Zhenqiao Song 「宋珍巧」

I am a second-year Ph.D. student in the Language Technology Institute (LTI) at Carnegie Mellon University, advised by Prof. Lei Li. Before that, I had been a full-time research scientist at ByteDance AI-Lab MLNLC group for two years, advised by Prof. Hao Zhou. I received my master's degree from Fudan University (FDU). During this period, I worked as a student researcher advised by Prof. Xiaoqing Zheng in Fudan University Natural Language Processing Group.

Email: zhenqias[at]andrew.cmu.edu

Github   /   Google Scholar   /   CV     

profile photo
Research Topics

My research interests lie in developing machine learning methods in scientific domains such as biology and chemistry. Currently, I mainly focus on developing generative algorithms for protein design. I'm also interested in multilingual learning in NLP, including but not limited to multilingual machine translation and multilingual text generation.

News

  • May. 2024: I will be an intern of NEC Lab, working with Martin Renqiang Min.

  • Oct. 2023: We organize the first GenBio Workshop on New Frontiers of Generative AI and Biology (GenBio) at NeurIPS 2023 in New Orleans in Dec. 2023! Check more details here (1st GenBio).

  • Jun. 2023- Sep.2023: Internship at Broad Institue of Havard and MIT, woking with Wengong Jin.

Selected Publication (Refer to my Google Scholar to check the full publication. # denotes student finished the work under my supervision.)

Conference Papers

Generative Enzyme Design Guided by Functionally Important Sites and Small-Molecule Substrates [code]
Zhenqiao Song,  Yunlong Zhao,  Wenxian Shi,  Wengong Jin,  Yang Yang,  Lei Li 
Proceedings of the 2024 International Conference on Machine Learning (ICML), 2024  

SurfPro: Functional Protein Design Based on Continuous Surface [code (coming soon)]
Zhenqiao Song,  Tinglin Huang,  Lei Li,  Wengong Jin 
Proceedings of the 2024 International Conference on Machine Learning (ICML), 2024  

Hire a Linguist!: Learning Endangered Languages with In-Context Linguistic Descriptions
Kexun Zhang,  Yee Man Choi,  Zhenqiao Song,  Taiqi He,  William Yang Wang,  Lei Li 
Proceedings of the 57th Annual Meeting of Findings of the Association for Computational Linguistics (ACL Findings), 2024  

Functional Geometry Guided Protein Sequence and Backbone Structure Co-Design [code]
Zhenqiao Song,  Yunlong Zhao,  Wenxian Shi,  Yang Yang,  Lei Li 
arXiv:2310.04343 

Joint Design of Protein Sequence and Structure based on Motifs
Zhenqiao Song,  Yunlong Zhao,  Yufei Song,  Wenxian Shi,  Yang Yang,  Lei Li 
arXiv:2310.02546 

FAFormer: Frame Averaging Transformer for Predicting Nucleic Acid-Protein Interactions
Tinglin Huang,  Zhenqiao Song,  Rex Ying,  Wengong Jin 
NeurIPS 2023 Machine Learning for Structural Biology Workshop (MLSB), 2023  

Importance Weighted Expectation-Maximization for Protein Sequence Design [code]
Zhenqiao Song,  Lei Li 
Proceedings of the 2023 International Conference on Machine Learning (ICML), 2023  

INSTRUCTSCORE: Explainable Text Generation Evaluation with Fine-grained Feedback
Wenda Xu,  Danqing Wang,  Liangming Pan,  Zhenqiao Song,  Markus Freitag,  William Yang Wang,  Lei Li 
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023  

MTG: A Benchmarking Suite for Multilingual Text Generation
Yiran Chen#Zhenqiao Song*,  Xuanze Wu,  Danqing Wang,  Jingjing Xu,  Jiaze Chen,  Hao Zhou,  Lei Li 
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL Findings), 2022  

switch-GLAT: Multilingual Parallel Machine Translation Via Code-Switch Decoder
Zhenqiao Song,  Hao Zhou,  Lihua Qian,  Jingjing Xu,  Mingxuan Wang,  Lei Li 
Proceedings of the International Conference on Learning Representations (ICLR), 2021  

Triangular Bidword Generation for Sponsored Search Auction
Zhenqiao Song,  Jiaze Chen,  Hao Zhou,  Lei Li 
Proceedings of the 14th ACM International Conference on Web Search and Data Mining (WSDM), 2021  

Improving Coreference Resolution by Leveraging Entity-Centric Features with Graph Neural Networks and Second-order Inference
Lu Liu,  Zhenqiao Song,  Xiaoqing Zheng,  Xuanjing Huang 
arXiv preprint arXiv:2009.04639, 2020  

Generating responses with a specific emotion in dialog
Zhenqiao Song,  Xiaoqing Zheng,  Lu Liu,  Mu Xu,  Xuanjing Huang 
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL), 2019  

Journal Papers

Jointly Learning Bilingual Word Embeddings and Alignments
Zhenqiao Song,  Xiaoqing Zheng,  Xuanjing Huang 
Journal of Machine Translation, 2021  

Exploring Implicit Semantic Constraints for Bilingual Word Embeddings
Jinsong Su,  Zhenqiao Song,  Yaojie Lu,  Mu Xu,  Changxing Wu,  Yidong Chen, 
Journal of Neural Processing Letters, 2018  

Invited Talk

  • Oct. 2023: Invited talk at 将门!

  • May 2023: Invited talk about my work "Importance Weighted Expectation-Maximization for Protein Sequence Design" at BytaDance Research!

Professional Services

PC Members:

  • Nature Communication
  • ACL: 2023, 2024
  • ICML: 2023, 2024
  • NeurIPS: 2023, 2024
  • ICLR: 2023
  • EMNLP: 2020, 2022, 2023
  • NLPCC: 2022, 2023
  • IJCAI: 2023, 2024
  • TMLR, ARR


  • Program Chair/Organizer:

  • The 1st GenBio workshop at NeurIPS 2023.

  • SoCal NLP Symposium 2022.
  • Awards

    National Scholarship of China. 2020.

    Shanghai Outstanding Graduate Student. 2020.



    6,154 Total Pageviews



    Updated at Sep. 2022
    Thanks Jon Barron for this amazing work