Yue Wang

[Google Scholar] [Email] [CV]

avatar.png

I am an Assistant Professor at USC CS (2023 Fall-), and a part-time Research Scientist at NVIDIA Research (2022 Fall-) working with Prof. Marco Pavone. I graduated from MIT EECS in 2022, advised by Prof. Justin Solomon at Geometric Data Processing Group. I was also fortunate to collaborate with Prof. Michael Bronstein and Prof. Phillip Isola. Previously, I was a master student at University of California, San Diego. Prior to that, I received my BEng in Computer Science from Zhejiang University. I’ve received the Nvidia Fellowship (2020-2021) and the MIT EECS William A. Martin Master’s Thesis Award (2021).

I am looking to hire multiple PhDs/visiting students. In particular, we welcome students from marginalized groups. We firmly support Viterbi school’s DEI initiative to contribute to diversity. For PhD applicants, please mention my name in your application. Interested candidates for visiting positions can fill this form and I will respond as soon as I find a good fit.


My research lies in the intersection of computer vision, computer graphics, and robotics. My goal is to use machine learning to enable robotic intelligence with minimal human supervision. I study how to design 3D learning systems which leverage geometry, appearance, motion, and any other cues that are naturally available in sensory inputs. I am also broadly interested in fundamental deep learning tools and eclectic applications on top of these systems.

Topics I currently focus on include:

Past topics:


PhD students:

MS students:

Undergrads:

  • James Qian
  • Dylan Sun

DGCNN received the Frontiers of Science Award (a.k.a Best Paper Award at ICBS), one of the only four awardees in the Graphics and Geometric Computing area in the past 5 years.

news

Feb 1, 2024 Three papers accepted to CVPR 2024!
Nov 1, 2023 We received an unrestricted gift funding from Google Research to support our research on “Towards Novel Geometric Rrepresentations for Robot Intelligence”. Thanks Google!
Oct 1, 2023 We organized “Neural fields for robotics and autonomous driving” at ICCV2023.
Aug 15, 2023 I joined USC CS as an Assistant Professor starting Fall 2023!
Feb 27, 2023 Four papers (few-shot neural rendering, representation learning for point clouds, end-to-end prediction for AV, and map learning) accepted to CVPR 2023!

selected publications

  1. arXiv
    Denoising Vision Transformers
    Jiawei Yang*, Katie Z Luo*, Jiefeng Li, Kilian Q Weinberger, Yonglong Tian, and Yue Wang
    2024
  2. arXiv
    A Language Agent for Autonomous Driving
    Jiageng Mao*, Junjie Ye*, Yuxi Qian, Marco Pavone, and Yue Wang
    2023
  3. arXiv
    LiNeRF: Rethinking Directional Integration in Neural Radiance Fields
    Congyue Deng, Jiawei Yang, Leonidas Guibas, and Yue Wang
    2023
  4. ICLR
    EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision
    Jiawei Yang, Boris Ivanovic, Or Litany, Xinshuo Weng, Seung Wook Kim, Boyi Li, Tong Che, Danfei Xu, and 3 more authors
    In International Conference on Learning Representations 2023
  5. arXiv
    GPT-Driver: Learning to Drive with GPT
    Jiageng Mao, Yuxi Qian, Hang Zhao, and Yue Wang
    2023
  6. CVPR
    FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularization
    Jiawei Yang, Marco Pavone, and Yue Wang
    In The Conference on Computer Vision and Pattern Recognition 2023
  7. CORL
    DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries
    Yue Wang, Vitor Guizilini, Tianyuan Zhang, Yilun Wang, Hang Zhao, and Justin M. Solomon
    In The Conference on Robot Learning 2021
  8. ECCV
    Rethinking few-shot image classification: a good embedding is all you need?
    Yonglong Tian*, Yue Wang*, Dilip Krishnan, Joshua B Tenenbaum, and Phillip Isola
    In The European Conference on Computer Vision 2020
  9. NeurIPS
    PRNet: Self-Supervised Learning for Partial-to-Partial Registration
    Yue Wang, and Justin M. Solomon
    In Conference on Neural Information Processing Systems 2019
  10. ICCV
    Deep Closest Point: Learning Representations for Point Cloud Registration
    Yue Wang, and Justin M. Solomon
    In The International Conference on Computer Vision 2019
  11. TOG
    Dynamic Graph CNN for Learning on Point Clouds
    Yue Wang, Yongbin Sun, Ziwei Liu, Sanjay E. Sarma, Michael M. Bronstein, and Justin M. Solomon
    ACM Transactions on Graphics 2019