Recently, Tao Xu received her PhD degree in Computer Science from Lehigh University. She is supervised by Prof. Xiaolei Huang. She also works closely with Prof. Shaoting Zhang, Prof. Hongsheng Li , Prof. Xiaogang Wang,  Prof. Dimitris N. Metaxas and Prof. Xiaodong He.  Her research interests are deep learning, machine learning, computer vision and medical image analysis. Her current research interests include deep learning, computer vision, and generative modeling, such as Generative Adversarial Networks (GANs) and Diffusion models.

Education

• 2013 ~ 2018,         PhD in Computer Science, Lehigh University, PA, U.S.

• 2010 ~ 2013,         M.S. in Computer Science and Technology , University of  Chinese Academy of Science , China

• 2006 ~ 2010,        B.E. in Agricultural Mechanization and Automatization , China Agricultural University, China

Working Experience

• 08/2023 - Present,    Staff Applied Research Scientist at Cruise, Sunnyvale, CA, USA

• 11/2018 ~ 07/2023,     Staff Research Scientist at Meta (Facebook), Menlo Park, CA, USA

• 01/2018 ~ 05/2018,    Research Intern at Facebook, Menlo Park, CA, USA 

• 05/2017 ~ 08/2017,    Research Intern at Microsoft, Redmond, WA, USA

• 05/2016 ~ 08/2016,   Data Science Intern at Awake Networks, Mountain View, CA, USA

• 04/2010 ~ 07/2010,   Software Engineering Intern at Sony China Research Laboratory, Beijing, China

Selected Publications

(* indicates equal contributions)

[arXiv'23] 3D-CLFusion: Fast Text-to-3D Rendering with Contrastive Latent Diffusion. [pdf]

Yu-Jhe Li, Tao Xu, Ji Hou, Bichen Wu, Xiaoliang Dai, Albert Pumarola, Peizhao Zhang, Peter Vajda, Kris Kitani

[arXiv'22] 3D-Aware Encoding for Style-based Neural Radiance Fields. [pdf]

Yu-Jhe Li, Tao Xu, Bichen Wu, Ningyuan Zheng, Xiaoliang Dai, Albert Pumarola, Peizhao Zhang, Peter Vajda, Kris Kitani. arXiv, 2022.

[arXiv'22] Efficient conditioned face animation using frontally-viewed embedding. [pdf]

Maxime Oquab, Daniel Haziza, Ludovic Schwartz, Tao Xu, Katayoun Zand, Rui Wang, Peirong Liu, Camille Couprie. arXiv, 2022

[CVM'22] Deep image synthesis from intuitive user input: A review and perspectives. [pdf]

Yuan Xue, Yuan-Chen Guo, Han Zhang, Tao Xu, Song-Hai Zhang, Xiaolei Huang. Computational Visual Media, 2022.

[CVPRW'21] Low bandwidth video-chat compression using deep generative models. [pdf]

Maxime Oquab, Pierre Stock, Daniel Haziza, Tao Xu, Peizhao Zhang, Onur Celebi, Yana Hasson, Patrick Labatut, Bobo Bose-Kolanu, Thibault Peyronel, Camille Couprie. CVPRW, 2021.

[CVPR'20] Fbnetv2: Differentiable neural architecture search for spatial and channel dimensions. [pdf][code]

Alvin Wan, Xiaoliang Dai, Peizhao Zhang, Zijian He, Yuandong Tian, Saining Xie, Bichen Wu, Matthew Yu, Tao Xu, Kan Chen, Peter Vajda, Joseph E Gonzalez. CVPR, 2020.

[ISBI'20] Semi-supervised cervical dysplasia classification with learnable graph convolutional network. [pdf]

Yanglan Ou, Yuan Xue, Ye Yuan, Tao Xu, Vincent Pisztora, Jia Li, Xiaolei Huang. ISBI, 2020.

[TPAMI'19] StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks. [pdf] [code]

Han Zhang*, Tao Xu*, Hongsheng Li, Shaoting Zhang, Xiaogang Wang, Xiaolei Huang, and Dimitris Metaxas. TPAMI, 2019. 

[MICCAI'18] Multimodal Recurrent Model with Attention for Automated Radiology Report Generation.

Yuan Xue, Tao Xu, L. Rodney Long, Zhiyun Xue, Sameer Antani, George R. Thoma, and Xiaolei Huang. MICCAI, 2018 (Early acceptance rate, ~10%). 

[CVPR'18] AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks. [pdf][code][project][blog]

Tao Xu, Pengchuan Zhang, Qiuyuan Huang, Han Zhang, Zhe Gan, Xiaolei Huang, and Xiaodong He. CVPR, 2018. 

[Neuroinformatics'18] SegAN: Adversarial Network with Multi-scale L1 Loss for Medical Image Segmentation. [pdf][code]

Yuan Xue*, Tao Xu*, Han Zhang, L. Rodney Long and Xiaolei Huang. Neuroinformatics, 2018.

[ISBI'18] Adversarial Learning with Multi-scale Loss for Skin Lesion Segmentation. [pdf][code]

Yuan Xue, Tao Xu and Xiaolei Huang. ISBI, 2018.

[ICCV'17] StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks. [arxiv] [iccv] [code]

Han Zhang, Tao Xu, Hongsheng Li, Shaoting Zhang, Xiaogang Wang, Xiaolei Huang, and Dimitris Metaxas. ICCV, 2017. (Oral presentation 45/2143=~2.10%)

[CVPR'16] SPDA-CNN: Unifying Semantic Part Detection and Abstraction for Fine-grained Recognition. [pdf]

Han Zhang*, Tao Xu*, Mohamed Elhoseiny, Xiaolei Huang, Shaoting Zhang, Ahmed Elgammal, and Dimitris Metaxas. CVPR, 2016.

[MICCAI'16] Multimodal Deep Learning for Cervical Dysplasia Diagnosis. [pdf]

Tao Xu*, Han Zhang*, Xiaolei Huang, Shaoting Zhang, and Dimitris Metaxas. MICCAI, 2016 (Early acceptance rate, ~10%). 

[PR'16] Multi-feature based Benchmark for Cervical Dysplasia Classification Evaluation. [pdf]

Tao Xu, Han Zhang, Cheng Xin, Edward Kim, L Rodney Long, Zhiyun Xue, Sameer Antani, and Xiaolei Huang. Pattern Recognition, 2016. 

[ISBI'15] Adjustable AdaBoost Classifier and Pyramid Features for Image-based Cervical Cancer Diagnosis .[pdf]

Tao Xu, Edward Kim, Xiaolei Huang. ISBI, 2015 (Oral with NIH Travel Support, Finalist of Best Student Papers [Link] ).

[MMM'13] Related HOG Features for Human Detection Using Cascaded Adaboost and SVM Classifiers. [pdf]

Hong Liu, Tao Xu, Xiangdong Wang and Yueliang Qian. MMM, 2013. 

[ICME'12] A Fast and Roust Pedestrian Detection Framework based on Static and Dynamic Information. [pdf]

Tao Xu, Hong Liu, Yueliang Qian and Zhe Wang. ICME, 2012. 

Selected Awards

• National Scholarship, CAS 2012

• Outstanding Graduate Student, CAS 2012

• First Prize in the Third ICT Technology Innovation Contest, CAS 2011

• Presidential Scholarship, CAU 2010

• Excellent Student Leader, CAU 2008

• Excellent Volunteer in Beijing Olympic and Paralympic Games, CAU 2008