# MedJev: A System One Vision-Language Decision Model for Fast and Effective Medical Image Understanding

> Source: <https://aiflash.com/news/153495/>
> Published: 2026-11-18 03:00:23+00:00

**Key takeaway:** MedJev replaces autoregressive reasoning and answer-token generation with a System One decision model, so inference cost no longer scales with response length and answers need not be parsed from free-form text.

Medical image understanding with vision-language models (VLMs) typically relies on autoregressively generating reasoning and answer tokens. These unnecessary tokens make the inference cost scale with the response length and force the answer to be parsed from free-form text, incurring avoidable laten
