Xianhang Li

Hi! I’m a Ph.D student in computer science at University of California, Santa Cruz. My adviser is Prof. Cihang Xie. My research interest is on computer vision and deep learning, with particular interests in action recognition, video classification and video synthesis.

My resume can be downloaded through this link CV.

News

• [new] We release Recap-DataComp-1B, where we use a LLaMA-3-powered LLaVA model to recaption the entire 1.3 billion images from DataComp-1B.

• [2024/10] One paper is accepted by NeurIPS 2024.

• [2024/9] EVP is accepted by TMLR 2024.

• [2024/5] I am honored to be selected as the only Jack Baskin and Peggy Downes-Baskin Fellowship recipient.

• [2024/2] Two papers (AdvXL, L2B) are accepted by CVPR 2024.

• [2023/9] CLIPA is accepted by NeurIPS 2023. In addition, we release our best model, CLIPA-G/14, which attains 83.0% zero-shot ImageNet top-1 accuracy.

• [2022/10/24] One paper was accepted in NeruaIPS ML Safty Workshop 2022.

• [2022/7/8] One paper was accepted in ECCV 2022.

• [2022/6/13] Started my summer intern at ByteDance with Dr. Peng Wang.

• [2022/1/28] One paper was accepted in ICLR 2022.

• [2021/10/4] One paper was accepted in WACV 2022.

• [2021/06/13] I will join UCSC as a Ph.D. student!

• [2021/01/13] One paper was accepted in ICLR 2021.

• [2020/02/24] One paper was accepted in CVPR 2020.

Publications [Full List]

 

What If We Recaption Billions of Web Images with LLaMA-3?
Xianhang Li*, Haoqin Tu*, Mude Hui*, Zeyu Wang*, Bingchen Zhao*, Junfei Xiao, Sucheng Ren, Jieru Mei, Qing Liu, Huangjie Zheng, Yuyin Zhou, Cihang Xie
arxiv, 2024.
[PDF] [Code]

 

Scaling White-Box Transformers for Vision
Jinrui Yang*, Xianhang Li*, Druv Pai, Yuyin Zhou, Yi Ma, Yadong Yu, Cihang Xie
NeurIPS, 2024.
[PDF] [Code]

 

Revisiting Adversarial Training at Scale
Zeyu Wang*, Xianhang Li*, Hongru Zhu, Cihang Xie
CVPR, 2024.
[PDF] [Code]

 

Learning to Bootstrap for Combating Label Noise
Yuyin Zhou*, Xianhang Li*, Fengze Liu, Xuxi Chen, Lequan Yu, Cihang Xie, Matthew P. Lungren, Lei Xing
CVPR, 2024.
[PDF] [Code]

 

Unleashing the Power of Visual Prompting At the Pixel Level
Junyang Wu*, Xianhang Li*, Chen Wei, Huiyu Wang, Alan Yuille, Yuyin Zhou, Cihang Xie
TMLR, 2024.
[PDF] [Code]

 

CLIPA-v2: Scaling CLIP Training with 81.1% Zero-shot ImageNet Accuracy within a $10,000 Budget; An Extra $4,000 Unlocks 81.8% Accuracy
Xianhang Li*, Zeyu Wang* and Cihang Xie
NeurIPS R0-FoMo Workshop, 2023.
[PDF] [Code]

 

An Inverse Scaling Law for CLIP Training
Xianhang Li*, Zeyu Wang* and Cihang Xie
NeurIPS 2023.
[PDF] [Code]

 

In Defense of Image Pre-Training for Spatiotemporal Recognition
Xianhang Li, Huiyu Wang, Chen Wei, Jieru Mei, Alan Yuille, Yuyin Zhou and Cihang Xie
European Conference on Computer Vision (ECCV'22), 2022.
[PDF] [Code]

 

Pose-guided Generative Adversarial Net for Novel View Action Synthesis
Xianhang Li, Junhao Zhang, Kunchang Li, Shruti Vyas, Yogesh S Rawat
Winter Conference on Applications of Computer Visions (WACV'22), 2022.
[PDF]

 

CT-Net: Channel Tensorization Network for Video Classification
Kunchang Li*, Xianhang Li*, Yali Wang*, Jun Wang, Yu Qiao
International Conference on Learning Representations (ICLR'21), 2021.
[PDF] [Code]

 

SmallBigNet: Integrating Core and Contextual Views for Video Classification
Xianhang Li*, Yali Wang*, Zhipeng Zhou*, Yu Qiao
Computer Vision and Pattern Recognition (CVPR'20), 2020.
[PDF] [Code]

Experience

• ByteDance Intelligent Creation Lab

  Research Intern 　    Moutain view, USA, 2022.06 - Present

  Efficient Video Training     One paper was submitted to CVPR2023

• Center for Research in Computer Vision(CRCV) in UCF

  Research Assistant 　    Orlando, USA, 2020.05 - 2020.08

  Cross-View Video Synthesis     One paper was accepted to WACV2022

• Multimedia Research Center(MMLAB) in SIAT

  Research Assistant 　    Shenzhen, China, 2018.10 - 2020.10

  Video Classification 　    One paper was submitted to ICLR2021; the other was published on CVPR2020

• Queen Mary University of London

  Research Assistant 　    London , UK, 2018.06 - 2018.10

Education

• 2021.09 - Present Ph.D. in Computer Science and Engineering, University of California, Santa Cruz (UCSC), Santa Cruz, USA advised by Prof. Cihang Xie

• 2019.08 - 2021.05
  M.Sc. in Computer Science, University of Central Florida (UCF), Orlando, USA
  GPA: 3.89/4.0
  advised by Prof. Yogesh Singh Rawat in Center for Research in Computer Vision, supported by Prof. Jun Wang.

• 2014.09 - 2018.07
  B.E. in Telecommunications Engineering and Management, Beijing University of Posts and Telecommunications(BUPT), Beijing, China

Moments

My girlfriend and I adopted a cute cat. His name is Turing! He is also one of the mentors in my family.