Timing Yang

Timing Yang

MS. student @ USC

Introduction

I am pursuing a Master of Science in Electrical and Computer Engineering (Machine Learning and Data Science) at the University of Southern California. I am conducting research on Mamba model at the Computational Cognition, Vision, and Learning lab at Johns Hopkins University, under the supervision of Prof. Alan Yuille. I previously worked on open-vocabulary 3D object detection at the Institute for Interdisciplinary Information Sciences at Tsinghua University with Prof. Li Yi (Eric).

Prior to this, I earned my Bachelor of Science in Electronic Information Engineering from Dalian University of Technology, where I conducted research on few-shot learning under the supervision of Prof. Peihua Li, worked on underwater object detection in IIAU-Lab under the supervision of Prof. Dong Wang, researched video segmentation under the supervision of Prof. Shenglan Liu, and worked on image monitoring for the crystallization process under the supervision of Prof. Tao Liu. I also interned at Panasonic Electrical Software Development (Dalian) Co. LTD.

📢 I am currently seeking a PhD position for Fall 2025

📮Email:(timingya@usc.edu); 🛰️wechat

DLUT USC Tsinghua JHU Panasonic

Current Research Interest

  • 2D/3D Scene Understanding(Object detection, Segmentation)
  • Transformer/Mamba for model interpreting.
  • Few-Shot Learning for classification
  • Video Action Segmentation

Education

  • (MS)University of Southern California, Los Angeles, United States
    08/2023-06/2025
    GPA: 4.0/4.0

  • (BS)Dalian University of Technology, Dalian, China
    09/2018-07/2022
    GPA: 87/100

Publication/Current and Future submission

  • Interpreting Mamba
    Timing Yang, Feng Wang, Jieru Mei, Alan Yuille.
    Target submission to CVPR 2025. ([arxiv] / [code])

  • Causal Image Modeling for Efficient Visual Understanding
    Feng Wang, Timing Yang, Yaodong Yu, Sucheng Ren, Guoyizhe Wei, Wei Shao, Yuyin Zhou, Alan Yuille, Cihang Xie.
    Submitted to ICLR 2025. (arxiv / code)

  • ImOV3D: Learning Open-Vocabulary Point Clouds 3D Object Detection from Only 2D Images
    Timing Yang*, Yuanliang Ju*, Li Yi.
    Accepted by NeurIPS 2024. ([arxiv] / [code])