Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequences.
Xiyao WangYuhang ZhouXiaoyu LiuHongjin LuYuancheng XuFeihong HeJaehong YoonTaixi LuGedas BertasiusMohit BansalHuaxiu YaoFurong HuangPublished in: CoRR (2024)
Keyphrases
- language model
- image sequences
- language modeling
- n gram
- document retrieval
- probabilistic model
- retrieval model
- multi modal
- speech recognition
- information retrieval
- query expansion
- test collection
- ad hoc information retrieval
- language modelling
- smoothing methods
- statistical language models
- computer vision
- translation model
- mixture model
- context sensitive
- word error rate
- statistical machine translation
- dirichlet prior
- language model for information retrieval
- document length
- document ranking
- vector space model
- query terms
- multimedia