AI engineering glossary · Generative media multimodal
What is perceiver resampler?
Perceiver resampler: A module that compresses a variable number of visual features into a fixed small set of tokens using cross-attention with learned latent queries, keeping the language model's input short. It is used in Flamingo-style models.
Perceiver resampler: an example
Frames from a video produce thousands of patch features, which the resampler reduces to 64 visual tokens.
Related terms
More Generative media multimodal terms
Where you learn it
Perceiver resampler is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.