Aohua Li

Knowdit is a knowledge-driven, agentic framework that significantly improves smart contract vulnerability detection by modeling shared DeFi semantics and leveraging historical audit knowledge.

This paper systematically investigates the vulnerability of near-field mmWave imaging to physical waveform-domain adversarial attacks, demonstrating that while deep learning algorithms show higher robustness than classical methods, the technology remains highly susceptible to concealment and alteration of targets.

The paper introduces Confidence-Adaptive SwiGLU ($κ$-SwiGLU), a novel gating mechanism for Mixture-of-Experts (MoE) models that dynamically adjusts the gate sharpness based on token-level routing confidence, improving performance with minimal overhead.

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.