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

Xinyi Wu

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

ML×1Crypto×1Info Retrieval×1

Frequent co-authors

Siyuan Liu1×
Ali Jadbabaie1×
Pei Chen1×
Geng Hong1×
Mengying Wu1×
Zixuan Zhu1×

Research Timeline

2026
Unveiling the Resilience of LLM-Enhanced Search Engines against Black-Hat SEO Manipulation

This paper systematically analyzes the resilience of LLM-enhanced search engines against black-hat SEO attacks, finding that while they block most traditional attacks, they remain vulnerable to sophisticated LLM-generated query manipulations.

How Data Shapes RoPE Frequency Usage: From Positional Scale Matching to Length Generalization

This paper explains how Rotary Position Embeddings (RoPE) frequencies in transformer models correspond to the relative-distance structure of training data, and the implications for long-context generalization.

Highlighted terms show continued research focus across papers

Papers

cs.LGEmpiricalRecentJul 8, 2026

How Data Shapes RoPE Frequency Usage: From Positional Scale Matching to Length Generalization

Xinyi Wu, Siyuan Liu, Ali Jadbabaie

This paper explains how Rotary Position Embeddings (RoPE) frequencies in transformer models correspond to the relative-distance structure of training data, and the implications for long-context genera…

View →
cs.CRcs.IRRecentMar 26, 2026

Unveiling the Resilience of LLM-Enhanced Search Engines against Black-Hat SEO Manipulation

Pei Chen, Geng Hong, Xinyi Wu, Mengying Wu +5 more

This paper systematically analyzes the resilience of LLM-enhanced search engines against black-hat SEO attacks, finding that while they block most traditional attacks, they remain vulnerable to sophis…

View →