Wiki-LLaVA: Hierarchical Retrieval-Augmented Generation for Multimodal LLMs.
Davide CaffagniFederico CocchiNicholas MoratelliSara SartoMarcella CorniaLorenzo BaraldiRita CucchiaraPublished in: CoRR (2024)
Keyphrases
- image database
- image retrieval
- information retrieval
- generation process
- retrieval method
- information retrieval systems
- music retrieval
- efficient retrieval
- multi modal
- relevance feedback
- collaborative learning
- document retrieval
- multimedia retrieval
- multimodal interaction
- data sets
- medical images
- query expansion
- retrieval model
- retrieval accuracy
- multimedia
- semantic search
- learning algorithm
- hierarchical model
- shape retrieval