Skip to main content
Search

# Visual Harness

1 related articles

Subscribe to updates
  1. arXiv

    General vision-language models skip medical retraining: VERA visual harness lifts spleen measurement from 63.3% to 98.3%

    VERA is a medical visual harness for general vision-language models that supplies interactive image tools, lossless evidence memory and evidence verification at inference time, so the model inspects images repeatedly and revises its answer. Across 11 tasks and four imaging modalities, the Qwen3.8-27B backbone improves on every task, with spleen measurement rising from 63.3% to 98.3% and pulmonary nodule detection from 0.0% to 28.2%. Stronger API-based models gain more with VERA, and GPT-6.1 Sol raises pulmonary nodule detection from 10.8% to 69.2%.

You’re all caught up