Jie Hu

PUSHAN is a novel, trace-free technique that successfully deobfuscates virtualization-obfuscated binaries, providing complete Control Flow Graphs (CFGs) and high-quality C pseudocode for effective analysis.

The paper proposes Functional Subspace Watermarking (FSW), a robust method that embeds ownership signals into a stable, low-dimensional functional subspace of LLMs, significantly improving detection accuracy against model modifications.

The paper introduces Kumushi, a root-cause-driven patching agent that significantly improves automated vulnerability repair by focusing LLMs on the true source of bugs, outperforming existing methods and matching commercial agents.

The paper proposes Multi-Adapter Representation Interventions via Energy Calibration (MARI), a method that adaptively adjusts the strength and direction of interventions across different inputs to improve alignment without degrading general model capabilities.

BayesNCL introduces a probabilistic gating mechanism to resolve the optimization conflict in Contrastive Learning, leading to highly disentangled and semantically consistent representations.

The paper introduces PaSBench-Video, a comprehensive streaming video benchmark designed to rigorously test multimodal LLMs' ability to issue proactive safety warnings, finding that current models struggle with temporal precision and high false-positive rates.