Peng Zhang

The paper proposes R-CoT, a reasoning-layer watermarking framework that embeds ownership watermarks directly into the stable reasoning path of LLMs, achieving high robustness against perturbations.

Permit is a novel framework that enforces fine-grained, permission-aware control over the hidden states of LLMs, preventing information leakage even when sensitive data is present in the context.

The paper proposes EMSFD, an evidence-based decision modeling approach that enhances synthetic face detection reliability and generalizability by explicitly modeling class evidence and incorporating uncertainty-driven active learning.

The paper introduces FORCEBENCH, a new stress test designed to evaluate whether cited sources genuinely warrant the strength of a claim, revealing that standard citation evaluation methods often fail to detect over-strong claims.

The paper proposes a pose-conditioned, permutation-equivariant denoiser to accurately reconstruct work zone geometry using noisy Ultra-Wideband (UWB) range data from connected and autonomous vehicles (CAVs).