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: NeurIPS (2023)
Keyphrases
- language model
- open ended
- language modeling
- n gram
- document retrieval
- speech recognition
- information retrieval
- query expansion
- probabilistic model
- retrieval model
- learning outcomes
- mixture model
- context sensitive
- test collection
- ad hoc information retrieval
- statistical language models
- smoothing methods
- query terms
- language modelling
- vector space model
- document ranking
- translation model
- word error rate
- language model for information retrieval
- document length
- statistical machine translation
- text categorization
- bayesian networks