Open Models Almanac
Methodsmodel architecturemultimodal architecture

single mention · model architecture

FiLM

FiLM conditions a network on an auxiliary input such as language by modulating its hidden features.1 Learned per-block projectors scale and shift feature maps globally across spatial dimensions, letting different blocks learn different modulation patterns.2

How this definition was written

Summarised by glm-5.3-flash from 1 source; every sentence is checked against the quote it cites.

  1. project language embeddings to obtain and are implemented as simple affine transformations — Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
  2. entire feature maps are scaled and shifted by individual elements of and — Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success

Filed under model architecture › multimodal architecture