Yue Wang

[Google Scholar] [Email]

avatar.png

I am an Assistant Professor at USC CS (2023 Fall-). 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:

  • neural representations for dynamic scenes
  • real2sim2real for robotics
  • robotic manipulation

PhD students:

MS students:

Undergrads:

  • Dylan Sun

Visitors:

  • Ziyu Chen
  • Feishi Wang
  • Yiduo Guo

Alumni:

  • James Qian (Next stop: Stanford)

Selected Award:

  • Toyota Research Young Faculty Researcher
  • Powell Faculty Research Award
  • ICBS Best Paper Award
  • Nvidia Fellowship
  • MIT William A. Martin Master’s Thesis Award

news

Oct 1, 2024 Serve as Area Chairs for 3DV 2025, ICLR 2025, CVPR 2025, and a Presentation Chair for RSS 2025.
Sep 25, 2024 Three papers (including one spotlight) accepted to NeurIPS 2024.
Sep 22, 2024 Three papers accepted to CoRL 2024. RAM is selected as an oral presentation.
Aug 1, 2024 Two papers accepted to ECCV 2024. DVT is selected as an oral presentation.
Jul 10, 2024 Agent-Driver is accepted to COLM 2024.

selected publications

  1. CORL Oral
    RAM: Retrieval-Based Affordance Transfer for Generalizable Zero-Shot Robotic Manipulation
    Yuxuan Kuang, Junjie Ye, Haoran Geng, Jiageng Mao, Congyue Deng, Leonidas Guibas, He Wang, and Yue Wang
    In The Conference on Robot Learning 2024
  2. COLM
    A Language Agent for Autonomous Driving
    Jiageng Mao*, Junjie Ye*, Yuxi Qian, Marco Pavone, and Yue Wang
    In Conference on Language Modeling 2024
  3. ECCV Oral
    Denoising Vision Transformers
    Jiawei Yang*, Katie Z Luo*, Jiefeng Li, Congyue Deng, Leo Guibas, Kilian Q Weinberger, Yonglong Tian, and Yue Wang
    In The European Conference on Computer Vision 2024
  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 2024
  5. 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
  6. 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
  7. 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
  8. NeurIPS
    PRNet: Self-Supervised Learning for Partial-to-Partial Registration
    Yue Wang, and Justin M. Solomon
    In Conference on Neural Information Processing Systems 2019
  9. ICCV
    Deep Closest Point: Learning Representations for Point Cloud Registration
    Yue Wang, and Justin M. Solomon
    In The International Conference on Computer Vision 2019
  10. 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