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.
Abstract: Audio and vision are two main modalities in video data. Multimodal learning, especially for audiovisual learning, has drawn considerable attention recently, which can boost the performance ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results