Sun Sep 18 2022
Wed Sep 14 2022

PaLI: A Jointly-Scaled Multilingual Language-Image Model

Artificial Intelligence
Language and Vision Models
Multilingual image-text analysis
Visual question-answering
Scene-text understanding

Trains a 17B ViT on a multilingual image-text dataset containing 10B images and texts in over 100 languages and achieves SotA perf in multiple vision and language tasks.

This joint scaling approach provides a simple, modular, and scalable design for improving vision, language, and multimodal tasks in multiple languages. It can benefit businesses with multilingual operations that require image-text analysis and processing.

Revisiting Neural Scaling Laws in Language and Vision

Artificial Intelligence
Scaling of Deep Learning Models
Image classification
Neural machine translation
Language modeling

Presents a recipe for estimating scaling law parameters reliably from learning curves and shows that it extrapolates more accurately than previous methods in various settings.

This methodology for estimating scaling law parameters can help businesses determine the appropriate size of their neural models for specific tasks, resulting in more efficient and effective training.

Sun Sep 11 2022
Thu Sep 01 2022
Tue Aug 30 2022
Sun Aug 28 2022