Zhiliang Tian   田植良 Associate Professor, Department of Computer, National University of Defense Technology (NUDT). Email: ztianac [AT] cse.ust.hk [Google Scholar]

Biography

I am an associate professor at NUDT. Before that, I received my Ph.D. degree from the Hong Kong University of Science and Technology (HKUST) supervised by Prof. Nevin L. Zhang. I received my B.E. degree from Harbin Institute of Technology supervised by Prof. Ting Liu and Prof. Haifeng Wang and worked at Baidu for three years. During my Ph.D. study, I was a visitor at ML2 Group, New York University, supervised by Dr. He He; I was an intern at Tencent. AI Lab, supervised by Dr. Wei Bi.

News

One of my demo papers was selected as CCL-2023 best demo.

One of my papers was accpeted by PRICAI 2023.

I was invited to deliver a tutorial about LLMs and privacy at NLGIW 2023.

One of my papers was accpeted by ICCV 2023.

Two of my papers was accpeted by ICASSP 2023.

Two of my papers were accpeted by ACL 2022 (one main conference paper and one finding paper).

One of my papers was accpeted by IJCAI 2023.

Two of my papers was accpeted by WWW 2023.

Four of my papers were accpeted by EMNLP 2022 (two main conference papers and two finding papers).

One of my papers was accpeted by NeurIPS 2022.

I was invited and will be an Area Chair of EMNLP 2022 and will serve for natural language generation area.

Interests

I have a broad interest in natural language processing and machine learning, especially text generation, conversation systems, privacy protection.

Education

• Ph. D., 2018 - 2022, Computer Science and Engineering, the Hong Kong University of Science and Technology (HKUST)
  supervised by Prof. Nevin L. Zhang
  

• Visiting Student, 2020 - 2021, Computer Science, New York University (NYU)
  supervised by Dr. He He
  

• B. Eng., 2010 - 2014, Computer Science and Technology, Harbin Institute of Technology (HIT)
  supervised by Prof. Ting Liu and Prof. Haifeng Wang
  

Work Experience

• Research Assistant, Jan. 2018 - Aug. 2018, Computer Science and Engineering, HKUST
  supervised by Prof. Nevin L. Zhang
  

• Intern / Engineer / Senior Engineer, Jul. 2013 - Dec. 2017, NLP department, Baidu Inc.
  supervised by Mr. Daxiang Dong and Dr. Dianhai Yu
  

Selective Publications (first or corresponding author papers)

• Scenario-independent Uncertainty Estimation for LLM-based QuestionAnswering via Factor Analysis
  Zhihua Wen, Zhizhao Liu, Zhiliang Tian, Shilong Pan, Zhen Huang, Dongsheng Li, Minlie Huang.
  The Web Conference, 2025 (WWW 2025).
  


• Test-Time Adaptation on Noisy Data via Model-pruning-based Filtering and Flatness-aware Entropy Minimization
  Xingzhi Zhou, Zhiliang Tian, Boyang Zhang, Yibo Zhang, Ka Chun Cheung, Simon See,Hao Yang , Yun Zhou, Nevin L. Zhang.
  Association for the Advancement of Artificial Intelligence, 2025 (AAAI 2025).
  


• Zero-resource Hallucination Detection for Text Generation via Graph-based Contextual Knowledge Triples Modeling
  Xinyue Fang, Zhen Huang, Zhiliang Tian, Minghui Fang, Ziyi Pan, Quntian Fang, Zhihua Wen, Hengyue Pan, Dongsheng Li.
  Association for the Advancement of Artificial Intelligence, 2025 (AAAI 2025).
  


• MiSum: Multi-modality Heterogeneous Code Graph Learning for Multi-intent Binary Code Summarization
  Kangchen Zhu, Zhiliang Tian, Shangwen Wang, Weiguo Chen, Zixuan Dong, Mingyue Leng, Xiaoguang Mao.
  Fast Software Encryption Conference, 2025 (FSE 2025).
  


• LT0S: Layout-controllable Text object Synthesis via Adaptive Cross attention Fusions
  Zhao Xiaoran, Wu Tianhao, Lai Yu, Zhiliang Tian, Huang Zhen, Liu Yahui, He Zejiang, Li Dongsheng.
  IEEE International Conference on Acoustics, Speech, and Signal Processing, 2025 (ICASSP 2025).
  


• Resilient Test-Time Adaptation by Mitigating Batch-Normalization Overfitting
  Xingzhi Zhou, Boyang Zhang, Zhiliang Tian, Yibo Zhang, Xin Niu, Ka Chun Cheung, Simon See, Nevin L. Zhang.
  IEEE International Conference on Acoustics, Speech, and Signal Processing, 2025 (ICASSP 2025).
  


