World's Best Scientists 2026 revealed!

Overview

Yuan Cao is affiliated with Google in the United States. The primary area of research focus is in the field of Computer Science, with significant contributions spanning artificial intelligence, computer vision and pattern recognition, and signal processing.

Cao's work covers a range of subfields within computer science, including:

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Mechanical Engineering
  • Civil and Structural Engineering

The main topics addressed in their research include:

  • Natural Language Processing Techniques
  • Topic Modeling
  • Advanced Neural Network Applications
  • Multimodal Machine Learning Applications
  • Speech Recognition and Synthesis
  • Stochastic Gradient Optimization Techniques
  • Domain Adaptation and Few-Shot Learning

Yuan Cao has published extensively, with over a hundred works primarily appearing in prominent venues such as:

  • arXiv (Cornell University)
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • SSRN Electronic Journal
  • IEEE Transactions on Power Delivery
  • Neurocomputing

The frequent collaboration network includes scholars such as Quanquan Gu, Yonghui Wu, Orhan Fırat, Qiang Yang, and Jie Gui.

Among Cao's recent published papers are:

  • "SimVLM: Simple Visual Language Model Pretraining with Weak Supervision," 2021, arXiv (Cornell University)
  • "MBANet: A 3D convolutional neural network with multi-branch attention for brain tumor segmentation from MRI images," 2022, Biomedical Signal Processing and Control
  • "Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual Models," 2020, arXiv (Cornell University)
  • "Generalization Error Bounds of Gradient Descent for Learning Over-Parameterized Deep ReLU Networks," 2020, Proceedings of the AAAI Conference on Artificial Intelligence
  • "Towards Zero-Label Language Learning," 2021, arXiv (Cornell University)

The research work demonstrates a blend of theoretical and applied approaches, including methods for neural network optimization, multimodal machine learning, and medical imaging analysis. This diverse output reflects active engagement with both foundational questions and practical implementations within the computing research community.

Best Publications

  • Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation

    Yonghui Wu;Mike Schuster;Zhifeng Chen;Quoc V. Le

  • Gradient descent optimizes over-parameterized deep ReLU networks

    Difan Zou;Yuan Cao;Dongruo Zhou;Quanquan Gu

  • Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges

    Naveen Arivazhagan;Ankur Bapna;Orhan Firat;Dmitry Lepikhin

  • SimVLM: Simple Visual Language Model Pretraining with Weak Supervision

    Zirui Wang;Jiahui Yu;Adams Wei Yu;Zihang Dai

  • Stochastic Gradient Descent Optimizes Over-parameterized Deep ReLU Networks

    Difan Zou;Yuan Cao;Dongruo Zhou;Quanquan Gu

  • Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling

    Jonathan Shen;Patrick Nguyen;Yonghui Wu;Zhifeng Chen

  • Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networks

    Yuan Cao;Quanquan Gu

  • Hierarchical Generative Modeling for Controllable Speech Synthesis.

    Wei-Ning Hsu;Yu Zhang;Ron J. Weiss;Heiga Zen

  • Gmail Smart Compose: Real-Time Assisted Writing

    Mia Xu Chen;Benjamin N. Lee;Gagan Bansal;Yuan Cao

  • Leveraging Weakly Supervised Data to Improve End-to-end Speech-to-text Translation

    Ye Jia;Melvin Johnson;Wolfgang Macherey;Ron J. Weiss

  • Closing the generalization gap of adaptive gradient methods in training deep neural networks

    Jinghui Chen;Dongruo Zhou;Yiqi Tang;Ziyan Yang

  • Training Deeper Neural Machine Translation Models with Transparent Attention

    Ankur Bapna;Mia Xu Chen;Orhan Firat;Yuan Cao

  • Towards Understanding the Spectral Bias of Deep Learning

    Yuan Cao;Zhiying Fang;Yue Wu;Ding-Xuan Zhou

  • On the Convergence of Adaptive Gradient Methods for Nonconvex Optimization

    Dongruo Zhou;Yiqi Tang;Ziyan Yang;Yuan Cao

  • Generalization error bounds of gradient descent for learning over-parameterized deep relu networks

    Yuan Cao;Quanquan Gu

  • Fully-Hierarchical Fine-Grained Prosody Modeling For Interpretable Speech Synthesis

    Guangzhi Sun;Yu Zhang;Ron J. Weiss;Yuan Cao

  • Leveraging Monolingual Data with Self-Supervision for Multilingual Neural Machine Translation

    Aditya Siddhant;Ankur Bapna;Yuan Cao;Orhan Firat

  • Generating Diverse and Natural Text-to-Speech Samples Using a Quantized Fine-Grained VAE and Autoregressive Prosody Prior

    Guangzhi Sun;Yu Zhang;Ron J. Weiss;Yuan Cao

  • Your GAN is Secretly an Energy-based Model and You Should use Discriminator Driven Latent Sampling

    Tong Che;Ruixiang Zhang;Jascha Sohl-Dickstein;Hugo Larochelle

  • A Generalization Theory of Gradient Descent for Learning Over-parameterized Deep ReLU Networks

    Yuan Cao;Quanquan Gu

Frequent Co-Authors

Quanquan Gu
Quanquan Gu University of California, Los Angeles
Yonghui Wu
Yonghui Wu Google (United States)
Chris Callison-Burch
Chris Callison-Burch University of Pennsylvania
Sanjeev Khudanpur
Sanjeev Khudanpur Johns Hopkins University
Heiga Zen
Heiga Zen Google (United States)
Zhifeng Chen
Zhifeng Chen Google (United States)
Philipp Koehn
Philipp Koehn Johns Hopkins University
Kenji Sagae
Kenji Sagae University of California, Davis
Murat Saraclar
Murat Saraclar Boğaziçi University

If you think any of the details on this page are incorrect, let us know.

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

Exploring Computer Science in the USA opens doors to a variety of related online degrees and flexible career pathways. For those interested in broadening their technical expertise, there are top-quality online electrical engineering courses USA which complement computer science fundamentals and strengthen job prospects in diverse tech industries.

If you’re seeking a quicker career boost, consider 3-month certificate programs that pay well. These certifications can help you specialize in areas like cybersecurity, data management, or software development—expanding your skills in a short time and paving the way for entry-level roles.

Looking to advance quickly? The fastest online master's degree programs allow students to complete postgraduate studies in less than a year, accelerating professional growth and increasing earning potential without prolonged study commitments.

For those interested in long-term value, choosing masters degrees that are worth it helps ensure your education aligns with in-demand industry needs, fostering rewarding and sustainable careers in technology and beyond.

Best Scientists Citing Yuan Cao

Trending Scientists