Xingxing Zhang (张星星) Pronounced as Shingshing Zhang E-mail: Address:   Building 2, No. 5 Dan Ling Street, Haidian District, Beijing , 100080 China

Hi! I am a Principal Researcher at General Artificial Intelligence Group, Microsoft Research Asia (MSRA).
Before joining MSRA, I completed my Ph.D. at Institute for Language, Cognition, and Computation in School of Informatics, University of Edinburgh,
where I was working on Language Modeling and Generation under the supervision of Prof. Mirella Lapata and Prof. Adam Lopez.

I am always looking for highly motivated interns to work with me on Large Language Models. Feel free to drop me an email, if you are interested.

Research Interests

Preprints

• Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models
  Haoran Li*, Qingxiu Dong*, Zhengyang Tang*, Chaojun Wang*, Xingxing Zhang*, Haoyang Huang*,
  Shaohan Huang, Xiaolong Huang, Zeqiang Huang, Dongdong Zhang, Yuxian Gu, Xin Cheng,
  Xun Wang, Si-Qing Chen, Li Dong, Wei Lu, Zhifang Sui, Benyou Wang, Wai Lam, Furu Wei. ArXiv 2024



• LongNet: Scaling Transformers to 1,000,000,000 Tokens
  Jiayu Ding, Shuming Ma, Li Dong, Xingxing Zhang, Shaohan Huang, Wenhui Wang, Nanning Zheng, Furu Wei. ArXiv 2023



• Momentum Calibration for Text Generation
  Xingxing Zhang*, Yiran Liu^♣*, Xun Wang, Pengcheng He, Yang Yu, Si-Qing Chen, Wayne Xiong, Furu Wei. ArXiv 2022



• Latent Prompt Tuning for Text Summarization
  Yubo Zhang^♣, Xingxing Zhang, Xun Wang, Si-qing Chen, Furu Wei. ArXiv 2022

Publications

• xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token
  Xin Cheng, Xun Wang, Xingxing Zhang, Tao Ge, Si-Qing Chen, Furu Wei, Huishuai Zhang, Dongyan Zhao. In NeurIPS 2024.



• MathScale: Scaling Instruction Tuning for Mathematical Reasoning
  Zhengyang Tang, Xingxing Zhang, Benyou Wan, Furu Wei. In ICML 2024.
[MWPBench]


• Tuna: Instruction Tuning using Feedback from Large Language Models
  Haoran Li, Yiran Liu, Xingxing Zhang, Wei Lu, Furu Wei. In EMNLP 2023.
[arXiv]


• Unsupervised Multi-Granularity Summarization
  Ming Zhong, Yang Liu, Suyu Ge, Yuning Mao, Yizhu Jiao, Xingxing Zhang, Yichong Xu, Chenguang Zhu, Michael Zeng, Jiawei Han. In EMNLP 2022.
[arXiv]


• Neural Label Search for Zero-Shot Multi-Lingual Extractive Summarization
  Ruipeng Jia, Xingxing Zhang, Yanan Cao, Shi Wang, Zheng Lin, Furu Wei. In ACL 2022.
[arXiv]


• Attention Temperature Matters in Abstractive Summarization Distillation
  Shengqiang Zhang, Xingxing Zhang, Hangbo Bao, Furu Wei. In ACL 2022.
[arXiv] [code]


• Sequence Level Contrastive Learning for Text Summarization
  Shusheng Xu, Xingxing Zhang, Yi Wu, Furu Wei. In AAAI 2022 (15% Acceptance Rate).
[arXiv] [code]


• Unsupervised Extractive Summarization by Pre-training Hierarchical Transformers
  Shusheng Xu, Xingxing Zhang, Yi Wu, Furu Wei and Ming Zhou. In Findings of EMNLP 2020.
[bib] [arXiv] [code]


• Pre-training for Abstractive Document Summarization by Reinstating Source Text
  Yanyan Zou, Xingxing Zhang, Wei Lu, Furu Wei and Ming Zhou. In EMNLP 2020.
[bib] [arXiv] [code]


• Improving the Efficiency of Grammatical Error Correction with Erroneous Span Detection and Correction
  Mengyun Chen, Tao Ge, Xingxing Zhang, Furu Wei and Ming Zhou. In EMNLP 2020.



