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

Chuan Shi

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

Robotics×1AI×1Software Eng.×1Crypto×1Info Retrieval×1

Frequent co-authors

Chenhao Bai1×
Liqin Lu1×
Kaijun Wang1×
Hui Chen1×
Jin-Chuan Shi1×
Yuyang Liu1×

Research Timeline

2026
BiRD: A Bidirectional Ranking Defense Mechanism for Retrieval Augmented Generation

The paper proposes BiRD, a bidirectional ranking defense mechanism that enhances the robustness of Retrieval-Augmented Generation (RAG) against adversarial attacks by analyzing the alignment between forward and backward document rankings.

ParaTool: Shifting Tool Representations from Context to Parameters

ParaTool introduces a novel framework that shifts tool representations from bulky context documentation to dedicated, loadable parameters, enabling efficient and robust tool calling in LLMs.

HORIZON: Recoverability-Governed Curriculum for Physical-Domain Scaling

This paper studies how to scale robust robot policies by expanding physical domains in a recoverable way.

Highlighted terms show continued research focus across papers

Papers

cs.RORecentJun 3, 2026

HORIZON: Recoverability-Governed Curriculum for Physical-Domain Scaling

Chenhao Bai, Liqin Lu, Kaijun Wang, Hui Chen +4 more

This paper studies how to scale robust robot policies by expanding physical domains in a recoverable way.

View →
cs.AIcs.SERecentMay 28, 2026

ParaTool: Shifting Tool Representations from Context to Parameters

Zekai Yu, Qi Meng, Qizhi Chu, Yu Hao +2 more

ParaTool introduces a novel framework that shifts tool representations from bulky context documentation to dedicated, loadable parameters, enabling efficient and robust tool calling in LLMs.

View →
cs.CRcs.IRRecentMay 19, 2026

BiRD: A Bidirectional Ranking Defense Mechanism for Retrieval Augmented Generation

Chengcai Gao, Zhihong Sun, Xiaochuan Shi, Qiufeng Wang +1 more

The paper proposes BiRD, a bidirectional ranking defense mechanism that enhances the robustness of Retrieval-Augmented Generation (RAG) against adversarial attacks by analyzing the alignment between f…

View →