Machine Learning Engineer at Meituan Inc, Beijing
Email: feizhengcong@gmail.com
know more about me: github scholar
September, 2019 - June, 2022 | Master’s Degree of Computer Application Technology, ICT, UCAS. |
September, 2015 - June, 2019 | Bachelor of Electronic information engineering, NJUST; GPA: 3.75/4 (rank: 1/165). |
AI, LLM, Multimodal
December, 2021 - Present | Vision Intelligence Center, Meituan. |
November, 2020 - November, 2021 | Wechat AI, Tencent Inc. |
July, 2020 - October, 2020 | AIEI, Sinovation Ventures. |
April, 2018 - October, 2018 | AAIS, Peking University. |
Our team (Zekang Li, Jinchao Zhang, Yang Feng and Jie Zhou) hold the DSTC10 Track1: Meme incorporated Open-domain Dialogue.
Our team (Zekang Li, Xiangru Tang, Xiaohao Xu and adviser Ming Zhou) won the first place in the 6-th National Youth artificial intelligence innovation and entrepreneurship Conference, CAAI.
Our team (Zekang Li, Xiangru Tang, Xiaohao Xu, and Hui Zheng) won the first place in the innovation track, Deecamp 2020, Sinovation Ventures. This project is about sci-fic novel generation.
Our team (Zekang Li, Xiangru Tang, and Xiaohao Xu) won the first place in the 2020 artificial intelligence application innovation competition, Huawei Cloud. This project is about AI assisted writing.
Zhengcong Fei, Mingyuan Fan, Changqian Yu, Debang Li, Junshi Huang. Diffusion-RWKV: Scaling RWKV-Like Architectures for Diffusion Models. In Technique Report. [paper] [code]
Zhengcong Fei, Mingyuan Fan, Junshi Huang. Music Consistency Models. In Technique Report. [paper] [demo]
Zhengcong Fei, Mingyuan Fan, Changqian Yu, Junshi Huang. Scalable Diffusion Models with State Space Backbone. In Technique Report. [paper] [code]
Xiaoyue Duan, Shuhao Cui, Guoliang Kang, Baochang Zhang, Zhengcong Fei, Mingyuan Fan, Junshi Huang. Tuning-Free Inversion-Enhanced Control for Consistent Image Editing. In AAAI2024. [paper] [video]
Zhengcong Fei, Mingyuan Fan, Junshi Huang. A-JEPA: Joint-Embedding Predictive Architecture Can Listen. In Technique Report. [paper] [code] [video]
Yuchen Ma, Zhengcong Fei, Junshi Huang. DiT: Efficient Vision Transformers with Dynamic Token Routing. In Technique Report. [paper] [code]
Zhengcong Fei, Mingyuan Fan, Junshi Huang. Gradient-Free Textual Inversion. In ACM MM2023. [paper] [code]
Zhengcong Fei, Zekang Li, Jinchao Zhang, Yang Feng, Jie Zhou. Overview of the Tenth Dialog System Technology Challenge: DSTC10. In IEEE/ACM Transactions on Audio, Speech, and Language Processing. [paper] [code]
Zhengcong Fei, Junshi Huang. Incorporating Unlikely Negative Cues for Distinctive Image Captioning. In IJCAI2023. [paper]
Zhengcong Fei, Mingyuan Fan, Li Zhu, Junshi Huang, Xiaoming Wei, Xiaolin Wei. Masked Auto-Encoders Meet Generative Adversarial Networks and Beyond. In CVPR2023. [paper]
Zhengcong Fei, Mingyuan Fan, Li Zhu, Junshi Huang, Xiaoming Wei, Xiaolin Wei. Uncertainty-Aware Image Captioning. In AAAI2023. [paper] [code]
Zhengcong Fei, Junshi Huang, Xiaoming Wei, Xiaolin Wei. Efficient Modeling of Future Context for Image Captioning. In ACM MM2022. [video] [paper] [code]
