LAION-5B is an openly released dataset of 5.85 billion CLIP-filtered image-text pairs that enables replication of foundational vision-language models.
Learning robust global repre- sentations by penalizing local predictive power
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2representative citing papers
Hybrid JEMs at intermediate generative-discriminative balance maximize human alignment on perceptual similarity, gloss, uncertainty, robustness, cue conflict, and feature attribution benchmarks.
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.
-
Not Too Generative, Not Too Discriminative: The Human Alignment Sweet Spot
Hybrid JEMs at intermediate generative-discriminative balance maximize human alignment on perceptual similarity, gloss, uncertainty, robustness, cue conflict, and feature attribution benchmarks.