Hyeseon An

SeqWM introduces a sequential behavioral watermarking framework that embeds ownership signals into history-conditioned transition patterns of LLM agent actions, providing robust and position-agnostic provenance tracking.

The paper introduces DLM-SWAI, a training-free method that effectively steers diffusion language models (DLMs) toward desired textual styles or properties by biasing the token distribution at each denoising step.

The paper introduces LUNA, a linguistically adaptive watermarking technique that achieves high detection accuracy across diverse languages while maintaining minimal text distortion, outperforming existing methods significantly.