Yihan Wu

An Ensemble Framework for Unbiased Language Model Watermarking

Model Correlation Detection via Random Selection Probing

Analyzing and Evaluating Unbiased Language Model Watermark

An Unlearning-Enhanced General Framework for Test-Time Adaptation

Modality-Balancing Preference Optimization of Large Multimodal Models by Adversarial Negative Mining

Robust Distortion-Free Watermark for Autoregressive Audio Generation Models

A Watermark for Order-Agnostic Language Models

Towards Optimal Multi-draft Speculative Decoding

De-mark: Watermark Removal in Large Language Models

Pseudo- vs. True-Randomness: Rethinking Distortion-Free Watermarks of Language Models under Watermark Key Collisions

RAG$^C$: Towards Copyright Protection for Knowledge Bases of Retrieval-augmented Language Models