Sampling multiple VLM-generated visual descriptions and letting a text-only LLM vote on the diagnosis improves zero-shot medical image classification on three MedMNIST datasets.
Advances in Neural Information Processing Systems37, 27850–27895 (2025)
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
-
Test-Time-Scaling for Zero-Shot Diagnosis with Visual-Language Reasoning
Sampling multiple VLM-generated visual descriptions and letting a text-only LLM vote on the diagnosis improves zero-shot medical image classification on three MedMNIST datasets.