Tencent's WeVisForensics: Self-Evolving Agent System for AI-Generated Video Detection
tencent · hf · 2026-11-20
Tencent (WeChat Vision) and Nanjing University introduce WeVisForensics, an agentic framework for detecting AI-generated videos with localized forensic evidence.
- A lead investigator agent coordinates a self-evolving library of visual and audio forensic inspector sub-agents.
- A dual-timescale policy optimization (DTPO) loop uses fast RL for the investigator and slower refinement for inspectors, guided by annotated artifact intervals.
- Ships with Forencue-30K, a dataset of role-specific forensic annotations and interaction trajectories.
The work targets the weakness of single-pass chain-of-thought detectors that miss brief or localized artifacts.
More from Research
- ICML 2026 paper finds multi-agent LLM debates undergo a phase transition into biased consensus — Hidenori8Tanaka · 2026-11-20
- KAIST's VSpark Speeds Up Autoregressive VLA Robot Models 2.1x with Speculative Decoding — kaist-ai · 2026-11-20
- ByteDance's FlashMorph2: On-Policy Layer Selection for Hybrid Attention Models — ByteDance-Seed · 2026-11-20
- Amazon's CompoundingKernel Hits #1 on SOL-ExecBench with Self-Improving GPU Kernel Agents — AmazonScience · 2026-11-20
- WAM-Policy Brings Language-Conditioned Loco-Manipulation to Arm-Free Quadruped Robots — Maincode · 2026-11-20
- NVIDIA's NarrowSpec: Halving Draft Hidden Width Still Speeds Up Speculative Decoding 1.44x — nvidia · 2026-11-20