A multimodal embedding model trained on 560K GPT-4o-synthesized examples, covering 93 languages and 7 modality combinations, reaches top average scores on MMEB and XTD.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data
A multimodal embedding model trained on 560K GPT-4o-synthesized examples, covering 93 languages and 7 modality combinations, reaches top average scores on MMEB and XTD.