the open
    research
    Contribute
    Back to the reading lists

    Computer vision & multimodal· 2023

    Improved Baselines with Visual Instruction Tuning

    Haotian Liu (first author) · 2023

    Read the original

    DOI 10.1109/cvpr52733.2024.02484arXiv 2310.03744OpenAlex W4402727764

    On the reading lists

    Why it matters

    Demonstrated surprisingly strong multimodal performance with simple MLP connectors and curated instructions.

    Condensed from the expert lists' notes.

    The record

    First released
    2023 (from arXiv 2310.03744)
    Citations
    6,015 citations, as counted by Papers With Code (CC BY-SA 4.0)
    Named by
    both expert lists
    Score
    0.387 · computed rank 387 · consensus 0.34, must-read 0, citations percentile 0.815 (2020s · vision), awards 0, existing lists 0. Method

    Data sources

    Catalogue data from OpenAlex (CC0), Crossref (CC0 metadata; no abstracts are shown), arXiv, and Papers With Code (CC BY-SA 4.0). Each count names its source. See the method.