Xiao An   |   安潇🧑‍🚀

I am a Ph.D. student at the State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing (LIESMARS), Wuhan University. I am a member of the EarthVision and Application (EVA) Group, advised by Prof. Wei He.

My research focuses on foundation models and large vision-language models for remote sensing, with particular interests in multimodal grounding, capability evaluation, and task-specific adaptation.

Portrait of Xiao An
News

  • May 2026 Our work on multi-image grounding for remote sensing was accepted by ISPRS Journal of Photogrammetry and Remote Sensing.
  • Mar. 2026 I joined the OpenDataLab team at Shanghai Artificial Intelligence Laboratory as a research intern.
  • Sep. 2025 Our paper CHOICE was accepted by NeurIPS 2025.
  • Publications

    Selected publications. See my Google Scholar profile for the complete list.

    * Equal contribution. † Corresponding author. Highlighted entries are selected works.

    MIGRANT overview Beyond Single and Earthbound: Exploring Multi-Image Grounding in Remote Sensing with Large Vision-Language Models
    Xiao An, Chen Zhong, Jiaxing Sun, Jun Liu, Wei He†
    Code / Paper
    ISPRS JPRS 2026

    MIGRANT advances multi-image grounding for remote sensing with a dedicated instruction dataset and benchmark.

    CLIPPER overview Is One-Shot In-Context Learning Helpful for Data Selection in Task-Specific Fine-Tuning of Multimodal LLMs?
    Xiao An, Jiaxing Sun, Ting Hu, Wei He†
    Paper
    ICME 2026 (Oral)

    CLIPPER uses one-shot in-context learning for efficient, training-free data selection in task-specific multimodal LLM fine-tuning.

    CHOICE benchmark overview CHOICE: Benchmarking the Remote Sensing Capabilities of Large Vision-Language Models
    Xiao An*, Jiaxing Sun*, Zihan Gui, Wei He†
    Code / Paper
    NeurIPS 2025

    CHOICE provides a hierarchical benchmark for evaluating the perception and reasoning capabilities of remote sensing VLMs.

    PIS method overview Pretrain a Remote Sensing Foundation Model by Promoting Intra-Instance Similarity
    Xiao An, Wei He†, Jiaqi Zou, Guangyi Yang, Hongyan Zhang
    Code / Paper
    IEEE TGRS 2024

    PIS pretrains remote sensing foundation models by promoting similarity among augmented views of each image instance.


    Experience
    Wuhan University logo Wuhan University
    Sep. 2026 - Present
    Integrated M.S.-Ph.D. Student (2+4 Program)
    State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing (LIESMARS)
    Shanghai Artificial Intelligence Laboratory logo Shanghai Artificial Intelligence Laboratory
    Mar. 2026 - Aug. 2026
    Research Intern
    OpenDataLab Team
    Wuhan University logo Wuhan University
    Sep. 2023 - Jun. 2026
    Undergraduate Student
    School of Electronic Information

    Service and Teaching

  • Reviewer: IEEE Transactions on Geoscience and Remote Sensing (TGRS); Conference on Neural Information Processing Systems (NeurIPS)
  • Teaching Assistant: Remote Sensing Image Processing (Undergraduate Course), Fall 2025

  • Awards and Honors

  • 2026: Oral Presentation, IEEE International Conference on Multimedia and Expo (ICME 2026)
  • 2025: Excellent Youth Oral Presentation Award, The Fifth International Forum on Big Data for Sustainable Development Goals
  • 2024: First Prize, International Graduate Workshop on Geoinformatics (IGWG 2024)
  • ✅复制完成