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

Han Yang

3 indexed papers

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

Publications per year

3
26

Top categories

NLP×3Crypto×1AI×1Software Eng.×1

Frequent co-authors

Mingyan Wu2×
Omer Ben-Porat2×
Yftah Ziser2×
Jin Lu1×
Xuening Han1×
Yang Zhong1×

Research Timeline

2026
When Knowledge Is Not Free: Cost-Aware Evidence Selection in Retrieval-Augmented Generation

This paper introduces cost-aware Retrieval-Augmented Generation (RAG), demonstrating that fixed evidence selection is brittle and that adaptive, agentic controllers are necessary for effective knowledge retrieval under budget constraints.

When Knowledge Is Not Free: Cost-Aware Evidence Selection in Retrieval-Augmented Generation

This paper introduces cost-aware Retrieval-Augmented Generation (RAG), demonstrating that fixed evidence selection is brittle and that adaptive, agentic controllers are necessary for effective knowledge retrieval under budget constraints.

VICBench: A Multi-Language Benchmark for Code Vulnerability Detection

This paper introduces VICBench, a benchmark dataset of 100 verified vulnerability-inducing commits (VICs) for 100 CVEs across 88 projects in Python, Java, and C++, featuring complex real-world vulnerability fixes and VICs.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.AIcs.CLDatasetRecentAug 12, 2026

VICBench: A Multi-Language Benchmark for Code Vulnerability Detection

Jin Lu, Xuening Han, Yang Zhong, Lin Tan +3 more

This paper introduces VICBench, a benchmark dataset of 100 verified vulnerability-inducing commits (VICs) for 100 CVEs across 88 projects in Python, Java, and C++, featuring complex real-world vulnera…

View →
cs.CLRecent
Jun 1, 2026

When Knowledge Is Not Free: Cost-Aware Evidence Selection in Retrieval-Augmented Generation

Mingyan Wu, Han Yang, Omer Ben-Porat, Yftah Ziser

This paper introduces cost-aware Retrieval-Augmented Generation (RAG), demonstrating that fixed evidence selection is brittle and that adaptive, agentic controllers are necessary for effective knowled…

View →
cs.CLRecentJun 1, 2026

When Knowledge Is Not Free: Cost-Aware Evidence Selection in Retrieval-Augmented Generation

Mingyan Wu, Han Yang, Omer Ben-Porat, Yftah Ziser

This paper introduces cost-aware Retrieval-Augmented Generation (RAG), demonstrating that fixed evidence selection is brittle and that adaptive, agentic controllers are necessary for effective knowled…

View →