Shun Zhang
3 indexed papers
Recent (6 mo)
3With code
0Influential cites
0Benchmarked
0Publications per year
326
Top categories
AI×3ML×1Vision×1Crypto×1
Frequent co-authors
Research Timeline
2026
SafeHarness: Lifecycle-Integrated Security Architecture for LLM-based Agent Deployment
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.
RPCASSM: Robust PCA State Space Model For Infrared Small Target Detection
The paper proposes RPCASSM, a novel state space model leveraging Robust PCA (RPCA) to accurately detect and segment infrared small targets by separately modeling background and target information based on their unique spatial properties.
PC Layer: Polynomial Weight Preconditioning for Improving LLM Pre-Training
This paper proposes a preconditioning layer for stable weight conditioning in LLM training.
Highlighted terms show continued research focus across papers