Tencent releases WeVisForensics-4B AI video detector
Tencent’s WeVisForensics repository releases five LoRA adapters for WeVisForensics-4B, built on Qwen3.5-4B and trained with DTPO. According to the repository, a main investigator agent coordinates inspector sub-agents that examine visual appearance, physical consistency, common sense, on-screen text, speech content, and voice profiles. Deployment options include merged models for multi-GPU use, five adapters served through vLLM on one GPU, and an in-process Transformers demo requiring at least 24 GB of GPU memory.
The release provides a concrete multi-agent architecture, five rank-64 LoRA adapters and documented deployment paths for research into AI-generated video forensics, though no independent performance results are included.
tencent/WeVisForensics Video-Text-to-Text • Updated about 2 hours ago • 10
license: apache-2.0 base_model: Qwen/Qwen3.5-4B library_name: peft pipeline_tag: video-text-to-text language:
- en tags:
- ai-generated-video-detection
- video-forensics
- omni-modal
- audio-visual
- agent
- multi-agent
- tool-use
- reinforcement-learning
- lora
- qwen3.5
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