• Multi-pattern retrieval-augmented framework for Text-to-SQL with Poincaré-Skeleton retrieval and meta-instruction reasoning
  Chunxi Guo, Zhiliang Tian, Jintao Tang, Shasha Li, Ting Wang.
  Information Processing and Management, 2025 (IPM 2025).
  


• Perception of knowledge boundary for large language models through semi-open-ended question answering
  Zhihua Wen, Zhiliang Tian, Zexin Jian, Zhen Huang, Pei Ke, Yifu Gao, Minlie Huang, Dongsheng Li.
  Neural Information Processing Systems, 2024 (NeurIPS 2024).
  


• PRIMAL: Prompting Multiple Language Models for Low-resource Diverse Response Generation
  Zhihua Wen*, Zhiliang Tian*, Shilong Pan, Kangchen Zhu, Xiangyun Meng, Yiping Song; Dongsheng Li.
  Transactions on Audio, Speech, and Language Processing, 2024 (TASLP 2024).
  


• Context-aware Watermark with Semantic Balanced Green-red Lists for Large Language Models
  Yuxuan Guo, Zhiliang Tian, Yiping Song, Tianlun Liu, Liang Ding, Dongsheng Li.
  Conference on Empirical Methods in Natural Language Processing, 2024 (EMNLP 2024).
  


• POMP: Probability-driven Meta-graph Prompter for LLMs in Low-resource Unsupervised Neural Machine Translation.
  Shilong Pan, Zhiliang Tian, Liang Ding, Haoqi Zheng, Zhen Huang, Zhihua Wen, Dongsheng Li+.
  Annual Meeting of the Association for Computational Linguistics, 2024 (ACL 2024).
  


• 360°REA: Towards A Reusable Experience Accumulation with $360^\circ$ Assessment for Multi-Agent System.
  Shen Gao*, Hao Li*, Zhengliang Shi, Chengrui Huang, Quan Tu, Shuo Shang, Zhiliang Tian, Minlie Huang.
  Annual Meeting of the Association for Computational Linguistics, 2024 (ACL(Finding) 2024).
  


• Intent-Aware and Hate-Mitigating Counterspeech Generation via Dual-Discriminator Guided LLMs.
  Haiyang Wang, Zhiliang Tian, Xin Song, Yue Zhang, Yuchen Pan, Hongkui Tu, Minlie Huang, Bin Zhou.
  International Conference on Computational Linguistics, 2024 (COLING 2024).
  


• StyleFlow: Disentangle Latent Representations via Normalizing Flow for Unsupervised Text Style Transfer.
  Kangchen Zhu, Zhiliang Tian, Jingyu Wei, Ruifeng Luo, Yiping Song, Xiaoguang Mao.
  International Conference on Computational Linguistics, 2024 (COLING 2024).
  


• Argumentative Relationship Recognition Based on End-to-End Multitask Learning.
  Jingyuan Huang, Quntian Fang, Sijie Wang, Zhiliang Tian, Feng Liu, Zhen Huang, Dongsheng Li.
  International Joint Conference On Knowledge Graphs, 2023 (IJCKG 2023).
  


• GROVE: A Retrieval-augmented Complex Story Generation Framework with A Forest of Evidence.
  Zhihua Wen, Zhiliang Tian, Wei Wu, Yuxin Yang, Yanqi Shi, Zhen Huang, Dongsheng Li.
  Conference on Empirical Methods in Natural Language Processing, 2023 (EMNLP(Finding) 2023).
  


• Self-Evolution Learning for Mixup: Enhance Data Augmentation on Few-Shot Text Classification Tasks.
  Haoqi Zheng, Qihuang Zhong, Liang Ding, Zhiliang Tian, Xin Niu, Changjian Wang, Dongsheng Li, Dacheng Tao.
  Conference on Empirical Methods in Natural Language Processing, 2023 (EMNLP 2023).
  


• A Multi-view Meta-learning Approach for Multi-modal Response Generation.
  Zhiliang Tian, Zheng Xie, Fuqiang Lin, Yiping Song.
  The Web Conference, 2023 (WWW 2023).
  


• DaMSTF: Domain Adversarial Learning Enhanced Meta Self-Training for Domain Adaptation.
  Menglong Lu, Zhen Huang, Yunxiang Zhao+, Zhiliang Tian, Yang Liu, Dongsheng Li.
  Annual Meeting of the Association for Computational Linguistics, 2023 (ACL 2023).
  


