I am Xinyu Yang (杨新宇), an undergraduate from ACM Honors Class, Zhiyuan College, Shanghai Jiao Tong University, and an incoming Ph.D. student at Carnegie Mellon University, advised by Prof. Beidi Chen. Currently, I’m fortunate to work with Prof. Song Han at MIT HAN Lab as a research intern, and Prof. Chelsea Finn at Stanford IRIS Lab remotely. During my junior year, I also had a wonderful time as an undergraduate researcher advised by Prof. Junchi Yan at SJTU ThinkLab.
My primary research interests lie in the intersection of machine learning and system (MLSys). I am currently working on building efficient transformers via algorithm/system co-design, with its applications in 3D vision.
 Xinyu Yang*, Huaxiu Yao*, Allan Zhou, Chelsea Finn, Multi-Domain Long-Tailed Learning by Augmenting Disentangled Representations, arXiv 2210.14358 (the short version is presented in NeurIPS 2022 Workshop on Distribution Shifts). [arXiv]
 Huaxiu Yao*, Xinyu Yang*, Xinyi Pan, Shengchao Liu, Pang Wei Koh, Chelsea Finn, Leveraging Domain Relations for Domain Generalization, arXiv 2302.02609 (the short version is presented in NeurIPS 2022 Workshop on Distribution Shifts). [arXiv]
 Zhijian Liu*, Xinyu Yang*, Haotian Tang, Shang Yang, Song Han, Flattened Window Attention for Efficient Point Cloud Transformer, in The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2023 (CVPR 2023), Vancouver, Canada, Jun. 2023. [arXiv]
 Zhijian Liu*, Haotian Tang*, Alexander Amini, Xinyu Yang, Huizi Mao, Daniela Rus, Song Han, BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird’s-Eye View Representation, in 2023 IEEE International Conference on Robotics and Automation (ICRA 2023), London, UK, Jun. 2023. [Project Page] [Code] [arXiv]
 Danning Lao*, Xinyu Yang*, Qitian Wu, Junchi Yan, Variational Inference for Training Graph Neural Networks in Low-Data Regime through Joint Structure-Label Estimation, in Proceedings of the 28th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2022), Washington DC, Aug. 2022 (Research Track). [PDF] [Code] [Slides] [Poster]