Zhiyang Teng

News

TikTok Global Live — Research Intern Hiring! 🚀
Location: Singapore (preferred), Beijing, Shanghai, Shenzhen, Guangzhou, or Australia.
We build multimodal foundation models and large-scale RL for MoE to power real-world Live experiences: understanding fast-changing live scenes, following multi-speaker conversations, recognizing events and intents, and enabling unified understanding + generation for image/video (e.g., live highlights, interactive assistants, safer and smarter live content, and better creator/viewer engagement).
Who we’re looking for: hands-on builders who are rigorous, reliable, and love turning ideas into working systems.
Bonus skills: Triton/CUDA, Linear Attention (FLA), Omni Models, Large-Scale RL for MoE, multimodal LLMs, diffusion-based multimodal LLMs, and unified image/video generation + understanding models.
Interested? DM me with your CV + a short note on what you’ve built (GitHub / papers / projects welcome).

Books

1. Yue Zhang and Zhiyang Teng. Natural Language Processing: A Machine Learning Perspective. Cambridge University Press. 2021. 486 pages. Cambridge.org, Amazon.com, Google Books Preview Online Course . It took us four years to finish this book and it's on sale now.

2. Yupeng Liu, Jinfeng Yang, Zhiyang Teng. Machine Learning with Tensorflow (Chinese Edition). China Machine Press. 2019. 200 pages.

Conference/Journal Publications

34. LogicLLM: Exploring Self-supervised Logic-enhanced Training for Large Language Model. Fangkai Jiao, Zhiyang Teng, Shafiq Joty, Bosheng Ding, Aixin Sun, Zhengyuan Liu, Nancy F Chen. NAACL 2024. [Paper]

33. Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature. Guangsheng Bao, Yanbin Zhao, Zhiyang Teng, Linyi Yang, Yue Zhang. ICLR 2024. [Paper]

32. Refining Latent Homophilic Structures over Heterophilic Graphs for Robust Graph Convolution Networks. Chenyang Qiu, Guoshun Nan, Tianyu Xiong, Wendi Deng, Di Wang, Zhiyang Teng, Lijuan Sun, Qimei Cui, Xiaofeng Tao. AAAI 2024. [Paper]

31. LogiCoT: Logical Chain-of-Thought Instruction-Tuning Data Collection with GPT-4. Hanmeng Liu, Zhiyang Teng+, Leyang Cui, Chaoli Zhang, Qiji Zhou, Yue Zhang+. EMNLP 2023 Findings. (co-corresponding author) [Paper]

30. Non-Autoregressive Document-Level Machine Translation. Guangsheng Bao*, Zhiyang Teng*, Hao Zhou, Jianhao Yan, Yue Zhang. EMNLP 2023 Findings. [Paper]

29. How Well Do Text Embedding Models Understand Syntax? Yan Zhang, Zhaopeng Feng, Zhiyang Teng , Zuozhu Liu, Haizhou Li. EMNLP 2023 Findings.

28. YATO: Yet Another deep learning based Text analysis Open toolkit. Zeqiang Wang, Yile Wang, Jiageng Wu, Zhiyang Teng, Jie Yang. EMNLP 2023 Demo Track. [Paper]

27. Target-Side Augmentation for Document-Level Machine Translation. Guangsheng Bao, Zhiyang Teng, Yue Zhang. ACL 2023. [Paper]

26. Multimodal Relation Extraction with Cross-Modal Retrieval and Synthesis. Xuming Hu, Zhijiang Guo, Zhiyang Teng, Irwin King, Philip S. Yu. ACL 2023. [Paper]

25. Token-level Fitting Issues of Seq2seq Models. Guangsheng Bao, Zhiyang Teng, Yue Zhang. ACL RepL4NLP 2023 Workshop. [Paper]

24. LogiQA 2.0 — An Improved Dataset for Logical Reasoning in Natural Language Understanding. Hanmeng Liu, Jian Liu, Leyang Cui, Zhiyang Teng, Nan Duan, Ming Zhou, Yue Zhang. IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP) 2023.

