Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward.
Ruohong ZhangLiangke GuiZhiqing SunYihao FengKeyang XuYuanhan ZhangDi FuChunyuan LiAlexander HauptmannYonatan BiskYiming YangPublished in: CoRR (2024)
Keyphrases
- language model
- probabilistic model
- language modeling
- smoothing methods
- n gram
- speech recognition
- language modelling
- document retrieval
- translation model
- information retrieval
- statistical language models
- retrieval model
- statistical language modeling
- mixture model
- test collection
- multimedia
- language models for information retrieval
- dependency structure
- statistical models
- relevance model
- document ranking
- pseudo relevance feedback
- text classification
- image retrieval
- bayesian networks
- feature selection