Senyuan Shi — accepted AI-conference papers

2026

Veritas: Generalizable Deepfake Detection via Pattern-Aware Reasoning

Hao Tan, jun lan, Zichang Tan, Senyuan Shi, Ajian Liu, Chuanbiao Song +4

ICLR 2026oral

Deepfake detection remains a formidable challenge due to the evolving nature of fake content in real-world scenarios. However, existing benchmarks suffer from severe discrepancies from industrial practice, typically featuring homogeneous training sources and low-quality testing images, which hinder…

Cited by 0 Source ↗code ↗Scholar ↗

2026

VideoVeritas: AI-Generated Video Detection via Perception Pretext Reinforcement Learning

Hao Tan, jun lan, Senyuan Shi, Zichang Tan, Zijian Yu, Huijia Zhu +3

ICML 2026poster

The growing capability of video generation poses escalating security risks, making reliable detection increasingly essential. In this paper, we introduce **VideoVeritas**, a framework that integrates fine-grained perception and fact-based reasoning. We observe that while current multi-modal large la…

Cited by 0 Source ↗Scholar ↗