collaborators

6 papers

cs.LG2025

Fast and scalable Wasserstein-1 neural optimal transport solver for single-cell perturbation prediction

Yanshuo Chen, Zhengmian Hu, Wei Chen +1

\textbf{Motivation:} Predicting single-cell perturbation responses requires mapping between two unpaired single-cell data distributions. Optimal transport (OT) theory provides a pr…

cs.CL2025

Towards Optimal Multi-draft Speculative Decoding

Zhengmian Hu, Tong Zheng, Vignesh Viswanathan +5

Large Language Models (LLMs) have become an indispensable part of natural language processing tasks. However, autoregressive sampling has become an efficiency bottleneck. Multi-Dra…

cs.CL2024

A Bayesian Approach to Harnessing the Power of LLMs in Authorship Attribution

Zhengmian Hu, Tong Zheng, Heng Huang

Authorship attribution aims to identify the origin or author of a document. Traditional approaches have heavily relied on manual features and fail to capture long-range correlation…

cs.CR2024

Inevitable Trade-off between Watermark Strength and Speculative Sampling Efficiency for Language Models

Zhengmian Hu, Heng Huang

Large language models are probabilistic models, and the process of generating content is essentially sampling from the output distribution of the language model. Existing watermark…

cs.CR2024

A Resilient and Accessible Distribution-Preserving Watermark for Large Language Models

Yihan Wu, Zhengmian Hu, Junfeng Guo +2

Watermarking techniques offer a promising way to identify machine-generated content via embedding covert information into the contents generated from language models. A challenge i…

cs.CR2024

Distortion-free Watermarks are not Truly Distortion-free under Watermark Key Collisions

Yihan Wu, Ruibo Chen, Zhengmian Hu +4

Language model (LM) watermarking techniques inject a statistical signal into LM-generated content by substituting the random sampling process with pseudo-random sampling, using wat…