World's Best Scientists 2026 revealed!

D-Index & Metrics

Computer Science

D-Index
47
Citations
9235
World Ranking
6471
National Ranking
2873

Overview

Chunyuan Li is a researcher affiliated with Microsoft in the United States. Their work primarily spans the field of Computer Science, with a particular focus on Artificial Intelligence and Computer Vision and Pattern Recognition. They have contributed to a considerable body of research encompassing several subfields, including Radiology, Nuclear Medicine and Imaging, Plant Science, and Information Systems.

Their research topics reflect a concentration on multimodal machine learning applications, domain adaptation and few-shot learning, and topic modeling. Additional areas include natural language processing techniques, advanced image and video retrieval methods, generative adversarial networks and image synthesis, as well as speech and dialogue systems.

Chunyuan Li has produced numerous publications, with a strong presence in prominent venues. Frequent platforms for their work include arXiv (Cornell University), which hosts the majority of their papers, alongside the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), the Proceedings of the AAAI Conference on Artificial Intelligence, Foundations and Trends® in Computer Graphics and Vision, and IEEE Transactions on Pattern Analysis and Machine Intelligence.

Some notable recent papers by Chunyuan Li include the following:

  • Visual Instruction Tuning, 2023, arXiv (Cornell University)
  • RegionCLIP: Region-based Language-Image Pretraining, 2022, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • A whole-slide foundation model for digital pathology from real-world data, 2024, Nature
  • Florence: A New Foundation Model for Computer Vision, 2021, arXiv (Cornell University)
  • Focal Self-attention for Local-Global Interactions in Vision Transformers, 2021, arXiv (Cornell University)

Their publishing record shows collaboration with several frequent coauthors, including Jianfeng Gao, Jianwei Yang, and Pengchuan Zhang. These collaborations have contributed significantly to their output in terms of both volume and diversity of research topics.

Best Publications

  • Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks

    Xiujun Li;Xi Yin;Chunyuan Li;Pengchuan Zhang

  • Variational autoencoder for deep learning of images, labels and captions

    Yunchen Pu;Zhe Gan;Ricardo Henao;Xin Yuan

  • Joint Embedding of Words and Labels for Text Classification

    Guoyin Wang;Chunyuan Li;Wenlin Wang;Yizhe Zhang

  • Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing

    Hao Fu;Chunyuan Li;Xiaodong Liu;Jianfeng Gao

  • Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms

    Dinghan Shen;Guoyin Wang;Wenlin Wang;Martin Renqiang Min

  • Florence: A New Foundation Model for Computer Vision

    Lu Yuan;Dongdong Chen;Yi-Ling Chen;Noel Codella

  • Preconditioned Stochastic Gradient Langevin Dynamics for deep neural networks

    Chunyuan Li;Changyou Chen;David Carlson;Lawrence Carin

  • Focal Self-attention for Local-Global Interactions in Vision Transformers

    Jianwei Yang;Chunyuan Li;Pengchuan Zhang;Xiyang Dai

  • Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-Training

    Weituo Hao;Chunyuan Li;Xiujun Li;Lawrence Carin

  • ALICE: Towards Understanding Adversarial Learning for Joint Distribution Matching

    Chunyuan Li;Hao Liu;Changyou Chen;Yunchen Pu

  • SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teaching

    Baolin Peng;Chunyuan Li;Jinchao Li;Shahin Shayandeh

  • Few-shot Natural Language Generation for Task-Oriented Dialog

    Baolin Peng;Chenguang Zhu;Chunyuan Li;Xiujun Li

  • Measuring the Intrinsic Dimension of Objective Landscapes.

    Chunyuan Li;Heerad Farkhoor;Rosanne Liu;Jason Yosinski

  • A comparison of 3D shape retrieval methods based on a large-scale benchmark supporting multimodal queries

    Bo Li;Yijuan Lu;Chunyuan Li;Afzal Godil

  • Persistence-Based Structural Recognition

    Chunyuan Li;Maks Ovsjanikov;Frederic Chazal

  • Shape Retrieval of Non-rigid 3D Human Models

    D. Pickup;X. Sun;P. L. Rosin;R. R. Martin

  • Optimus: Organizing Sentences via Pre-trained Modeling of a Latent Space

    Chunyuan Li;Xiang Gao;Yuan Li;Baolin Peng

  • A multiresolution descriptor for deformable 3D shape retrieval

    Chunyuan Li;A. Ben Hamza

  • SOLOIST: Few-shot Task-Oriented Dialog with A Single Pre-trained Auto-regressive Model

    Baolin Peng;Chunyuan Li;Jinchao Li;Shahin Shayandeh

  • Triangle Generative Adversarial Networks

    Zhe Gan;Liqun Chen;Weiyao Wang;Yunchen Pu

Frequent Co-Authors

Lawrence Carin
Lawrence Carin Duke University
Jianfeng Gao
Jianfeng Gao Microsoft (United States)
Zhe Gan
Zhe Gan Microsoft (United States)
A. Ben Hamza
A. Ben Hamza Concordia University
Liqun Chen
Liqun Chen University of Surrey
Guoyin Wang
Guoyin Wang Chongqing University of Posts and Telecommunications
Yejin Choi
Yejin Choi Stanford University
Noah A. Smith
Noah A. Smith University of Washington
Ryutarou Ohbuchi
Ryutarou Ohbuchi University of Yamanashi
Asli Celikyilmaz
Asli Celikyilmaz Facebook (United States)

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

As you consider studying Computer Science in the USA, it’s helpful to explore other online degrees and career pathways that align with your interests. For example, electrical engineering online tuition costs tend to be similar to those of computer science programs, making it feasible to diversify your skill set without a major financial burden.

If you want to enhance your resume quickly, there are easy licenses and certifications to get that can boost employability in related tech fields. These credentials can often be completed online in a matter of weeks or months.

For those seeking advanced qualifications without a long-term commitment, some of the shortest masters degree programs are available online, allowing you to upskill rapidly. Choosing one of the best masters degree to get helps ensure your credentials remain in demand and relevant in today’s evolving tech job market.

Best Scientists Citing Chunyuan Li

Trending Scientists

Recently Published Articles