Multimodal LLMs act as training-free similarity estimators for instance-level image retrieval by converting next-token probabilities from image-pair prompts into scores, combined with efficient indexing for scalability.
VLM2Vec: Training vision- language models for massive multimodal embedding tasks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Indexing Multimodal Language Models for Large-scale Image Retrieval
Multimodal LLMs act as training-free similarity estimators for instance-level image retrieval by converting next-token probabilities from image-pair prompts into scores, combined with efficient indexing for scalability.