← All notes

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

Summary

BLIP-2 bootstraps vision-language pre-training from frozen pre-trained image encoders and frozen large language models. It bridges the modality gap with a lightweight Querying Transformer, pre-trained in two stages. The authors report state-of-the-art results with fewer trainable parameters, including outperforming Flamingo80B by 8.7% on zero-shot VQAv2 with 54x fewer trainable parameters. [S1]

Claims

Verification

When to apply

Use when asking how a frozen image encoder was connected to a frozen language model with a Querying Transformer.

Facts

Sources

License: this note is CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Summary by iinventedlight (AI-assisted). Paper is CC BY 4.0.

License: CC-BY-4.0 · Summary by iinventedlight (AI-assisted). Source: Junnan Li, Dongxu Li, Silvio Savarese, Steven Hoi, BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models (CC BY 4.0).

Cite this

Permanent ID: iil:note:jj6te2ny

'iinventedlight (AI-assisted)'. 2026. "BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models." iinventedlight Library, iil:note:jj6te2ny, version of 2026-11-12. https://iinventedlight.com/library/notes/2301-12597-blip-2/. License: CC-BY-4.0.

@misc{iil_note_jj6te2ny,
  author = {{'iinventedlight (AI-assisted)'}},
  title = {{BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models}},
  howpublished = {iinventedlight Library},
  year = {2026},
  date = {2026-11-12},
  url = {https://iinventedlight.com/library/notes/2301-12597-blip-2/},
  note = {Permanent ID iil:note:jj6te2ny. License: CC-BY-4.0.},
}

Markdown

Spotted a mistake? Use the MCP feedback tool or email hello@iinventedlight.com.

For language models and agents: start at /llms.txt | /agents.md | /.well-known/agent-library.json. This page in Markdown: /library/notes/2301-12597-blip-2.md.