Ziqian Zeng 曾子倩

Logo

View My GitHub Profile

About me

I am Ziqian Zeng, I am now an associate professor at Shien-Ming Wu School of Intelligent Engineering, South China University of Technology.
My research area is natural language processing. I am interested in LLM Efficient Inference, LLM Privacy Protection, and LLM Safety.
View my Google Scholar.
View the Github Profile of my research group.

Education

Ph.D. Department of Computer Science and Engineering, the Hong Kong University of Science and Technology, 2016 - 2021, Supervisor: Yangqiu Song.

B.Eng. School of Computer Science and Engineering, South China University of Technology, 2012 - 2016.

Preprint

[7] Eraser: Jailbreaking Defense in Large Language Models via Unlearning Harmful Knowledge
Weikai Lu, Ziqian Zeng#, Jianwei Wang, Zhengdong Lu, Zelin Chen, Huiping Zhuang, Cen Chen. [pdf]

[6] Chimera: A Lossless Decoding Method for Accelerating Large Language Models Inference by Fusing all Tokens
Ziqian Zeng*, Jiahong Yu*, Qianshi Pang, Zihao Wang, Huiping Zhuang, Shao Hongen, Zou Xiaofeng. [pdf]

[5] PrivacyRestore: Privacy-Preserving Inference in Large Language Models via Privacy Removal and Restoration
Ziqian Zeng*#, Jianwei Wang*, ZhengdongLu, Huiping Zhuang, Cen Chen. [pdf]

[4] Federated Domain-Specific Knowledge Transfer on Large Language Models Using Synthetic Data
Haoran Li, Xinyuan Zhao, Dadi Guo, Hanlin Gu, Ziqian Zeng, Yuxing Han, Yangqiu Song, Lixin Fan, Qiang Yang. [pdf]

[3] Analytic Federated Learning
Huiping Zhuang, Run He, Kai Tong, Di Fang, Han Sun, Haoran Li, Tianyi Chen, Ziqian Zeng. [pdf]

[2] AIR: Analytic Imbalance Rectifier for Continual Learning
Di Fang, Yinan Zhu, Runze Fang, Cen Chen, Ziqian Zeng, Huiping Zhuang [pdf]

[1] GenderAlign: An Alignment Dataset for Mitigating Gender Bias in Large Language Models
Tao Zhang, Ziqian Zeng#, Yuxiang Xiao, Huiping Zhuang, Cen Chen, James Foulds, Shimei Pan. [pdf] [data]

Conference

[19] F-OAL: Foward-only Online Analytic Learning with Fast Training and Low Memory Footprint in Class Incremental Learning
Huiping Zhuang, Yuchen Liu, Run He, Kai Tong, Ziqian Zeng, Cen Chen, Yi Wang, Lap-Pui Chau. NeurIPS 2024. [pdf]

[18] GACL: Exemplar-Free Generalized Analytic Continual Learning
Huiping Zhuang, Yizhu Chen, Di Fang, Run He, Kai Tong, Hongxin Wei, Ziqian Zeng, Cen Chen. NeurIPS 2024. [pdf]

[17] PsFuture: A Pseudo-Future-based Zero-Shot Adaptive Policy for Simultaneous Machine Translation
Libo Zhao, Jing Li#, Ziqian Zeng#. EMNLP 2024. [pdf] [code]

[16] Dissecting Fine-Tuning Unlearning in Large Language Models
Yihuai Hong, Yuelin Zou, Lijie Hu, Ziqian Zeng, Di Wang, Haiqin Yang. EMNLP 2024 (short).

[15] Zero-shot Explainable Mental Health Analysis on Social Media by Incorporating Mental Scales
Wenyu Li#, Yinuo Zhu, Xin Lin, Ming Li, Ziyue Jiang, Ziqian Zeng#. WWW 2024 (short). [pdf] [code]

[14] On the use of Silver Standard Data for Zero-shot Classification Tasks in Information Extraction
Jianwei Wang, Tianyin Wang, Ziqian Zeng#. COLING 2024. [pdf] [code]

[13] Zero-shot Event Detection using a Textual Entailment Model as an Enhanced Annotator
Ziqian Zeng, Runyu Wu, Yuxiang Xiao, Xiaoda Zhong, Hanlin Wang, Zhengdong Lu, Huiping Zhuang. COLING 2024 (short). [pdf] [code]

[12] ConsistentEE: A Consistent and Hardness-Guided Early Exiting Method for Accelerating Language Models Inference
Ziqian Zeng*, Yihuai Hong*, Hongliang Dai, Huiping Zhuang and Cen Chen. AAAI 2024. [pdf][code]

[11] DS-AL: A Dual Stream Analytic Learning for Examplar-Free Class-Incremental Learning
Huiping Zhuang, Run He, Kai Tong, Ziqian Zeng, Zhiping Lin, Cen Chen. AAAI 2024. [pdf]

[10] Adaptive Policy with Wait-k Model for Simultaneous Translation
Libo Zhao, Kai Fan, Wei Luo, Jing Wu, Shushu Wang, Ziqian Zeng#, and Zhongqiang Huang#. EMNLP, 2023. [pdf] [code]

[9] From Ultra-Fine to Fine: Fine-tuning Ultra-Fine Entity Typing Models to Fine-grained
Hongliang Dai, and Ziqian Zeng. ACL, 2023. [pdf] [code]

[8] GKEAL: Gaussian Kernel Embedded Analytic Learning for Few-shot Class Incremental Task
Huiping Zhuang, Zhenyu Weng, Run He, Zhiping Lin, Ziqian Zeng. CVPR, 2023. [pdf] [code]

[7] Weakly Supervised Text Classification using Supervision Signals from a Language Model
Ziqian Zeng, Weimin Ni, Tianqing Fang, Xiang Li, Xinran Zhao, and Yangqiu Song. NAACL, 2022. [pdf] [code]

[6] Debiasing Career Recommendations with Neural Fair Collaborative Filtering
Rashidul Islam, Kamrun Naher Keya, Ziqian Zeng, Shimei Pan, and James Foulds. WWW, 2021. [pdf] [code]

[5] Fair Representation Learning for Heterogeneous Information Networks
Ziqian Zeng, Rashidul Islam, Kamrun Naher Keya, James Foulds, Yangqiu Song, and Shimei Pan. ICWSM, 2021. [pdf] [code]

[4] Variational Weakly Supervised Sentiment Analysis with Posterior Regularization
Ziqian Zeng, and Yangqiu Song. EACL, 2021. [pdf] [code]

[3] A Variational Approach to Weakly Supervised Document-Level Multi-Aspect Sentiment Classification
Ziqian Zeng, Wenxuan Zhou, Xin Liu, and Yangqiu Song. NAACL, 2019. [pdf] [code]

[2] Biased RandomWalk based Social Regularization for Word Embeddings
Ziqian Zeng*, Xin Liu*, and Yangqiu Song. IJCAI, 2018. [pdf] [code]

[1] Socialized Word Embeddings
Ziqian Zeng, Yichun Yin, Yangqiu Song, and Ming Zhang. IJCAI, 2017. [pdf] [code]

Journal

[1] Efficient Point Cloud Video Recognition via Spatio-Temporal Pruning for MEC Based Consumer Applications
Cen Chen, Songyu Xie, Jing Liu, Zhongyao Cheng, Ziqian Zeng, Huiping Zhuang, IEEE Transactions on Consumer Electronics, 2024. [pdf]

* Equal Contribution
# Correspondence Author

Academic Service

Teaching Experience