LAION-5B is an openly released dataset of 5.85 billion CLIP-filtered image-text pairs that enables replication of foundational vision-language models.
General facial representa- tion learning in a visual-linguistic manner
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
PercHead achieves state-of-the-art single-image 3D head reconstruction and editing by replacing low-level losses with a perceptual loss from DINOv2 and SAM 2.1 inside a Vision Transformer architecture.
GraphPL combines GNNs with patchwork learning to integrate all observed modalities for unsupervised imputation, achieving SOTA results on benchmarks and enabling disease prediction on real EHR data.
citing papers explorer
-
LAION-5B: An open large-scale dataset for training next generation image-text models
LAION-5B is an openly released dataset of 5.85 billion CLIP-filtered image-text pairs that enables replication of foundational vision-language models.