Yinshuang Xu 许吟霜

I'm a fifth 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, robotics and machine learning.

Email / Google Scholar / Github

Research

	EqNIO: Subequivariant Neural Inertial Odometry Royina Karegoudra Jayanth, Yinshuang Xu, Ziyun Wang,Evangelos Chatzipantazis, Daniel Gehrig, Kostas Daniilidis ICLR, 2025 paper / bibtex
	\(SE(3)\) Equivariant Ray Embeddings for Implicit Multi-View Depth Estimation Yinshuang Xu, Dian Chen, Katherine Liu, Sergey Zakharov, Rares Andrei Ambrus, Kostas Daniilidis, Vitor Campagnolo Guizilini NeurIPS, 2024 paper / bibtex
	\(SE(3)\) 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