个人简介

本科毕业于复旦大学数学系（2011），博士毕业于TTIC研究院（2017），师从许锦波教授。2018-2022年继续在微软研究院开展研究，2022至今复旦大学智能复杂体系基础理论与关键技术实验室担任青年研究员。致力于深度学习在生命科学和自然语言处理等交叉学科中的应用研究,并侧重于提高模型的精度和速度，解决模型在实践落地中的具体问题。在PLOS Computational Biology、Nucleic Acids Research、ACL、EMNLP、NAACL、NeurIPS、ICML等国际顶级刊物和会议上发表多篇论文,共计被引用超过2000次（据谷歌学术统计）。其中以共同一作身份研究并开发的算法获得了PLOS Computational Biology 2018年度的“突破/创新”奖项，相关成果还获得了The Critical Assessment of protein Structure Prediction 12 (CASP 12）接触图比赛预测的全球第一名。此外，有多个工作被有国际影响力的媒体报道，例如The Economics, Science, The New York Times, Adweek, The Register, Synced等。多次受邀参与国际顶级学术会议ECML-PKDD和EMNLP的程序委员会。

研究兴趣

深度学习，自然语言处理，计算生物学

代表成果

1. Yizhe Zhang, Siqi Sun, Xiang Gao, Yuwei Fang, Chris Brockett, Michel Galley, Jianfeng Gao, Bill Dolan, RetGen: A Joint framework for Retrieval and Grounded Text Generation Modeling, Proceedings of the AAAI Conference on Artificial Intelligence, [2022].

2. Siqi Sun*, Yen-Chun Chen*, Linjie Li, Shuohang Wang, Yuwei Fang, Jingjing Liu, Lightningdot: Pre-training visual-semantic embeddings for real-time image-text retrieval, Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, [2021].

3. Siqi Sun, Zhe Gan, Yu Cheng, Yuwei Fang, Shuohang Wang, Jingjing Liu, Contrastive Distillation on Intermediate Representations for Language Model Compression, Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), [2020].

4. Yuwei Fang, Shuohang Wang, Zhe Gan, Siqi Sun, Jingjing Liu, Filter: An enhanced fusion method for cross-lingual language understanding, Proceedings of the AAAI Conference on Artificial Intelligence, [2021].

5. Yuwei Fang, Siqi Sun, Zhe Gan, Rohit Pillai, Shuohang Wang, Jingjing Liu, Hierarchical graph network for multi-hop question answering, Proceedings of the 2020 conference on empirical methods in natural language processing (EMNLP), [2020].

6. Yizhe Zhang, Siqi Sun, Michel Galley, Yen-Chun Chen, Chris Brockett, Xiang Gao, Jianfeng Gao, Jingjing Liu, Bill Dolan, Dialogpt: Large-scale generative pre-training for conversational response generation, Proceedings of the 58th annual meeting of the association for computational linguistics: system demonstrations, [2020].

7. Chen Zhu, Yu Cheng, Zhe Gan, Siqi Sun, Tom Goldstein, Jingjing Liu, Freelb: Enhanced adversarial training for natural language understanding, International Conference on Learning Representations, [2019].

8. Siqi Sun, Yu Cheng, Zhe Gan, Jingjing Liu, Patient knowledge distillation for bert model compression, Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP), [2019].

9. Sheng Wang, Siqi Sun, Jinbo Xu, Analysis of deep learning methods for blind protein contact prediction in CASP12, Proteins: Structure, Function, and Bioinformatics, [2018], 86: 67-77.

10. Sheng Wang*, Siqi Sun*, Zhen Li, Renyu Zhang, Jinbo Xu, Accurate de novo prediction of protein contact map by ultra-deep learning model, PLoS computational biology, [2017], 13(1): e1005324.

11. Qingming Tang*, Siqi Sun*, Jinbo Xu, Learning scale-free networks by dynamic node specific degree prior, International Conference on Machine Learning, [2015].

12. Siqi Sun, Mladen Kolar, Jinbo Xu, Learning structured densities via infinite dimensional exponential families, Advances in neural information processing systems 28, [2015].

13. Siqi Sun*, Xinran Dong*, Yao Fu, Weidong Tian, An iterative network partition algorithm for accurate identification of dense network modules, Nucleic Acids Research, [2012], 40(3): e18-e18.