain, out-of-domain and agentic benchmarks, 9.0% above the strongest prior detector, while grounding its verdicts in localized evidence.
View arXiv page View PDF Project page GitHub 25 Add to collection
Get this paper in your agent:
hf papers read 2611.21373
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 1
Video-Text-to-Text • Updated about 20 hours ago • 10tencent/WeVisForensics
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2611.21373 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2611.21373 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co