Yulong Shi Master's Student Northeastern University, Shenyang, China Email: derek_shiii@yeah.net GitHub  /  Google Scholar  /  ORCID CV (English)  /  简历 (中文)

Biography

I am a Master's student in Biomedical Engineering at Northeastern University, China. Before that, I received my B.Eng. in Measurement and Control Technology and Instrument from Guilin University of Electronic Technology in 2024.

I am actively looking for a PhD position starting in Fall 2027. If you are interested in my background, please feel free to reach out via email.

My research interests include world action models, autonomous driving, medical image analysis, and vision foundation models for medical applications. Recently, I am also exploring multimodal medical image analysis and 3D medical vision.

Publications [Google Scholar]

• PARDA: A Perceive-Act-Reflect-Distill Agent for Source-Free Unsupervised Domain Adaptation
  Yulong Shi, Shijie Li, Ziyi Li, Lin Qi (corresponding author), Shouliang Qi, Ting Liu, Wei Qian.
  IEEE Transactions on Medical Imaging (IEEE TMI), 2026.
  
  IF: 13.0, JCR Q1   Code
  Bib

  @article{shi2026parda,
    title={PARDA: A Perceive-Act-Reflect-Distill Agent for Source-Free Unsupervised Domain Adaptation},
    author={Shi, Yulong and Li, Shijie and Li, Ziyi and Qi, Lin and Qi, Shouliang and Liu, Ting and Qian, Wei},
    journal={IEEE Transactions on Medical Imaging},
    year={2026},
    doi={10.1109/TMI.2026.3744091}
  }

• Search2Adapt: Multi-Agent Collaborative Tree Search for Source-Free Unsupervised Domain Adaptation
  Yulong Shi, Wenwen Zhang, Ziyi Li, Lin Qi.
  The 34th ACM International Conference on Multimedia (ACM MM), 2026.
  
  CCF-A, CORE A*   Code  

  Bib

  @inproceedings{shi2026search2adapt,
    title={Search2Adapt: Multi-Agent Collaborative Tree Search for Source-Free Unsupervised Domain Adaptation},
    author={Shi, Yulong and Zhang, Wenwen and Li, Ziyi and Qi, Lin},
    booktitle={Proceedings of the 34th ACM International Conference on Multimedia},
    year={2026}
  }

• AutoLand: A Data-Efficient Automated Agentic Workflow for Universal Medical Landmark Detection
  Ziyi Li, Jiarui Li, Yulong Shi, Xue Jiang, Shouliang Qi, Ting Liu, Lin Qi, Wei Qian.
  29th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2026.
  
  CCF-B, CORE A  

  Bib

  @inproceedings{li2026autoland,
    title={AutoLand: A Data-Efficient Automated Agentic Workflow for Universal Medical Landmark Detection},
    author={Li, Ziyi and Li, Jiarui and Shi, Yulong and Jiang, Xue and Qi, Shouliang and Liu, Ting and Qi, Lin and Qian, Wei},
    booktitle={Proceedings of the 29th International Conference on Medical Image Computing and Computer Assisted Intervention},
    year={2026}
  }

• Tell2Adapt: A Unified Framework for Source Free Unsupervised Domain Adaptation via Vision Foundation Model
  Yulong Shi, Shijie Li, Ziyi Li, Lin Qi.
  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2026.
  
  CCF-A, CORE A*   Code  

  Bib

  @InProceedings{Shi_2026_CVPR,
      author    = {Shi, Yulong and Li, Shijie and Li, Ziyi and Qi, Lin},
      title     = {Tell2Adapt: A Unified Framework for Source Free Unsupervised Domain Adaptation via Vision Foundation Model},
      booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
      month     = {June},
      year      = {2026},
      pages     = {6941-6950}
  }

• HEAL: Learning-Free Source Free Unsupervised Domain Adaptation for Cross-Modality Medical Image Segmentation
  Yulong Shi, Jiapeng Li, Lin Qi.
  The 36th British Machine Vision Conference (BMVC), 2025.
  
  CCF-C, CORE A   arXiv   Code  

  Bib

  @misc{shi2025heallearningfreesourcefree,
        title={HEAL: Learning-Free Source Free Unsupervised Domain Adaptation for Cross-Modality Medical Image Segmentation},
        author={Yulong Shi and Jiapeng Li and Lin Qi},
        year={2025},
        eprint={2511.17958},
        archivePrefix={arXiv},
        primaryClass={cs.CV},
        url={https://arxiv.org/abs/2511.17958},
  }

• A3-DualUD: Source-free unsupervised domain adaptation via anatomical anchor alignment and dual-path uncertainty denoising for cross-modality medical image segmentation
  Jie Zhou^*, Yulong Shi^*, Lin Qi, Xue Jiang, Shouliang Qi, Wei Qian. (^*equal contribution)
  Computer Methods and Programs in Biomedicine, 2025.
  
  IF: 4.8, JCR Q1   Code  

  Bib

  @article{zhou2025a3,
    title={A3-DualUD: Source-free unsupervised domain adaptation via anatomical anchor alignment and dual-path uncertainty denoising for cross-modality medical image segmentation},
    author={Zhou, Jie and Shi, Yulong and Qi, Lin and Jiang, Xue and Qi, Shouliang and Qian, Wei},
    journal={Computer Methods and Programs in Biomedicine},
    volume={271},
    pages={109017},
    year={2025},
    publisher={Elsevier}
  }

Experience

• Huawei Intelligent Automotive Solution BU   Multimodal Foundation Model Engineer 06/2026 – 09/2026
  ReinWAM. Proposed a reinforcement post-training framework for World Action Models that optimizes the World Model, Action Expert, and their information coupling while keeping the pretrained backbone frozen. Introduced factorized credit assignment for World-Action coupling to avoid indiscriminate propagation of global rewards, mitigating safety degradation from shared credit. Achieved 91.1% PDMS on NAVSIM with consistent EP improvements.
  JEV-Drive. Designed a fast end-to-end planning framework combining single-step semantic decision-making with conditional diffusion. Built a 36-class orthogonal driving-intent codebook on Qwen3.5-0.8B; independent Byte Token mapping enables answer-position logit-slice readout after a single prefill, avoiding autoregressive decoding latency. Injected Qwen instructions into DiffusionDrive through Cross-Attention KV, FiLM feature modulation, and classification-score bias to guide 20 anchors through two DDIM denoising steps and trajectory selection. Achieved 90.5 ms inference and 88.7% PDMS on NAVSIM using a single front-view input.

Honors & Awards

• National Scholarship 2025
• First Prize, 10th National Biomedical Engineering Innovation Design Competition 2025
  Project: SFLocNet - Source-Free Anatomical Landmark Localization Framework.

Education

• M.S. in Biomedical Engineering 2024 – Present
  Northeastern University Shenyang, China
• B.Eng. in Measurement and Control Technology and Instrument 2020 – 2024
  Guilin University of Electronic Technology Guilin, China