跳到正文
实时
Hugging Face Daily Papers·· 8 小时前

WeVisForensics:一种用于全模态 AI 生成视频检测的自进化智能体

WeVisForensics: Self-Evolving Agent for Omni AI-Generated Video Detection

要点速览

WeVisForensics 通过双时间尺度强化学习策略协调自进化视觉和音频取证检查智能体,以高精度检测生成视频伪影并提供局部证据,在领域内、领域外和智能体基准测试中平均达到 95.2% 的检测准确率,比最强先验检测器高 9.0%。

正文

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

tencent/WeVisForensics

Video-Text-to-Text •

Updated about 23 hours ago

•

10

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.

来源: Hugging Face Daily Papers · huggingface.co