Boosting Multimodal Large Language Models with Visual Tokens Withdrawal for Rapid Inference.
Zhihang LinMingbao LinLuxi LinRongrong JiPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- n gram
- probabilistic model
- document retrieval
- speech recognition
- visual information
- statistical language models
- information retrieval
- retrieval model
- language modelling
- query expansion
- smoothing methods
- vector space model
- context sensitive
- query terms
- okapi bm
- test collection
- language models for information retrieval
- visual features
- multi modal
- document ranking
- ad hoc information retrieval
- bayesian networks
- translation model
- document length