MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI.
Kaining YingFanqing MengJin WangZhiqian LiHan LinYue YangHao ZhangWenbo ZhangYuqi LinShuo LiuJiayi LeiQuanfeng LuRunjian ChenPeng XuRenrui ZhangHaozhe ZhangPeng GaoYali WangYu QiaoPing LuoKaipeng ZhangWenqi ShaoPublished in: CoRR (2024)
Keyphrases
- language model
- multi task
- language modeling
- multitask learning
- multi task learning
- probabilistic model
- learning tasks
- n gram
- query expansion
- retrieval model
- speech recognition
- document retrieval
- information retrieval
- test collection
- language modelling
- learning problems
- multiple tasks
- multi class
- computer vision
- statistical language models
- feature selection
- multi modal
- transfer learning
- machine learning
- gaussian processes
- document ranking
- supervised learning
- learning experience
- audio visual
- information gain
- smoothing methods