Dynamic per-epoch cluster scaling that preserves relative cluster order and upsamples the long tail cuts VLM pre-training cost and improves long-tail zero-shot accuracy.
On the de-duplication of laion-2b
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2representative citing papers
Diffusion models show distinct patterns of recognizing versus replicating culturally iconic references, with recognition linked to data frequency, textual uniqueness, popularity, and creation date rather than simple copying.
citing papers explorer
-
Dynamic Cluster Data Sampling for Efficient and Long-Tail-Aware Vision-Language Pre-training
Dynamic per-epoch cluster scaling that preserves relative cluster order and upsamples the long tail cuts VLM pre-training cost and improves long-tail zero-shot accuracy.
-
The Persistence of Cultural Memory: Investigating Multimodal Iconicity in Diffusion Models
Diffusion models show distinct patterns of recognizing versus replicating culturally iconic references, with recognition linked to data frequency, textual uniqueness, popularity, and creation date rather than simple copying.