Yibing Song

宋奕兵

Artificial Intelligence Innovation and Incubation (AIĀ³) Institute
Fudan University

Email: yibingsong.cv at gmail dot com

Biography


Yibing Song is a faculty member in Fudan University. Previously, he worked at Tencent AI Lab where he led visual understanding area. Yibing Song received PhD/Mphil degrees from City University of Hong Kong during which he visited Adobe Research and UC Merced, and received a bachelor degree from University of Science and Technology of China. Currently, Yibing Song researches around intelligent foundation models, from both model-centric and data-centric perspectives, with applications ranging from multi-modality understanding to generations in computer vision. He has been elected among Top 2% Scientists worldwide 2023 by Stanford University.


Service Highlights


Area Chairs / Meta Reviewers: CVPR (2024,2023), ICCV 2023, NeurIPS (2023,2022), ICML (2024,2023), ICLR (2024,2023,2022).

Outstanding / Top Reviewers: CVPR (2020,2019,2018), ECCV 2022, NeurIPS 2019.


3 Representative Publications   [More] [Citations]


DiffusionDet: Diffusion Model for Object Detection
Shoufa Chen, Peize Sun, Yibing Song, and Ping Luo,
IEEE/CVF International Conference on Computer Vision (ICCV) 2023 (Best Paper Nominee)
Paper / Project
VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
Zhan Tong, Yibing Song, Jue Wang, and Limin Wang,
Advances in Neural Information Processing Systems (NeurIPS) 2022 (Spotlight)
Paper / Project / Hugging Face Repo
Ranked 8th in most influential NIPS 2022 papers / Ranked 39th in most cited 2022 AI papers
InstructDET: Diversifying Referring Object Detection with Generalized Instructions
Ronghao Dang, Jiangyan Feng, Haodong Zhang, Chongjian Ge, Lin Song, Lijun Gong, Chengju Liu, Qijun Chen, Feng Zhu, Rui Zhao, and Yibing Song,
Arxiv Preprint 2023
Paper / Project