Yinshuang Xu 许吟霜

I'm a second-year Ph.D. student at the Department of Computer and Information Science, University of Pennsylvania, and my advisor is Prof. Kostas Daniilidis.

Before that, I got my bachelor's degree in Engineering Mechanics at Shanghai Jiao Tong University and my master's degree in Robotics at University of Pennsylvania.

My research interest lies in equivariance, geometric deep learning and their applications in computer vision and machine learning.

Email / Google Scholar / Github

Research

	\(SE(3)\) Equivariant Convolution and Transformer in Ray Space Yinshuang Xu, Jiahui Lei, Kostas Daniilidis NeurIPS (Spotlight), 2023 paper / code / bibtex
	Unified Fourier-based Kernel and Nonlinearity Design for Equivariant Networks on Homogeneous Spaces Yinshuang Xu, Jiahui Lei, Edgar Dobriban, Kostas Daniilidis ICML (Spotlight), 2022 arXiv / bibtex
	Equivariant Multi-View Networks Carlos Esteves, Yinshuang Xu, Christine Allen-Blanchette, Kostas Daniilidis ICCV (Oral), 2019 arXiv / code / poster / bibtex
	Nested Scale-Editing for Conditional Image Synthesis Lingzhi Zhang, Jiancong Wang, Yinshuang Xu, Jie Min, Tarmily Wen, James C. Gee, Jianbo Shi CVPR, 2020 arXiv / bibtex

Teaching

CIS580: Machine Perception. Teaching assistant, Spring2020, Spring2021

ESE546: Principles of Deep Learning. Teaching assistant, Fall2021

Service

ICML reviewer (International Conference on Machine Learning)

ECCV reviewer (European Conference on Computer Vison)

NeurIPS reviewer (Conference on Neural Information Processing Systems)

CVPR reviewer (Computer Vision and Pattern Recognition)

ICLR reviewer (International Conference on Learning Representations)

Co-organizer: CVPR2024 Workshop on Equivariant Vision: From Theory to Practice

Developed from this webpage