Breaking Down the Task: A Unit-Grained Hybrid Training Framework for Vision and Language Decision Making.
Ruipu LuoJiwen ZhangZhongyu WeiPublished in: CoRR (2023)
Keyphrases
- decision making
- computer vision
- main contribution
- theoretical framework
- vision system
- decision making under uncertainty
- context dependent
- language learning
- database
- artificial intelligence
- learning algorithm
- real time
- programming language
- natural language
- online learning
- decision support
- lightweight
- reinforcement learning
- fine grained
- information retrieval