publications

2026

  1. Under Review
    avenir.png
    Avenir-Web: Human-Experience-Imitating Multimodal Web Agents with Mixture of Grounding Experts
    Aiden Yiliu Li, Xinyue Hao, Shilong Liu, and 1 more author
    arXiv preprint arXiv:2602.02468, 2026
    PDF
  2. Under Review
    davison.png
    It’s a Matter of Time: Three Lessons on Long-Term Motion for Perception
    Willem Davison, Xinyue Hao, and Laura Sevilla-Lara
    arXiv preprint arXiv:2602.14705, 2026
    PDF

2025

  1. ICCV
    thumbnail_noword.png
    Principles of Visual Tokens for Efficient Video Understanding
    Xinyue Hao, Gen Li, Shreyank N Gowda, and 4 more authors
    In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025
    PDF Code
  2. NeurIPS
    teaser1.png
    Progressive Data Dropout: An Embarrassingly Simple Approach to Train Faster
    Shriram M S*, Xinyue Hao*, Shihao Hou, and 4 more authors
    In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025
    PDF Code Website

2024

  1. ECCVW
    watt_for_what.jpeg
    Watt for what: Rethinking deep learning’s energy-performance relationship
    Shreyank N Gowda, Xinyue Hao, Gen Li, and 3 more authors
    In European Conference on Computer Vision Workshop, 2024
    PDF

2020

  1. ICRA
    openloris.jpeg
    OpenLORIS-Object: A Robotic Vision Dataset and Benchmark for Lifelong Deep Learning
    Qi She, Fan Feng, Xinyue Hao, and 9 more authors
    In 2020 IEEE International Conference on Robotics and Automation (ICRA), 2020
    DOI PDF