Abstract: In unsupervised medical image registration, encoder-decoder architectures are widely used to predict dense, full-resolution displacement fields from paired images. Despite their popularity, ...
Abstract: Video traffic continues to surge, pushing codecs toward higher efficiency at the cost of sharply increased complexity. The H.266/Versatile Video Coding (VVC) standard roughly halves bitrate ...
Penguin-VL is a compact vision-language model family built to study how far multimodal efficiency can be pushed by redesigning the vision encoder, rather than only scaling data or model size.