Retrieval-selected demonstration examples let a multimodal LLM classify images as accurately as random many-shot prompting with far fewer examples.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Visual RAG: Expanding MLLM visual knowledge without fine-tuning
Retrieval-selected demonstration examples let a multimodal LLM classify images as accurately as random many-shot prompting with far fewer examples.