Kangli Zi — accepted AI-conference papers

2025

LightFair: Towards an Efficient Alternative for Fair T2I Diffusion via Debiasing Pre-trained Text Encoders

Boyu Han, Qianqian Xu, Shilong Bao, Zhiyong Yang, Kangli Zi, Qingming Huang

NeurIPS 2025poster

This paper explores a novel lightweight approach LightFair to achieve fair text-to-image diffusion models (T2I DMs) by addressing the adverse effects of the text encoder. Most existing methods either couple different parts of the diffusion model for full-parameter training or rely on auxiliary netwo…

Cited by 0 Source ↗code ↗Scholar ↗

2021

SOM-NCSCM : An Efficient Neural Chinese Sentence Compression Model Enhanced with Self-Organizing Map

Kangli Zi, Shi Wang, Yu Liu, Jicun Li, Yanan Cao, Cungen Cao

EMNLP 2021main

Sentence Compression (SC), which aims to shorten sentences while retaining important words that express the essential meanings, has been studied for many years in many languages, especially in English. However, improvements on Chinese SC task are still quite few due to several difficulties: scarce o…

Cited by 7 Source ↗PDF ↗code ↗Scholar ↗