Do a bit.
ProductsResearchWritingContact

Research.

I work at the intersection of HCI, visualization, and AI agents — using interaction and visualization to help people communicate information more clearly, and more beautifully.

  • IGenBench
    ACL 2026Website

    IGenBench

    Benchmarking how reliably text-to-infographic models reproduce the data they're given.

  • ViviDoc
    ACL 2026 DemoWebsite

    ViviDoc

    Generating interactive documents through human-agent collaboration.

  • DataLab
    ICDE 2025

    DataLab

    A unified platform that lets non-technical users query and visualize their data through an LLM.

  • Multimodal Prompt for Visualization
    arXiv 2025

    Multimodal Prompt for Visualization

    Authoring data visualizations by sketching and pointing — multimodal prompts for LLMs.

  • VIS-Shepherd
    arXiv 2025

    VIS-Shepherd

    A critic model that catches mistakes in LLM-generated data visualizations.

  • SCORPIO
    arXiv 2025

    SCORPIO

    Serving the right LLM-inference requests at the right time for heterogeneous SLOs.

  • DLRover-RM
    VLDB 2024

    DLRover-RM

    Cutting cloud cost for deep recommendation model training by reusing resources across jobs.

  • MixLoRA
    arXiv 2024

    MixLoRA

    Fine-tuning LLMs more efficiently by routing through a mixture of LoRA experts.

← back home

BuBu.
Yinghao Tang

Researcher and builder. I make things so people fight their tools less, and live their lives more.

ExploreProductsWritingContact
© 2026 · BuBuless friction, more life.