Why do LLaVA Vision-Language Models Reply to Images in English?
Musashi HinckCarolin HoltermannMatthew Lyle OlsonFlorian SchneiderSungduk YuAnahita BhiwandiwallaAnne LauscherShao-Yen TsengVasudev LalPublished in: CoRR (2024)
Keyphrases
- language model
- image database
- image features
- statistical language models
- language modeling
- image understanding
- probabilistic model
- document retrieval
- n gram
- retrieval model
- language model for information retrieval
- computer vision
- image classification
- image retrieval
- natural language
- cross language retrieval
- information retrieval
- query expansion
- machine translation
- vector space model
- translation model
- language models for information retrieval
- spoken term detection