← Search

Ross Wightman

2 accepted papers

2023

Reproducible Scaling Laws for Contrastive Language-Image Learning

CVPR 2023poster

Scaling up neural networks has led to remarkable performance across a wide range of tasks. Moreover, performance often follows reliable scaling laws as a function of training set size, model size, and compute, which offers valuable guidance as large-scale experiments are becoming increasingly expens…

2022

LAION-5B: An open large-scale dataset for training next generation image-text models

NeurIPS 2022accept

Groundbreaking language-vision architectures like CLIP and DALL-E proved the utility of training on large amounts of noisy image-text data, without relying on expensive accurate labels used in standard vision unimodal supervised learning. The resulting models showed capabilities of strong text-guide…