Author

Yihan Wu

3 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#natural language process... Feb 2025

Towards Optimal Multi-draft Speculative Decoding

The results show that the draft sampling method strongly influences the optimal acceptance rate, with sampling without replacement outperforming sampling with replacement, and the theoretical upper bound of MDSD efficiency is measured for the first time.

Zheng-Mian Hu, Tong Zheng, V. Viswanathan et al. · International Conference on... · 26 citations · ⚡4

#natural language process... Preprint Sep 2026

TTMark: Pairwise Distortion-Free Watermarking Beyond Single-Token Entropy

Tandem Token WaterMark (TTMARK), a general pairwise watermarking framework that extends distortion-free watermarking from individual tokens to adjacent token pairs, and introduces a branch-isolating concatenated tandem generation algorithm that efficiently constructs the joint distribution in a single forward pass.

Rui-Bo Chen, Zheng-Mian Hu, Dong-Hang Lu et al. · 0 citations

#natural language process... Feb 2026

More Haste, Less Speed: Weaker Single-Layer Watermark Improves Distortion-Free Watermark Ensembles

This work proposes a general framework that utilizes weaker single-layer watermarks to preserve the entropy required for effective multi-layer ensembling and demonstrates that this counter-intuitive strategy mitigates signal decay and consistently outperforms strong baselines in both detectability and robustness.

Ruibo Chen, Yihan Wu, Xuehao Cui et al. · arXiv.org · 2 citations