Weiqing He — accepted AI-conference papers

2026

Break the Trade-off Between Watermark Strength and Speculative Sampling Efficiency for Language Models

Weiqing He, Xiang Li, Li Shen, Weijie J Su, Qi Long

ICLR 2026poster

Watermarking is a principled approach for tracing the provenance of large language model (LLM) outputs, but its deployment in practice is hindered by inference inefficiency. Speculative sampling accelerates inference, with efficiency improving as the acceptance rate between draft and target models i…

Cited by 0 Source ↗Scholar ↗

2025

On the Empirical Power of Goodness-of-Fit Tests in Watermark Detection

Weiqing He, Xiang Li, Tianqi Shang, Li Shen, Weijie J Su, Qi Long

NeurIPS 2025spotlight

Large language models (LLMs) raise concerns about content authenticity and integrity because they can generate human-like text at scale. Text watermarks, which embed detectable statistical signals into generated text, offer a provable way to verify content origin. Many detection methods rely on pivo…

Cited by 0 Source ↗Scholar ↗