Feature-wise Linear Modulation (FiLM)
First seen somewhere, but more recently in OpenVLA-OFT.
- Yes, Diffusion Policy seems to also use this
FiLM learns to adaptively influence the output of a neural network by applying anAffine Transformation, or FiLM, to the network’s intermediate features, based on some input.
What is conditioning?
Conditioning, in a general sense, involves adjusting a model’s behavior based on additional information. In probabilistic terms, it’s akin to computing the probability of an event given some known context.
2000+ citations
Links:
How does FILM conditioning work?
Related
- CLIP
- There’s also Frame Interpolation for Large Motion which is also long for FiLM, but that’s probs not what you are looking for