Artificial Intelligence · Computer Vision

Multimodal Vision-Language Models

A topic within Computer Vision, itself one of 11 topics in that field and part of Artificial Intelligence.

Reading on Multimodal Vision-Language Models

2 works

Paper2021

Learning Transferable Visual Models From Natural Language Supervision

Radford et al.

Trains an image encoder and a text encoder together to predict which captions match which images across 400 million pairs, producing representations (CLIP) that transfer to new visual tasks with no task-specific training.

48 pageslink checked 17 Sept 2026

Artificial Intelligence · Computer Vision

FreeAdvanced

Paper2022

Flamingo: a Visual Language Model for Few-Shot Learning

Alayrac et al.

Bridges frozen pretrained vision and language models with cross-attention layers, letting one model handle arbitrarily interleaved images and text and adapt to new vision-language tasks from a handful of examples.

66 pageslink checked 17 Sept 2026

Artificial Intelligence · Computer Vision

FreeAdvanced

Reading on Multimodal Vision-Language Models

Learning Transferable Visual Models From Natural Language Supervision

Flamingo: a Visual Language Model for Few-Shot Learning

Other topics in Computer Vision