Xiaojun Xu

Any-Depth Alignment: Unlocking Innate Safety Alignment of LLMs to Any-Depth

Reasoned Safety Alignment: Ensuring Jailbreak Defense via Answer-Then-Check

Robust Multi-bit Text Watermark with LLM-based Paraphrasers

BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning

Learning to Watermark LLM-generated Text via Reinforcement Learning

Progressive LLM Alignments Using Two-Player Games