🏢 Apple

STIV: A novel, scalable method for text and image-conditioned video generation, systematically improving model architectures, training, and data curation for superior performance.

Cut Cross-Entropy (CCE) dramatically reduces the memory footprint of training large language models by cleverly computing the cross-entropy loss without materializing the full logit matrix.

Steering large language and diffusion models is made easy and efficient via Activation Transport (ACT)! This novel framework uses optimal transport theory to precisely control model activations, leadi…