23. Pre-Training a Graph Recurrent Network Language Model. Yile Wang, Linyi Yang, Zhiyang Teng, Ming Zhou and Yue Zhang. NeurIPS Efficient Natural Language and Speech Processing (ENLSP) Workshop 2022. [Paper] [Code]

22. METS-CoV: A Dataset of Medical Entity and Targeted Sentiment on COVID-19 Related Tweets. Peilin Zhou, Zeqiang Wang, Dading Chong, Zhijiang Guo, Yining Hua, Zichang Su, Zhiyang Teng, Jiageng Wu, Jie Yang. NeurIPS 2022 Datasets and Benchmarks Track. [Paper]

21. SemGloVe: Semantic Co-occurrences for GloVe from BERT. Leilei Gan*, Zhiyang Teng*, Yue Zhang*, Linchao Zhu, Fei Wu, Yi Yang. IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP) 2022. [Paper]

20. Contrastive Latent Variable Models for Neural Text Generation. Zhiyang Teng, Chenhua Chen, Yan Zhang, Yue Zhang. UAI 2022. [Paper] [Code]

19. Discrete Opinion Tree Induction for Aspect-based Sentiment Analysis. Chenhua Chen, Zhiyang Teng+, Zhongqing Wang, Yue Zhang+. ACL 2022. ( co-corresponding author) [Paper] [Code]

18. Solving Aspect Category Sentiment Analysis as a Text Generation Task. Jian Liu, Zhiyang Teng+, Leyang Cui, Hanmeng Liu and Yue Zhang. EMNLP 2021. + denotes corresponding author. [Paper] [Code]

17. G-Transformer for Document-level Machine Translation. Guangsheng Bao, Yue Zhang, Zhiyang Teng, Boxing Chen and Weihua Luo. ACL 2021. [Paper] [Code]

16. Dialogue State Induction Using Neural Latent Variable Models. Qingkai Min*, Libo Qin*, Zhiyang Teng*, Xiao Liu and Yue Zhang. IJCAI 2020. [Paper] [Slides] [Bib] (* indicates equal contributions.)

15. Inducing Target-Specific Latent Structures for Aspect Sentiment Classification. Chenhua Chen, Zhiyang Teng and Yue Zhang. EMNLP 2020. [Paper] [Code] [Video] [Bib]

14. Lightweight, Dynamic Graph Convolutional Networks for AMR-to-Text Generation. Yan Zhang*, Zhijiang Guo*, Zhiyang Teng, Wei Lu, Shay B. Cohen, Zuozhu Liu, Lidong Bing. EMNLP 2020. [Paper] [Code] [Video] [Slides]

13. Densely Connected Graph Convolutional Network for Graph-to-Sequence Learning. Zhijiang Guo*, Yan Zhang*, Zhiyang Teng and Wei Lu. TACL 2019. [Paper] [Code] [Video] [Slides]

12. Two Local Models for Neural Constituent Parsing. Zhiyang Teng and Yue Zhang. COLING 2018. [Paper] [Code][Bib]

11. DeepClue: Visual Interpretation of Text-based Deep Stock Prediction. Lei Shi, Zhiyang Teng, Le Wang, Yue Zhang and Alexander Binder. TKDE 2018. [PDF]

10. Head-Lexicalized Bidirectional Tree LSTMs. Zhiyang Teng and Yue Zhang. TACL 2017. [Paper] [Code] [Video]

9. ViViSnoop: Someone is Snooping Your Typing Without Seeing It! Kun Jin, Si Fang, Chunyi Peng, Zhiyang Teng, Xufei Mao, Lan Zhang and Xiang-Yang Li. IEEE CNS 2017.

8. Context-Sensitive Lexicon Features for Neural Sentiment Analysis. Zhiyang Teng, Duy-Tin Vo and Yue Zhang. EMNLP 2016. [Paper] [Code] [Bib]

7. Expectation-Regulated Neural Model for Event Mention Extraction. Ching-Yun Chang, Zhiyang Teng and Yue Zhang. NAACL 2016. [Paper] [Bib]

6. Measuring the Information Content of Financial News. Ching-Yun Chang, Yue Zhang, Zhiyang Teng, Zahn Bozanic and Bin Ke. COLING 2016. [Paper] [Bib] (Data can be available via email.)

