Yunyang Xiong

I am a senior research scientist at Facebook Reality Lab. Prior to that, I completed my Ph.D. in the department of Computer Sciences at University of Wisconsin-Madison under Vikas Singh. Before joining Facebook, I was a research intern at Google Mobile Vision working on neural architecture search (MobileDets). I also did research internship at Facebook AI and Amazon Lab 126.

My research interests include natural language modeling, efficient Transformers, and neural architecture search. I am paritcularly interested in efficient AI.

---

Publications

• Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-Experts
  Ganesh Jawahar, Haichuan Yang, Yunyang Xiong, Zechun Liu, Dilin Wang, Fei Sun, Meng Li, Aasish Pappu, Barlas Oguz, Muhammad Abdul-Mageed, Laks VS Lakshmanan, Raghuraman Krishnamoorthi, Vikas Chandra
  [arxiv]
• Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference
  Haoran You, Yunyang Xiong, Xiaoliang Dai, Bichen Wu, Peizhao Zhang, Haoqi Fan, Peter Vajda, Yingyan Celine Lin
  CVPR 2023. [pdf]
• Self-positioning Point-based Transformer for Point Cloud Understanding
  Jinyoung Park, Sanghyeok Lee, Sihyeon Kim, Yunyang Xiong, Hyunwoo J Kim
  CVPR 2023. [pdf]
• Fast Point Cloud Generation with Straight Flows
  Lemeng Wu, Dilin Wang, Chengyue Gong, Xingchao Liu, Yunyang Xiong, Rakesh Ranjan, Raghuraman Krishnamoorthi, Vikas Chandra, Qiang Liu
  CVPR 2023. [pdf]
• Sagemix: Saliency-guided mixup for point clouds
  Sanghyeok Lee, Minkyu Jeon, Injae Kim, Yunyang Xiong, Hyunwoo J Kim
  NeurIPS 2022. [pdf]
• You only sample (almost) once: Linear cost self-attention via bernoulli sampling
  Zeng, Zhanpeng, Yunyang Xiong, Sathya Ravi, Shailesh Acharya, Glenn M. Fung, Vikas Singh
  ICML 2021. [pdf]
• MobileDets: Searching for Object Detection Architectures for Mobile Accelerators
  Yunyang Xiong, Hanxiao Liu, Suyog Gupta, Berkin Akin, Gabriel Bender, Yongzhe Wang, Pieter-Jan Kindermans, Mingxing Tan, Vikas Singh, Bo Chen
  CVPR 2021. [arxiv]
• Nyströmformer: A Nyströmformer-based Algorithm for Approximating Self-Attention
  Yunyang Xiong, Zhanpeng Zeng, Rudrasis Chakraborty, Mingxing Tan, Glenn Fung, Yin Li, Vikas Singh
  AAAI 2021. [pdf]
• MobileDets: Searching for Object Detection Architectures for Mobile Accelerators
  Yunyang Xiong, Hanxiao Liu, Suyog Gupta, Berkin Akin, Gabriel Bender, Yongzhe Wang, Pieter-Jan Kindermans, Mingxing Tan, Vikas Singh, Bo Chen
  NeurIPS 2020, Workshop on MetaLearning. [arxiv]
• Performing Group Difference Testing on Graph Structured Data from GANs: Analysis and Applications in Neuroimaging?
  Tuan Quang Dinh, Yunyang Xiong, Zhichun Huang, Tien Vo, Akshay Mishra, Won Hwa Kim, Sathya Ravi, Vikas Singh
  TPAMI 2020. [pdf]
• Resource Constrained Neural Network Architecture Search: Will a Submodularity Assumption Help?
  Yunyang Xiong, Ronak Mehta, Vikas Singh
  ICCV 2019. [arxiv]
• Scaling Recurrent Models via Orthogonal Approximations in Tensor Trains
  Ronak Mehta, Rudrasis, Chakraborty, Yunyang Xiong, Vikas Singh
  ICCV 2019. [pdf]
• Mixed Effects Neural Networks (MeNets) with Applications to Gaze Estimation
  Yunyang Xiong, Hyunwoo J. Kim, Vikas Singh
  CVPR 2019. [pdf]
• ANTNets: Mobile Convolutional Neural Networks for Resource Efficient Image Classification
  Yunyang Xiong, Hyunwoo J. Kim, Varsha Hedau
  CVPR 2019, ECV Workshop (Oral). [arxiv]
• On Training Deep 3D CNN Models with Dependent Samples in Neuroimaging
  Yunyang Xiong, Hyunwoo J. Kim, Bhargav Tangirala, Ronak Mehta, Sterling C. Johnson, Vikas Singh
  IPMI 2019 (Oral). [pdf]
• Building Bayesian Neural Networks with Blocks: On Structure, Interpretability and Uncertainty
  Hao Henry Zhou, Yunyang Xiong, Vikas Singh
  [arxiv]
• Filter Flow made Practical: Massively Parallel and Lock-Free
  Sathya N. Ravi, Yunyang Xiong, Lopamudra Mukherjee, Vikas Singh
  CVPR 2017. [pdf]