2 papers
cs.CL2026
Dynamic Semantic Compression for Efficient Latent-Space Inference in Large Language Models
Peipei Li, Dongsen Zhang, Yuchen Liu +1
Large Language Models (LLMs) primarily perform inference at the token level, resulting in substantial memory overhead and compromised computational efficiency. In this paper, we pr…
cs.CR2025
MCP Security Bench (MSB): Benchmarking Attacks Against Model Context Protocol in LLM Agents
Dongsen Zhang, Zekun Li, Xu Luo +3
The Model Context Protocol (MCP) standardizes how large language model (LLM) agents discover, describe, and call external tools. While MCP unlocks broad interoperability, it also e…