u-LLaVA: Unifying Multi-Modal Tasks via Large Language Model.
Jinjin XuLiwu XuYuzhe YangXiang LiYanchun XieYi-Jie HuangYaqian LiPublished in: CoRR (2023)
Keyphrases
- multi modal
- language model
- language modeling
- n gram
- probabilistic model
- speech recognition
- information retrieval
- document retrieval
- query expansion
- multi modality
- retrieval model
- test collection
- language modelling
- video search
- ad hoc information retrieval
- statistical language models
- mixture model
- uni modal
- cross modal
- pseudo relevance feedback
- context sensitive
- high dimensional
- relevance model
- audio visual
- text classification
- feature space