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

Song Li

2 indexed papers

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

Publications per year

2
26

Top categories

NLP×1Crypto×1

Frequent co-authors

Jiebin Zhang1×
Zhenghan Yu1×
Song Liu1×
Eugene J. Yu1×
Zheng Li1×
Dawei Zhu1×

Research Timeline

2026
VIPER-MCP: Detecting and Exploiting Taint-Style Vulnerabilities in Model Context Protocol Servers

VIPER-MCP is a novel, end-to-end automated framework that detects and dynamically confirms the exploitability of taint-style vulnerabilities in Model Context Protocol (MCP) servers, achieving high-fidelity vulnerability discovery in real-world systems.

DFlare: Scaling Up Draft Capacity for Block Diffusion Speculative Decoding

DFlare introduces a lightweight layer-wise fusion mechanism to overcome the narrow conditioning bottleneck of existing block diffusion methods, enabling the scaling of draft models and achieving superior speculative decoding speedups across multiple LLMs.

Highlighted terms show continued research focus across papers

Papers

cs.CLRecentJun 1, 2026

DFlare: Scaling Up Draft Capacity for Block Diffusion Speculative Decoding

Jiebin Zhang, Zhenghan Yu, Song Liu, Eugene J. Yu +8 more

DFlare introduces a lightweight layer-wise fusion mechanism to overcome the narrow conditioning bottleneck of existing block diffusion methods, enabling the scaling of draft models and achieving super…

View →
cs.CRRecentMay 20, 2026

VIPER-MCP: Detecting and Exploiting Taint-Style Vulnerabilities in Model Context Protocol Servers

Pengyu Sun, Qishu Jin, Enhao Huang, Zifeng Kang +3 more

VIPER-MCP is a novel, end-to-end automated framework that detects and dynamically confirms the exploitability of taint-style vulnerabilities in Model Context Protocol (MCP) servers, achieving high-fid…

View →