Song Li
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
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 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.
Papers
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…