Nan Sun

The paper introduces SafeHarness, a novel, lifecycle-integrated security architecture that significantly reduces unsafe behavior and attack success rates in LLM agents by weaving multiple defense layers directly into the agent's execution pipeline.

IstGPT introduces a novel LLM-based framework for real-time, fine-grained anomaly detection in complex industrial cyber-physical systems, achieving state-of-the-art performance across multiple benchmarks.

This paper proposes Head-Chunked Multi-Stream Pipeline (HCMS) to exploit the computational independence of multi-head attention and achieve fine-grained communication-computation overlap, resulting in speedups of up to 17.5% over the Ulysses baseline.