A compact VLM fine-tuned on Gemini-generated quality scores can filter image-caption pairs, yielding data with higher CLIP alignment, lower perplexity, and higher Gemini-judged captioning preference.
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
-
Trust the Model: Compact VLMs as In-Context Judges for Image-Text Data Quality
A compact VLM fine-tuned on Gemini-generated quality scores can filter image-caption pairs, yielding data with higher CLIP alignment, lower perplexity, and higher Gemini-judged captioning preference.