Bio
Hello! Welcome to my homepage! I am Yu Wang, a dedicated research scientist specializing in machine learning techniques and theories. I recently moved to San Fransisco bay area and look forward to joining the local academia!
I obtained my PhD degree in Computer Science from the University of Cambridge UK in 2016. My PhD study was co-supervised by Dr. Ian Wassell and Dr. David Wipf (David is my internship mentor at Microsoft Research), with a focus on variational Bayesian inference. I received my postdoc training at the Department of Pure Mathematics and Statistics (DPMMS) of University of Cambridge, UK, co-supervised by Prof. John Aston and Prof. Carola-Bibiane Schönlieb in 2016-2018.
After my postdoc, I respectively worked as a senior research scientist at JD AI research academy working with Prof. Tao Mei, and as a senior research fellow at QY lab – Tsinghua University working with Prof. Lu Fang.
Research Interests
I love math and CS! My research interests include machine learning theories (and their application on computer vision tasks, language models), generalization theories, generative modeling, self-supervised learning, Bayesian inference, sparse coding, safety of foundation models, and broader statistical machine learning problems.
Publications
( * indicate joint first authors with equal contributions )
- Kernel Masked Image Modeling Through the Lens of Theoretical Understanding
Yurui Qian*; Yu Wang*; Jingjing Zou*; Jingyang Lin; Yingwei Pan; Ting Yao; Qibin Sun; Tao Mei
IEEE Transactions on Neural Networks and Learning Systems, 2024 (TNNLS)
- When Visual Grounding Meets Gigapixel-level Large-scale Scenes: Benchmark and Approach
Tao Ma, Bing Bai, Haozhe Lin, Heyuan Wang, Yu Wang, Lin Luo, LU FANG
CVPR 2024
- RealGraph: A Multiview Dataset for 4D Real-world Context Graph Generation
Haozhe Lin*, Zequn Chen*, Jinzhi Zhang*, Bing Bai, Yu Wang, Ruqi Huang, Lu Fang
ICCV 2023
- Boosting Graph Contrastive Learning via Graph Contrastive Saliency
Chunyu Wei*, Yu Wang*, Bing Bai*, Kai Ni, David J. Brady, Lu Fang
ICML 2023
- DartBlur: Privacy Preservation with Detection Artifacts Suppression
Baowei Jiang*, Bing Bai*, Haozhe Lin*, Yu Wang, Yuchen Guo, Lu Fang
CVPR 2023
- Dual Vision Transformer
Ting Yao, Yehao Li, Yingwei Pan, Yu Wang, Xiao-Ping Zhang, Tao Mei
Transactions on Pattern Analysis and Machine Intelligence, 2023 (T-PAMI)
- Out-of-Distribution Detection via Conditional Kernel Independence Model
Yu Wang*, Jingjing Zou*, Jingyang Lin, Qing Ling, Yingwei Pan, Ting Yao, Tao Mei
NeurIPS 2022 (spotlight)
- SPE-Net: Boosting Point Cloud Analysis via Rotation Robustness Enhancement
Zhaofan Qiu, Yehao Li, Yu Wang, Yingwei Pan, Ting Yao, Tao Mei
ECCV 2022
- A low rank promoting prior for unsupervised contrastive learning
Yu Wang, Jingyang Lin, Qi Cai, Yingwei Pan, Ting Yao, Hongyang Chao, Tao Mei
Transactions on Pattern Analysis and Machine Intelligence (T-PAMI) 2022
- Improving self-supervised learning with automated unsupervised outlier arbitration
Yu Wang, Jingyang Lin, Jingjing Zou, Yingwei Pan, Ting Yao, Tao Mei
NeurIPS 2021
- Transferrable contrastive learning for visual domain adaptation
Yang Chen, Yingwei Pan, Yu Wang, Ting Yao, Xinmei Tian, Tao Mei
ACM MM 2021
- A style and semantic memory mechanism for domain generalization
Yang Chen, Yu Wang, Yingwei Pan, Ting Yao, Xinmei Tian, Tao Mei
ICCV 2021
- Joint contrastive learning with infinite possibilities
Qi Cai*, Yu Wang*, Yingwei Pan, Ting Yao, Tao Mei
NeurIPS 2020 (Spotlight, top 2%)
- Learning a unified sample weighting network for object detection
Qi Cai, Yingwei Pan, Yu Wang, Jingen Liu, Ting Yao, Tao Mei
CVPR 2020
- Transferrable prototypical networks for unsupervised domain adaptation
Yingwei Pan, Ting Yao, Yehao Li, Yu Wang, Chong-Wah Ngo, Tao Mei
CVPR 2019 (Oral)
- Artificial intelligence in breast imaging
EPV Le, Yu Wang, Yuan Huang, Sarah Hickman, Fiona J. Gilbert
Clinical Radiology 74 (5), 357-366
- Recurrent variational autoencoders for learning nonlinear generative models in the presence of outliers
Yu Wang*, Bin Dai*, Gang Hua, John Aston, David Wipf
IEEE Journal of Selected Topics in Signal Processing (JSTSP), vol. 12, no. 6, Dec. 2018
- Connections with robust PCA and the role of emergent sparsity in variational autoencoder models
Bin Dai, Yu Wang, John Aston, Gang Hua, David Wipf
Journal of Machine Learning Research (JMLR), vol.19, no.1, Jan, 2018
- Green generative modeling: recycling dirty data using recurrent variational autoencoders
Yu Wang, Bin Dai, Gang Hua, John Aston, David Wipf
UAI 2017
- Simultaneous Bayesian sparse approximation with structured sparse models
Wei Chen, David Wipf, Yu Wang, Yang Liu, Ian J Wassell
IEEE Transactions on Signal Processing (TSP),vol. 64, no. 23, Sep, 2016
- Clustered sparse Bayesian learning.
Yu Wang, David P Wipf, Jeong-Min Yun, Wei Chen, Ian J Wassell
UAI 2015 (Oral, top 1%)
- Multi-task learning for subspace segmentation
Yu Wang, David Wipf, Qing Ling, Wei Chen, Ian Wassell
ICML 2015 (Oral)
- Exploiting the convex-concave penalty for tracking: A novel dynamic reweighted sparse Bayesian learning algorithm
Yu Wang, David Wipf, Wei Chen, Ian J Wassell
ICASSP 2014
- Exploiting hidden block sparsity: Interdependent matching pursuit for cyclic feature detection
Yu Wang, Wei Chen, Ian J Wassell
GLOBECOM 2013
Awards
1st Place at CVPR 2021 Open World Vision Grand Challenge
University of Cambridge Overseas Trust PhD Scholarship
University of Cambridge Girton College Travel Award
“Star of Tomorrow Internship Excellence Award”, Microsoft Research Asia
Hobbies
I love classical music and reading. My favorite music is Rachmaninov Piano Concerto No.2. I am a professional clarinetist, and I also had the honor to be invited to play concert at the “Temple of Music” in Vienna, Austria – Wiener Musikverein, Großer Saal (we were playing Beethoven Symphony No. 8, and Brahms Symphony No. 1.), when I was 16 years old. At the age of 14, I recorded my first clarinet album with a theme on Mozart and Weber. I also enjoy playing piano and saxophone for fun.