the open
    research
    Contribute
    Back to the reading lists

    Computer vision & multimodal· 2023

    BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models

    Junnan Li (first author) · 2023

    Read the original

    arXiv 2301.12597OpenAlex W4318718936

    On the reading lists

    Why it matters

    Established the Q-Former approach for efficiently connecting frozen vision encoders and LLMs.

    Condensed from the expert lists' notes.

    The record

    First released
    2023 (from arXiv 2301.12597)
    Citations
    9,535 citations, as counted by Papers With Code (CC BY-SA 4.0)
    Named by
    both expert lists
    Score
    0.630 · computed rank 125 · consensus 0.91, must-read 0.5, citations percentile 0.877 (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.