• GRACE: Gradient-guided Controllable Retrieval for Augmenting Attribute-based Text Generation.
  Zhihua Wen, Zhiliang Tian, Zhen Huang, Yuxin Yang, Zexin Jian, Changjian Wang, Dongsheng Li+.
  Annual Meeting of the Association for Computational Linguistics, 2023 (ACL(Finding) 2023).
  


• Meta-Tsallis-Entropy Minimization: a new Self-Training approach for domain adaptation on text classification.
  Menglong Lu, Zhen Huang, Zhiliang Tian, Yunxiang Zhao+, Xuanyu Fei, Dongsheng Li.
  International Joint Conference on Artificial Intelligence, 2023 (IJCAI 2023).
  


• Retrieval-augmented GPT-3.5-based Text-to-SQL Framework with Sample-aware Prompting and Dynamic Revision Chain.
  Chenxi Guo, Zhiliang Tian, Jintao Tang, Pancheng Wang, Zhihua Wen, Ting Wang.
  China National Conference on Computational Linguistics, 2023 (CCL 2023 (Best Demo Award)).
  


• Progressive Meta-Pooling Learning for Lightweight Image Classification Model.
  Peijie Dong, Xin Niu+, Zhiliang Tian, Lujun Li, Xiaodong Wang, Zimian Wei, Hengyue Pan, Dongsheng Li .
  ,IEEE International Conference on Acoustics, Speech and Signal Processing 2023 (ICASSP 2023).
  


• RD-NAS: Enhancing One-shot Supernet Ranking Ability via Ranking Distillation from Zero-cost Proxies.
  Peijie Dong, Xin Niu+, Lujun Li, Zhiliang Tian, Xiaodong Wang, Zimian Wei, Hengyue Pan, Dongsheng Li .
  ,IEEE International Conference on Acoustics, Speech and Signal Processing 2023 (ICASSP 2023).
  


• Prompting GPT-3.5 for Text-to-SQL with De-semanticization and Skeleton Retrieval.
  Chunxi Guo, Zhiliang Tian, Jintao Tang, Pancheng Wang, Zhihua Wen, Kang Yang and Ting Wang .
  Pacific Rim International Conference on Artificial Intelligence, 2023 (PRICAI 2023 ).
  


• SeqPATE: Differentially Private Text Generation via Knowledge Distillation.
  Zhiliang Tian, Yingxiu Zhao, Ziyue Huang, Yuxiang Wang, Nevin Zhang, He He.
  Conference on Neural Information Processing Systems, 2022 (NeurIPS 2022).
  


• Improving Meta-learning for Low-resource Text Classification and Generation via Memory Imitation.
  Yingxiu Zhao, Zhiliang Tian, Huaxiu Yao, Yinhe Zheng, Dongkyu Lee, Yiping Song, Jian Sun, Nevin Zhang
  Annual Meeting of the Association for Computational Linguistics, 2022 (ACL 2022).
  


• Hard Gate Knowledge Distillation - Leverage Calibration for Robust and Reliable Language Model.
  Dongkyu Lee, Zhiliang Tian, Yingxiu Zhao, Ka Chun Cheung, Nevin L. Zhang.
  Conference on Empirical Methods in Natural Language Processing, 2022 (EMNLP 2022).
  


• Empathetic and Emotionally Positive Conversation Systems with an Emotion-specific Query-Response Memory.
  Zhiliang Tian, Yinliang Wang, Yiping Song, Chi Zhang, Dongkyu Lee, Yingxiu Zhao, Dongsheng Li, Nevin L. Zhang.
  Conference on Empirical Methods in Natural Language Processing, 2022 (EMNLP (Finding) 2022).
  


• Emotion-aware Multimodal Pre-training for Image-grounded Emotional Response Generation.
  Zhiliang Tian*, Zhihua Wen*, Zhenghao Wu, Yiping Song, Jintao Tang, Dongsheng Li, Nevin L. Zhang
  International Conference on Database Systems for Advanced Applications, 2022 (DASFAA 2022).
  


• Learning from My Friends: Few-Shot Personalized Conversation Systems via Social Networks.
  Zhiliang Tian, Wei Bi, Zihan Zhang, Dongkyu Lee, Yiping Song, Nevin L. Zhang
  AAAI Conference on Artificial Intelligence, 2021 (AAAI 2021).
  


• Enhancing Content Preservation in Text Style Transfer Using Reverse Attention and Conditional Layer Normalization.
  Dongkyu Lee, Zhiliang Tian, Lanqing Xue and Nevin L. Zhang
  Annual Meeting of the Association for Computational Linguistics, 2021 (ACL 2021).
  