5. Exploiting Mutual Benefits between Syntax and Semantic Roles using Neural Network. Peng Shi, Zhiyang Teng and Yue Zhang. EMNLP 2016. [Paper] [Bib]

4. LibN3L: A Lightweight Package for Neural NLP. Meishan Zhang, Jie Yang, Zhiyang Teng and Yue Zhang. LREC 2016. [Code]

3. Combining Discrete and Neural Features for Sequence Labeling. Jie Yang, Zhiyang Teng, Meishan Zhang and Yue Zhang. CICLING 2016.

2. Unsupervised Joint Monolingual Character Alignment and Word Segmentation. Zhiyang Teng, Hao Xiong and Qun Liu. CCL/NLP-NABD 2014. Best Paper Award. [Paper]

1. Bilingual Lexical Cohesion Trigger Model for Document-Level Machine Translation. Guosheng Ben, Deyi Xiong, Zhiyang Teng, Yajuan Lü and Qun Liu. ACL 2013.

Preprints

3. Multi-scale 2D Temporal Map Diffusion Models for Natural Language Video Localization. Chongzhi Zhang, Mingyuan Zhang, Zhiyang Teng, Jiayi Li, Xizhou Zhu, Lewei Lu, Ziwei Liu, Aixin Sun. [Paper]

2. Evaluating the logical reasoning ability of ChatGPT and GPT-4. Hanmeng Liu, Ruoxi Ning, Zhiyang Teng, Jian Liu, Qiji Zhou, Yue Zhang. [Paper]

1. End-to-End Chinese Parsing Exploiting Lexicons. Yuan Zhang, Zhiyang Teng and Yue Zhang. [Paper]

Academic Activities

Area Chair/Session Chair

2025, Area Chair, ARR, LREC 2026

2024, Area Chair, ACL

2022, Area Chair, Sentiment Analysis, Stylistic Analysis, and Argument Mining Track of EMNLP

2022, Area Chair, Semantics Track of AACL-IJCNLP

2021, Area Chair, Sentiment Analysis, Stylistic Analysis, and Argument Mining Track of EMNLP

2021, Session Chair, 5C: Dialogue and Interactive Systems 3 of EMNLP

Conference Program Committee/Reviewer

2024: AAAI, COLING, NAACL, EACL-WNUT, IJCAI, ICML

2023: ACL, IJCAI, KDD, NLPCC, CCL, IJCNLP-AACL, NeurIPS, EMNLP, ICLR

2022: AAAI, IJCAI, ACL ARR January, ICML, ACL ARR March, COLING, NLPCC

2021: ACL ARR October, IJCAI, AAAI, W-NUT, CCL, PACLIC, NLPCC

2020: ACL, AAAI, IJCAI, EMNLP, COLING, CCL (Best reviewer), NLPCC, W-NUT, PACLIC, AACL-IJCNLP

2019: ACL, AAAI, IJCAI, EMNLP-IJCNLP, CCL, NLPCC, PACLIC

2018: EMNLP, COLING, NLPCC, PACLIC, IALP

2017: NLPCC

2016: NLPCC, CLP, EACL SRW (Secondary Reviewer)

2015: CCL

Journal Reviewer

2023: IEEE Signal Processing Letters, Transactions on Audio, Speech and Language Processing, International Journal of Medical Informatics, Computational Intelligence, Transactions on Multimedia Computing Communications and Applications

2022: Neurocomputing, Transactions on Asian and Low-Resource Language Information Processing, Information Processing and Management, IEEE Transactions on Affective Computing, IEEE Transactions on Audio, Speech and Language Processing, International Journal of Medical Informatics (IJMEDI)

2021: Journal of Artificial Intelligence Research (JAIR), Neurocomputing, IEEE Transactions on Knowledge and Data Engineering (TKDE), MDPI Entropy, Transactions on Asian and Low-Resource Language Information Processing (TALLIP)

2020: Neurocomputing (7 times), Transactions on Asian and Low-Resource Language Information Processing (TALLIP, twice), Engineering Reports (ENG)

2018: TACL (Co-Reviewer)

2017: Computational Linguistics (CL, Co-Reviewer)

2015: Transactions on Asian and Low-Resource Language Information Processing (TALLIP), Acta Scientiarum Naturalium Universitatis Pekinensis (Secondary Reviewer)

Last update：