HyperLLaVA: Dynamic Visual and Language Expert Tuning for Multimodal Large Language Models.
Wenqiao ZhangTianwei LinJiang LiuFangxun ShuHaoyuan LiLei ZhangWanggui HeHao ZhouZheqi LvHao JiangJuncheng LiSiliang TangYueting ZhuangPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- probabilistic model
- statistical language models
- context sensitive
- speech recognition
- language modelling
- n gram
- information retrieval
- document retrieval
- query expansion
- retrieval model
- natural language
- relevance model
- multi modal
- smoothing methods
- visual features
- visual information
- okapi bm
- query terms
- ad hoc information retrieval
- document ranking
- translation model
- term dependencies
- pseudo relevance feedback
- vector space model
- test collection
- bayesian networks