• Response-Anticipated Memory for On-Demand Knowledge Integration in Response Generation.
  Zhiliang Tian, Wei Bi, Dongkyu Lee, Lanqing Xue, Yiping Song, Xiaojiang Liu, Nevin L. Zhang
  Annual Meeting of the Association for Computational Linguistics, 2020 (ACL 2020).
  


• Learning to Abstract for Memory-augmented Conversational Response Generation.
  Zhiliang Tian, Wei Bi, Xiaopeng Li, Nevin L. Zhang
  Annual Meeting of the Association for Computational Linguistics, 2019 (ACL 2019).
  


• How to Make Contexts More Useful? An Empirical Study to Context-Aware Neural Conversation Models.
  Zhiliang Tian, Rui Yan, Lili Mou, Yiping Song, Yansong Feng, Dongyan Zhao
  Annual Meeting of the Association for Computational Linguistics, 2017 (ACL 2017).
  

* denotes the equal contribution

Awards & Scholarship

• YSSNLP-2024 Best Poster Award, CIPS, 2024

• CCL-2023 Best Demo Award, CIPS, 2023

• Academic Excellence Award, HKUST, 2021

• Finalist of Adobe fellowship (30 nominees from the world), Adobe Inc., 2021

• Outstanding reviewer of EMNLP'2020, EMNLP, 2020

• Top 40 in Baidu fellowship competition (Top 40 from the world), Baidu Inc., 2020

• Nominee of MSRA fellowship (27 nominees from Asia), Microsoft Inc., 2020

• SENG (School of Engineering) Academic Award, HKUST, 2020

• Excellent Patent Award, Tencent Inc., 2020

• Tencent AI Lab Rhino-Bird Gift Fund (24 awardees from the whole China), Tencent Inc., 2020

• Postgraduate Studentship, HKUST, 2018 - 2022

• IJCAI Travel Grant, IJCAI, 2018

• The Highest Award of Baidu, Baidu Inc., 2015

  Top 5 teams in Baidu, the highest group award in Baidu Inc. $1,000,000 reward for an 8-member team.

• The Star of Business Group, Baidu Inc., 2014

• Excellent Intern Award, Baidu Inc., 2013

• Meritorious Winner (First-class Prize), the Mathematical Contest in Modeling (MCM), 2013

• Pacemaker to Excellent Students Cadres, HIT. 2011 & 2012

• National Encouragement Scholarship, HIT. 2011 & 2012

Academic Services

• Conference Publication Chair:

  2024: CCL, CCKS-IJCKG

• Conference Area Chair:

  2024: ACL-ARR

  2023: ACL-ARR

  2022: EMNLP

• Conference Senior PC:

  2024: IJCAI

  2021: IJCAI

• Conference PC & Reviewer:

  2024: ICML, ICLR

  2023: ICML, NeurIPS, ICLR, UAI, ACL, IJCAI, EMNLP, CCKS, Coling

  2022: ICML, ICLR, UAI, ACL (ARR), IJCAI, AAAI

  2021: NeurIPS, ICLR, ACL, UAI, EMNLP, NAACL, AAAI, EACL, NLPCC

  2020: ACL, EMNLP (Outstanding reviewer), COLING, NLPCC

• Journal Reviewer:

  TNNLS, TBD, TASLP, TOPS

Talks & Teaching

• Keynote speaker at AIS seminar, CIPS, May 2019 & May 2020

• TA for Machine Learning (COMP 5212), HKUST, Spring 2020 & Spring 2022

• TA for Introduction to Artificial Intelligence (COMP 3211), HKUST, Spring 2019

• TA for Machine Learning (CSIT 6000), HKUST, Spring 2018 & Fall 2019

Selected Patents

• Audio Data Processing Method and Device, Storage Medium and Equipment. (ZL 202010612049.8, China)
  Zhiliang Tian
  


• Name Information Processing Method and Device Based on Name Prediction Model and Electronic Equipment. (ZL 202010362632.8, China)
  Zhiliang Tian
  


• Intelligent Text Processing Method and Device, Electronic Equipment and Storage Medium. (ZL 202010194392.5, China)
  Zhiliang Tian
  


• Artificial Intelligence-based News Recalling Method and Device, Equipment and Storage Medium. (ZL 201710413884.7, China)
  Zhiliang Tian, Daxiang Dong, Dianhai Yu
  


• Public Opinion Monitoring Method, Device, Equipment and Storage Medium. (ZL 201711131841.6, China)
  Zhiliang Tian, Daxiang Dong, Dianhai Yu