| Sun Siqi Principal Investigator, Doctoral Supervisor Research Institute of Intelligent Complex Systems, Fudan University E-mail: siqisun AT fudan.edu.cn |
Biography：
Sun Siqi received his bachelor’s degree in 2011 from School of Mathematical Sciences, Fudan University and his doctor’s degree in 2017 from TTIC Institute (guided by Professor Hui Jinbo). He continued his research at Microsoft Research from 2018-2022 and has been a Junior Principal Investigator at the Research Institute of Intelligent Complex Systems of Fudan University since 2022. He is dedicated to the application of deep learning in interdisciplinary disciplines such as life sciences and natural language processing, and focuses on improving the accuracy and speed of models and solving specific problems in the practical implementation of models. He has published several papers in top international publications and conferences, including PLOS Computational Biology, Nucleic Acids Research, ACL, EMNLP, NAACL, NeurIPS and ICML. These papers have been cited more than 4000 times in total (according to Google Scholar). The algorithm he researched and developed as a co-author won PLOS Computational Biology's 2018 Breakthrough/Innovation award, and the concerning achievements also won first place in The Critical Assessment of protein Structure Prediction 12 (CASP 12) contact prediction task. In addition, his work has been featured in internationally influential media such as The Economics, Science, The New York Times, Adweek, The Register, Synced and others. He was invited to participate in the program committee of the top international academic conferences ECML-PKDD and EMNLP.
Research Interests：
Deep Learning, Natural Language Processing, Computational Biology
Selected Publications：
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, AAAI 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, NAACL 2021
3. Siqi Sun, Zhe Gan, Yu Cheng, Yuwei Fang, Shuohang Wang, Jingjing Liu, Contrastive Distillation on Intermediate Representations for Language Model Compression, EMNLP 2021
4. Yuwei Fang, Shuohang Wang, Zhe Gan, Siqi Sun, Jingjing Liu, Filter: An enhanced fusion method for cross-lingual language understanding, AAAI 2021
5. Yuwei Fang, Siqi Sun, Zhe Gan, Rohit Pillai, Shuohang Wang, Jingjing Liu, Hierarchical graph network for multi-hop question answering, 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, ACL 2020
7. Chen Zhu, Yu Cheng, Zhe Gan, Siqi Sun, Tom Goldstein, Jingjing Liu, Freelb: Enhanced adversarial training for natural language understanding, ICLR 2019
8. Siqi Sun, Yu Cheng, Zhe Gan, Jingjing Liu, Patient knowledge distillation for bert model compression, EMNLP 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
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
11. Qingming Tang*, Siqi Sun*, Jinbo Xu, Learning scale-free networks by dynamic node specific degree prior, ICML 2015
12. Siqi Sun, Mladen Kolar, Jinbo Xu, Learning structured densities via infinite dimensional exponential families, NeurIPS 2015
