Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Fei Shen

Fei Shen

6 indexed papers

Recent (6 mo)
5
With code
0
Influential cites
0
Benchmarked
0

Publications per year

6
26

Top categories

Vision×2AI×2Info Retrieval×1Crypto×1Social Networks×1

Frequent co-authors

Yue Feng2×
Jingjing Li2×
Qijia Lu2×
Wei Ji2×
Jingrou Zhang2×
Xiao Li2×

Research Timeline

2026
UniDetect: LLM-Driven Universal Fraud Detection across Heterogeneous Blockchains

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.

TRACE: Trajectory Risk-Aware Compression for Long-Horizon Agent Safety

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.

TRACE: Trajectory Risk-Aware Compression for Long-Horizon Agent Safety

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.

Explainable Forensics of Manipulated Segments in Untrimmed Long Videos

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.

Explainable Forensics of Manipulated Segments in Untrimmed Long Videos

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.

Log-Insight: Automating Microservice Incident Diagnosis via Neuro-Symbolic Log Analysis

Log-Insight is an automated incident-diagnosis system for large-scale microservice systems that reduces raw events by 1,000-7,000x while preserving statistically significant failure signals, achieving high accuracy in under a minute.

Highlighted terms show continued research focus across papers

Papers

cs.IREmpiricalRecentJul 9, 2026

Log-Insight: Automating Microservice Incident Diagnosis via Neuro-Symbolic Log Analysis

Carlos Garcia-Hernandez, Aymane Abdali, Guangyu Wu, Mingxue Wang +3 more

Log-Insight is an automated incident-diagnosis system for large-scale microservice systems that reduces raw events by 1,000-7,000x while preserving statistically significant failure signals, achieving…

View →
cs.CVRecentJun 1, 2026

Explainable Forensics of Manipulated Segments in Untrimmed Long Videos

Yue Feng, Jingjing Li, Qijia Lu, Wei Ji +8 more

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.

View →
cs.CVRecentJun 1, 2026

Explainable Forensics of Manipulated Segments in Untrimmed Long Videos

Yue Feng, Jingjing Li, Qijia Lu, Wei Ji +8 more

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.

View →
cs.AIRecentMay 30, 2026

TRACE: Trajectory Risk-Aware Compression for Long-Horizon Agent Safety

Zhepei Hong, Lin Wang, Liting Li, Haokai Ma +4 more

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…

View →
cs.AIRecentMay 30, 2026

TRACE: Trajectory Risk-Aware Compression for Long-Horizon Agent Safety

Zhepei Hong, Lin Wang, Liting Li, Haokai Ma +4 more

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…

View →
cs.CRcs.SIApr 14, 2026

UniDetect: LLM-Driven Universal Fraud Detection across Heterogeneous Blockchains

Shuyi Miao, Wangjie Qiu, Shengda Zhuo, Fei Shen +4 more

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

View →