MILS uses an LLM plus a pretrained scorer in an iterative generate-score-refine loop to produce competitive zero-shot captions and improved text-to-image prompts without training.
Improving image generation with better captions
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
-
LLMs can see and hear without any training
MILS uses an LLM plus a pretrained scorer in an iterative generate-score-refine loop to produce competitive zero-shot captions and improved text-to-image prompts without training.