Fei Shen

UniDetect is a novel LLM-driven method that detects cross-chain cryptocurrency fraud by generating generalized transaction summaries, significantly outperforming existing detection techniques across multiple blockchains.

The paper proposes TRACE, a trajectory risk-aware compression method, to effectively aggregate sparse and delayed safety evidence across long agent trajectories, achieving state-of-the-art performance on multiple safety benchmarks.

This paper addresses the challenge of detecting and explaining AI-manipulated segments within long, untrimmed videos by proposing a new benchmark and a coarse-to-fine forensic detection framework.