Hi, my name is Wei Liu (刘威). Currently, I am a final-year graduate student at ShanghaiTech University, advised by Prof. Kewei Tu. I am also a research assistant in HKUST NLP, working closely with Prof. Junxian He.

I am focusing on natural language processing (NLP) and machine learning (ML).

To be more specific, my research interests lie in:

  • Efficient Sequence Modeling: Exploring more efficient model architecture, particularly for long-range sequence.
  • Structured Predictions: Parsing and application of parsing algorithm in downstream tasks.
  • Deep Generative Models: Deep Latent-variable models.
  • Large Language Models (LLMs): Explorations of their Emergent Capabilities and Applications in Complex Scenarios.

📝 Publications (* denotes equal contribution)

MathAttack: Attacking Large Language Models Towards Math Solving Ability


Zihao Zhou, Qiufeng Wang, Mingyu Jin, Jie Yao, Jianan Ye, Wei Liu, Wei Wang, Xiaowei Huang, Kaizhu Huang

SeqGPT: An Out-of-the-box Large Language Model for Open Domain Sequence Understanding

Preprint code

Tianyu Yu*, Chengyue Jiang*, Chao Lou*, Shen Huang*, Xiaobin Wang, Wei Liu, Jiong Cai, Yangning Li, Yinghui Li, Kewei Tu, Hai-Tao Zheng, Ningyu Zhang, Pengjun Xie, Fei Huang, Yong Jiang

Simple Hardware-Efficient PCFGs with Independent Left and Right Productions

Wei Liu, Songlin Yang, Yoon Kim, Kewei Tu

In Findings of EMNLP, 2023.

Joint Entity and Relation Extraction with Span Pruning and Hypergraph Neural Networks

Zhaohui Yan, Songlin Yang, Wei Liu, Kewei Tu

In Proceedings of EMNLP, 2023.

Structured Mean-Field Variational Inference for Higher-Order Span-Based Semantic Role Labeling

In Findings of ACL, 2023. code

Wei Liu, Songlin Yang, Kewei Tu

Dynamic Programming in Rank Space: Scaling Structured Inference with Low-Rank HMMs and PCFGs

Songlin Yang*, Wei Liu*, Kewei Tu

In Proceedings of NAACL, 2022(Top-3 Score in ARR Jan 2022). code

Knowledge-Based Chat Detection With False Mention Discrimination

Wei Liu, Peijie Huang, Dongzhu Liang, Zihao Zhou

In Proceedings of ICASSP, 2021.

A Knowledge-gated Mechanism for Utterance Domain Classification

Zefeng Du, Peijie Huang, Yuhong He, Wei Liu & Jiankai Zhu

In Proceedings of NLPCC, 2019.

💻 Internships

  • 2022.07 - Present, Alibaba DAMO academy
    • Doing some research about pre-trained language models and few-shot learning
    • One of the developers of AdaSeq
    • MAOE (Paper underwriting): A pre-trained language model that supports (ultra-)fine-grained named entity recognition. Welcome to try out our model: Try it now

📖 Educations

  • 2021.09 - Present, ShanghaiTech University, M.S. in computer science
  • 2017.09 - 2021.06, South China Agricultural University, B.E. in computer science