Towards artificial general intelligence via a multimodal foundation model
Beijing Institute of Big Data Research · Renmin University of China · +3 more institutions
Abstract
The fundamental goal of artificial intelligence (AI) is to mimic the core cognitive activities of human. Despite tremendous success in the AI research, most of existing methods have only single-cognitive ability. To overcome this limitation and take a solid step towards artificial general intelligence (AGI), we develop a foundation model pre-trained with huge multimodal data, which can be quickly adapted for various downstream cognitive tasks. To achieve this goal, we propose to pre-train our foundation model by self-supervised learning with weak semantic correlation data crawled from the Internet and show that promising results can be obtained on a wide range of downstream tasks. Particularly, with the…
Citation impact
- FWCI
- 32.60
- Percentile
- 100%
- References
- 48
Authors
12- NFNanyi FeiCorresponding
Beijing Institute of Big Data Research, Renmin University of China
- ZLZhiwu Lu
Beijing Institute of Big Data Research, Beijing Academy of Artificial Intelligence, Renmin University of China
- YGYizhao Gao
Beijing Institute of Big Data Research, Renmin University of China
- GYGuoxing Yang
Beijing Institute of Big Data Research, Renmin University of China
- YHYuqi Huo
Beijing Institute of Big Data Research, Renmin University of China
Topics & keywords
- Computer science
- Interpretability
- Foundation (evidence)
- Artificial intelligence
- Transformative learning
- Cognition
- Artificial general intelligence