Groma: Localized Visual Tokenization for Grounding Multimodal Large Language Models.
Chuofan MaYi JiangJiannan WuZehuan YuanXiaojuan QiPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- n gram
- document retrieval
- speech recognition
- information retrieval
- probabilistic model
- statistical language models
- visual information
- language modelling
- query expansion
- retrieval model
- language models for information retrieval
- ad hoc information retrieval
- low level
- pseudo relevance feedback
- document ranking
- visual features
- document length
- multi modal
- multimedia
- translation model
- vector space model
- context sensitive
- relevance model
- query specific
- out of vocabulary
- query terms
- named entities
- term dependencies
- text retrieval