• DualVD: An Adaptive Dual Encoding Model for Deep Visual Understanding in Visual Dialogue
  Xiaoze Jiang, Jing Yu, Zengchang Qin, Yingying Zhuang, Xingxing Zhang, Yue Hu, Qi Wu. In AAAI 2020.
[arXiv]


• Document-Based Question Answering Improves Query-Focused Multi-document Summarization
  Weikang Li, Xingxing Zhang, Yunfang Wu, Furu Wei, Ming Zhou. In NLPCC 2019.



• HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization
  Xingxing Zhang, Furu Wei and Ming Zhou. In ACL 2019.
[bib] [arXiv] [slides] [project page]


• Automatic Grammatical Error Correction for Sequence-to-sequence Text Generation: An Empirical Study
  Tao Ge, Xingxing Zhang, Furu Wei and Ming Zhou. In ACL 2019.
[bib]


• Neural Latent Extractive Document Summarization
  Xingxing Zhang, Mirella Lapata, Furu Wei and Ming Zhou. In EMNLP 2018 (short paper).
[bib] [arXiv] [resource]


• Natural Language Generation as Neural Sequence Learning and Beyond
  Xingxing Zhang. Ph.D Thesis, 2017.
[bib] [code & data] [slides]


• UParse: the Edinburgh system for the CoNLL 2017 UD shared task
  Clara Vania, Xingxing Zhang, Adam Lopez. In CoNLL 2017 Shared Task.
[bib][arXiv]


• Sentence Simplification with Deep Reinforcement Learning
  Xingxing Zhang and Mirella Lapata. In EMNLP 2017.
[bib] [arXiv] [code & data] [slides]


• Dependency Parsing as Head Selection
  Xingxing Zhang, Jianpeng Cheng and Mirella Lapata. In EACL 2017.
[bib] [arXiv] [resource] [code] [slides]


• Top-down Tree Long Short-Term Memory Networks
  Xingxing Zhang, Liang Lu and Mirella Lapata. In NAACL 2016.
[bib] [arXiv] [code] [slides]


• On Training the Recurrent Neural Network Encoder-Decoder for Large Vocabulary End-to-End Speech Recognition
  Liang Lu, Xingxing Zhang and Steve Renals. In ICASSP 2016.


• A Study of the Recurrent Neural Network Encoder-Decoder for Large Vocabulary Speech Recognition
  Liang Lu, Xingxing Zhang, Kyunghyun Cho and Steve Renals. In INTERSPEECH 2015.


• Chinese Poetry Generation with Recurrent Neural Networks
  Xingxing Zhang and Mirella Lapata. In EMNLP 2014.
[bib] [data] [code]

• Towards Accurate Distant Supervision for Relational Facts Extraction
  Xingxing Zhang, Jianwen Zhang, Junyu Zeng, Jun Yan, Zheng Chen and Zhifang Sui. In ACL 2013 (short paper).


• Learning to Extract Attribute Values from a Search Engine with Few Examples
  Xingxing Zhang, Tao Ge and Zhifang Sui. In Chinese Computational Linguistics (CCL) 2013.


• Semantic Class Learning with Deep Coordinate Structures in Web Pages
  Xingxing Zhang and Zhifang Sui. Journal of Computational Information Systems (JCIS) 8:3 (2012) 1245-1254.

Software

• Dress Simplification Model: DRESS: Deep REinforcement Sentence Simplification Model (in Lua with Torch)
• DeNSe Parser: A Neural Dependency Parser (in Lua with Torch)
• TD-TreeLSTM: Top-down Tree Long Short-Term Memory Networks (in Lua with Torch)
• RNNPG: A (Hierarchical) Recurrent Neural Network based Chinese Poetry Generator (in C++)

Professional Activities

• Area Chair for ACL 2021
• Area Chair for INLG 2021
• Area Chair (Action Editor) for ACL/ARR 2022
• Area Chair (Action Editor) for NAACL/ARR 2022
• Area Chair for ACL 2023
• Area Chair for EMNLP 2024