Yuxin Wu

Yuxin Wu

I’m building large multimodal models at Moonshot AI. We’re hiring top talents in China and US.

Prior to this, I worked at Google Brain on foundation models, and at Facebook AI Research on computer vision. I have expertise in research and infrastructure for deep learning and computer vision.

My previous works at FAIR have received Best Paper Honorable Mention in ECCV 2018, Best Paper Nomination in CVPR 2020, and Mark Everingham Prize in ICCV 2021. I also created detectron2, one of the most popular Facebook AI projects.

Education

  • Master in Computer Vision, 2016

    Carnegie Mellon University

  • Bachelor in Computer Science, 2015

    Tsinghua University

Selected Publications

Rethinking "Batch" in BatchNorm
Deep analysis of all the caveats in BatchNorm.
Yuxin Wu, Justin Johnson
Tech Review, 2021
Paper Code
Rethinking "Batch" in BatchNorm
Momentum Contrast for Unsupervised Visual Representation Learning
Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, Ross Girshick
Computer Vision and Pattern Recognition (CVPR), 2020 (Oral)
Best Paper Nomination
Paper Code Code Slides Talk
Momentum Contrast for Unsupervised Visual Representation Learning
PointRend: Image Segmentation as Rendering
Alexander Kirillov, Yuxin Wu, Kaiming He, Ross Girshick
Computer Vision and Pattern Recognition (CVPR), 2020 (Oral)
Paper Code Slides Talk
PointRend: Image Segmentation as Rendering
Feature Denoising for Improving Adversarial Robustness
The first ImageNet classifier that survives strong white-box adversarial attacks.
Cihang Xie, Yuxin Wu, Laurens van der Maaten, Alan Yuille, Kaiming He
Computer Vision and Pattern Recognition (CVPR), 2019
Paper Code
Feature Denoising for Improving Adversarial Robustness
Group Normalization
Yuxin Wu, Kaiming He
European Conference on Computer Vision (ECCV), 2018 (Oral)
Best Paper Honorable Mention (top 3)
Paper Code Poster Slides Talk Extended Journal Version
Group Normalization
House3D: A Rich and Realistic 3D Environment
Yi Wu, Yuxin Wu, Georgia Gkioxari, Yuandong Tian
International Conference on Learning Representations (ICLR), 2018
Paper Code Media
House3D: A Rich and Realistic 3D Environment
ELF: An Extensive, Lightweight and Flexible Research Platform for Real-time Strategy Games
Platform that powers large-scale RL projects such as OpenGO.
Yuandong Tian, Qucheng Gong, Wenling Shang, Yuxin Wu, Lawrence Zitnick
Neural Information Processing Systems (NeurIPS), 2017 (Oral)
Paper Code Slides Talk
ELF: An Extensive, Lightweight and Flexible Research Platform for Real-time Strategy Games
Training Agent for First-Person Shooter Game with Actor-Critic Curriculum Learning
Award-winning AI that plays FPS games.
Yuxin Wu, Yuandong Tian
International Conference on Learning Representations (ICLR), 2017
Paper Code Video Demo
Training Agent for First-Person Shooter Game with Actor-Critic Curriculum Learning
DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients
Comprehensive results on low bitwidth neural network.
Shuchang Zhou, Yuxin Wu, Zekun Ni, Xinyu Zhou, He Wen, Yuheng Zou
Tech Report, 2016
Paper Code

Open Source Projects

Full list of OSS contributions can be found here.

Detectron2

A computer vision library with a focus on detection-related tasks.

  • Widely used in research community.
  • Support training and deployment for dozens of Meta’s products & services, e.g. 1 2 3 4.
Docs
Detectron2
Tensorpack
A neural net training interface on TensorFlow, with focus on speed + flexibility. Includes highly-optimized trainers, data pipelines, and solid paper reproductions.
Docs
Tensorpack
Adversarial Attack on Face Recognition
Black-box adversarial attacks on AWS/Azure’s public face recognition APIs, the first successful attack of its kind.
Tutorial (Chinese) Media (Chinese)
Adversarial Attack on Face Recognition
OpenPano
Panorama stitching written from scratch in C++. Includes SIFT feature detection, RANSAC, bundle adjustment (w/ analytical gradients), straightening and warping.
Tutorial
OpenPano
wechat-dump
Cracking encrypted wechat message history from Android phones by reverse-engineering.
wechat-dump

Awards

  • Mark Everingham Prize in ICCV 2021 for the detectron2 project.
    Announcement Media

  • Best Paper Nominee in CVPR 2020 for the paper “Momentum Contrast”.

  • Winner of defense track in Competition on Adversarial Attacks and Defenses (CAAD) 2018.

    We trained an ImageNet classifier with state-of-the-art robustness against adversarial attacks.

  • Winner of CTF in Competition on Adversarial Attacks and Defenses (CAAD) CTF 2018. Competition Recording (Chinese) Media (Chinese)

    We performed successful adversarial attacks / defenses against other teams during the live competition.

  • Best Paper Honorable Mention award in ECCV 2018 for the paper “Group Normalization”. Announcement

  • Google Open Source Peer Bonus in 2017 for the tensorpack project. Announcement

  • Winner of VizDoom AI Competition in CIG 2016.

    Our Doom bot, “F1”, beat competitors in death matches by a large margin.
    Competition Media Video

  • Champion of Student Cluster Competition in both ISC 2015 and ASC 2015.

    Optimize software and hardware for low-power high-performance computation. Media Media

  • Finalist in SIGMOD Programming Contest in SIGMOD 2014, as team leader of “blxlrsmb”.

    Design and implement a large social network database to support efficient queries.

  • Capture the Flags (CTF, a security competition): 11th in SECCON CTF 2014, 8th in Codegate CTF 2015, 5th in DEFCON CTF 2015 as a team member of “blue-lotus”.