跳到正文
腾讯混元模型发布·· 3 天前AI 评分58

腾讯发布 WeVisForensics:自进化智能体检测 AI 生成视频

tencent/WeVisForensics

AI 导读

腾讯发布 WeVisForensics,一个用于检测 AI 生成视频的自进化智能体检测器,主调查智能体协调视觉外观、物理一致性、常识、屏幕文字、语音内容与声纹等检查子智能体。

正文 · 原文

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

Paper: WeVisForensics: Self-Evolving Agent for Omni AI-Generated Video Detection | Code: Tencent/WeVisForensics | Project Page: WeVisForensics

WeVisForensics is a self-evolving agentic detector of AI-generated video. A main investigator agent coordinates forensic inspector sub-agents for visual appearance, physical consistency, common sense, on-screen text, speech content, and voice profile. This repository releases the five LoRA adapters of WeVisForensics-4B, trained with DTPO on top of Qwen3.5-4B.

Released Adapters

Adapter Purpose
main Main investigator agent
visual_appearance Visual-appearance inspector
physical_consistency Physical-consistency inspector
common_sense Common-sense inspector
ocr_consistency On-screen text inspector

All five adapters are rank 64 and alpha 128 on Qwen/Qwen3.5-4B, in BF16. skill_card.json holds the inspector skill cards used at inference.

Quick Start

Clone the code repository, then deploy in one of three ways.

Multi-GPU. Merge each adapter into the base model, then point the inference config at the merged model and at the bundled skill_card.json:

python scripts/merge_lora.py --base Qwen/Qwen3.5-4B --adapters <local copy of this repo> --output <merged dir>

Single GPU. Serve all five adapters from one vLLM process without merging:

BASE=Qwen/Qwen3.5-4B ADAPTERS=<local copy of this repo> \
  GPU_MEMORY_UTILIZATION=0.66 bash scripts/serve_lora.sh

Transformers. Run the whole agent in-process on one GPU with at least 24 GB, without vLLM. This backs the Gradio demo and the HF Mirror Space:

pip install -r demo/requirements.txt "gradio>=6.0"
WVF_ADAPTERS=tencent/WeVisForensics python demo/app.py

See the repository README for the full commands.

Intended Use

The release is intended for research in AI-generated video forensics. It is not intended for malicious use or for making autonomous high-impact decisions about individuals.

License

Unless otherwise noted, the adapters and Tencent-authored code are released under the Apache License 2.0. Speech, speaker, and OCR third-party models keep their own licenses.

Citation

If WeVisForensics is helpful to your work, please consider giving us a ⭐ and citing:

@misc{du2026wevisforensicsselfevolvingagentomni,
      title={WeVisForensics: Self-Evolving Agent for Omni AI-Generated Video Detection}, 
      author={Yipeng Du and Yuxi Li and Ying Zhang and Chong Sun and Chen Li and Jing Lyu and Ying Tai},
      year={2026},
      eprint={2611.21373},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2611.21373}, 
}

来源:腾讯混元模型发布 · hf-mirror.com