Sotabase

Career

· Assistant Professor, New York University2023–
· Research Scientist, Meta AI (Facebook AI Research)2018–2022
· PhD Student, University of California, San Diego2013–2018
· Research Scientist, Google DeepMind
· Education, Shanghai Jiao Tong University

Publications (101)

Momentum Contrast for Unsupervised Visual Representation Learning
Computer Vision and Pattern Recognition · 2019
14,167
cited
Aggregated Residual Transformations for Deep Neural Networks
Computer Vision and Pattern Recognition · 2016
11,346
cited
Masked Autoencoders Are Scalable Vision Learners
Computer Vision and Pattern Recognition · 2021
10,316
cited
A ConvNet for the 2020s
Computer Vision and Pattern Recognition · 2022
7,220
cited
Scalable Diffusion Models with Transformers
IEEE International Conference on Computer Vision · 2022
4,485
cited
Holistically-Nested Edge Detection
International Journal of Computer Vision · 2015
3,779
cited
Deeply-Supervised Nets
International Conference on Artificial Intelligence and Statistics · 2014
2,405
cited
An Empirical Study of Training Self-Supervised Vision Transformers
IEEE International Conference on Computer Vision · 2021
2,220
cited
Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification
European Conference on Computer Vision · 2017
1,456
cited
Decoupling Representation and Classifier for Long-Tailed Recognition
International Conference on Learning Representations · 2019
1,421
cited
ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders
Computer Vision and Pattern Recognition · 2023
1,368
cited
Masked Feature Prediction for Self-Supervised Visual Pre-Training
Computer Vision and Pattern Recognition · 2021
796
cited
PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding
European Conference on Computer Vision · 2020
758
cited
SLIP: Self-supervision meets Language-Image Pre-training
European Conference on Computer Vision · 2021
582
cited
SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training
International Conference on Machine Learning · 2025
433
cited
Exploring Randomly Wired Neural Networks for Image Recognition
IEEE International Conference on Computer Vision · 2019
380
cited
Attentional ShapeContextNet for Point Cloud Recognition
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2018
339
cited
FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions
Computer Vision and Pattern Recognition · 2020
321
cited
Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts
Computer Vision and Pattern Recognition · 2020
310
cited
Rethinking Spatiotemporal Feature Learning For Video Understanding
arXiv.org · 2017
260
cited
Sotabase