VL-GPT: A Generative Pre-trained Transformer for Vision and Language Understanding and Generation.
Jinguo ZhuXiaohan DingYixiao GeYuying GeSijie ZhaoHengshuang ZhaoXiaohua WangYing ShanPublished in: CoRR (2023)
Keyphrases
- language understanding
- pre trained
- natural language understanding
- language processing
- computer vision
- training data
- generative model
- spoken dialogue systems
- vision system
- dialogue system
- semantic interpretation
- fuzzy logic
- knowledge representation
- training examples
- natural language
- learning algorithm
- training set
- information retrieval
- general knowledge
- small number
- neural network
- feature selection
- data mining