LLaVA-φ: Efficient Multi-Modal Assistant with Small Language Model.
Yichen ZhuMinjie ZhuNing LiuZhicai OuXiaofeng MouJian TangPublished in: CoRR (2024)
Keyphrases
- multi modal
- language model
- language modeling
- probabilistic model
- information retrieval
- language modelling
- document retrieval
- n gram
- query expansion
- audio visual
- multi modality
- high dimensional
- speech recognition
- cross modal
- mixture model
- image annotation
- statistical language models
- context sensitive
- statistical machine translation
- pseudo relevance feedback
- retrieval model
- ad hoc information retrieval
- uni modal
- image segmentation
- document length
- test collection
- information retrieval systems
- relevance model
- language model for information retrieval