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

Pengcheng Li

2 indexed papers

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

Info Retrieval×1Crypto×1AI×1

Frequent co-authors

Weisheng Li1×
Chuqiao Huang1×
Zhengchao Peng1×
Qiang Xiao1×
Zhongqian Xie1×
Qiang Huang1×

Research Timeline

2026
Mitigating Many-shot Jailbreak Attacks with One Single Demonstration

The paper proposes mitigating the progressive degradation of safety in language models caused by many-shot jailbreak attacks by appending a single, fixed safety demonstration at inference time.

PIANO: Personalized Reranking via Information Aggregation Node for Music Search Optimization

Proposes a personalized listwise re-ranking framework for music search to improve Click-Through Rate (CTR) and Conversion Rate (CVR) by aligning user preferences with current queries.

Highlighted terms show continued research focus across papers

Papers

cs.IREmpiricalRecentJun 15, 2026

PIANO: Personalized Reranking via Information Aggregation Node for Music Search Optimization

Weisheng Li, Chuqiao Huang, Pengcheng Li, Zhengchao Peng +4 more

Proposes a personalized listwise re-ranking framework for music search to improve Click-Through Rate (CTR) and Conversion Rate (CVR) by aligning user preferences with current queries.

View →
cs.CRcs.AIMay 8, 2026

Mitigating Many-shot Jailbreak Attacks with One Single Demonstration

Kejia Chen, Jiawen Zhang, Boheng Li, Pengcheng Li +5 more

The paper proposes mitigating the progressive degradation of safety in language models caused by many-shot jailbreak attacks by appending a single, fixed safety demonstration at inference time.

View →