Ji-Xiang He*, Zhengcong Fei*, Ling Fu, Cai-Ping Tian, Fu-Chu He, Si-Min He, Hao Chi, Jing Yang. pChem: a modification-centric assessment tool for the performance of chemoproteomic probes. In Nature Chemical Biology. [paper] [code] [web]
Zhengcong Fei, Xu Yan, Shuhui Wang, Qi Tian. DeeCap: Dynamic Early Exiting for Efficient Image Captioning. In CVPR2022. [paper] [code]
Zhexin Zhang, Yeshuang Zhu, Zhengcong Fei, Jinchao Zhang, Jie Zhou. Selecting Stickers in Open-Domain Dialogue through Multitask Learning. In ACL2022 Findings. [paper] [code]
Zhengcong Fei. Attention-Aligned Transformer for Image Captioning. [claim]
Zhengcong Fei, Zekang Li, Jinchao Zhang, Yang Feng, Jie Zhou. Towards Expressive Communication with Internet Memes: A New Multimodal Conversation Dataset and Benchmark. In DSTC10 track1 organizer. [paper] [code] [web]
Xu Yan*, Zhengcong Fei*, Zekang Li, Shuhui Wang, Qingming Huang, Qi Tian. Semi-Autoregressive Image Captioning. In ACM MM2021. [paper] [code] [video]
Zekang Li, Jinchao Zhang, Zhengcong Fei, Yang Feng, Jie Zhou. Conversionsa Are not Flat: Modeling the Dynamic Information Flow between Dialogue Utterances. In ACL2020. [paper] [code]
Zekang Li, Jinchao Zhang, Zhengcong Fei, Yang Feng, Jie Zhou. Addressing Inquiries about History: An Efficient and Practical Framework for Evaluating Open-domain Chatbot Consistency. In ACL2021 Findings. [paper] [code]
Zhengcong Fei. Memory-Augumented Image Captioning. In AAAI2021. [paper] [code] [video]
Zhengcong Fei. Partially Non-Autoregressive Image Captioning. In AAAI2021. [paper] [code] [video]
Zhengcong Fei. Retrieve and Revise: Improving Peptide Identification with Similar Mass Spectra. In AAAI2021. [paper] [video]
Zhengcong Fei. Iterative Back Modification for Faster Image Captioning. In ACM MM2020. [paper] [code] [video]
Zhengcong Fei. Improving Tandem Mass Spectra Analysis with Hierarchical Learning. In IJCAI2020. [paper] [video]
Zhengcong Fei. Actor-Critic Sequence Generation for Relative Difference Captioning. In ICMR2020. [paper] [video]
Zhengcong Fei. Novel Peptide Sequencing with Deep Reinforcement Learning. In ICME2020. [paper]
Zhengcong Fei. Fast Image Caption Generation with Position Alignment. In AAAI2020 Workshop. [paper] [code] [PPT]
Zhengcong Fei. Better Understanding Hierarchical Visual Relationship for Image Caption. In NeurIPS2019 Workshop. [paper] [code]
2020 | China National Scholarship, ICT |
2018 | China National Scholarship, NJUST |
2018 | Outstanding Student Award, NJUST |
2018 | The Mathematical/Interdisciplinary Contest in Modeling, Meritorious Winner |
2018 | China Undergraduate Mathematical Contest in Modeling, First Prize |
2018 | MathorCup Mathematical Contest, First Prize |
2017 | Suzhou Industrial Park Scholarship |
2017 | Certification Cup Mathematical Contest, First Prize |
2017 | National Military Mathematical Modeling League, Second Prize |
2016 | Mathematics competition of Chinese College Students, First Prize |
2015 | Chinese Mathematics Competitions, First Prize |
Familiar with C++,python
Know Shell, MATLAB and LaTeX
CET-6: 551; CET-4: 571
Reviewer: CVPR2022; ICLR2021; NeurIPS2021; ICCV2021; ICML2021; CVPR2021; IJCAI2021; NeurIPS2020;
Last updated on Apr 29, 2024