// ◉ Multimodal & Vision

Flamingo

Inserts cross-attention into a frozen LLM to read interleaved images and text.

Flamingo 交错图文模型 2022 Advanced extended

IN PLAIN WORDS

A Perceiver resampler turns vision features into a fixed set of tokens injected via new gated cross-attention layers into a frozen LM, enabling few-shot visual tasks.

Used in: Open replications such as Idefics

TIMELINE · prerequisites → this → what builds on it

2017 Transformer &…2021 CLIP (Contras…2022 Flamingo

01Original paper

Flamingo: a Visual Language Model for Few-Shot Learning

Jean-Baptiste Alayrac, Jeff Donahue, Pauline Luc, et al. · 2022

arXiv ↗ ✓ Verified · arXiv API

02Where it sits

Learn the left column first; the right column builds on this one.

Learn first

Flamingo

Then you can learn

Nothing in the atlas builds on it yet

Left: prerequisites · right: builds on this · dashed: related. Full map →

03Learning resources

Official docs, explainers, courses and reference code. All links checked.

Explainers

Lilian Weng：Generalized Visual Language Models ↗EN

04Where the course teaches it

U71 CLIP & Vision-Language Models Contrastive image–text pre-training, SigLIP, LLaVA-style VLMs and Flamingo. 8 h4 algorithms4 papers

For AI / data

Verification: verified, checked 2026-10-21.
JSON: /api/learn/algorithms.json (id: flamingo)