VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks.
Wenhai WangZhe ChenXiaokang ChenJiannan WuXizhou ZhuGang ZengPing LuoTong LuJie ZhouYu QiaoJifeng DaiPublished in: CoRR (2023)
Keyphrases
- language model
- open ended
- language modeling
- n gram
- probabilistic model
- information retrieval
- learning outcomes
- document retrieval
- ad hoc information retrieval
- speech recognition
- retrieval model
- language modelling
- statistical language models
- mixture model
- context sensitive
- smoothing methods
- test collection
- relevance model
- query terms
- relevant documents
- transfer learning
- statistical machine translation
- document ranking
- error rate
- language model for information retrieval