Lijie Hu

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 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.