Peng Hu

The paper introduces ImageProtector, a user-side method that embeds an imperceptible perturbation into images to prevent Multi-modal Large Language Models (MLLMs) from analyzing and extracting sensitive information from them.

The paper presents a large-scale study demonstrating that tool cloning is a pervasive and severe source of hidden duplication in agent-tool ecosystems, necessitating changes in how tool diversity is measured.

The paper introduces Accordion, an end-to-end framework that significantly improves the efficiency of compiling fermionic Hamiltonians into quantum circuits for simulation on constrained quantum hardware.

This paper demonstrates that fusing multi-viewpoint data from multiple satellites significantly enhances the accuracy of space object detection in congested LEO constellations, establishing multi-view fusion as an effective strategy.

The paper proposes TDPM, a time-aware diffusion model for generative recommendation, which significantly improves recommendation accuracy by explicitly modeling the non-stationary, time-evolving nature of user preferences.