# Beyond Discrete Tokens: Preserving Numerical Continuity in Medical Vision-Language Models

Source: [arXiv](https://arxiv.org/abs/2610.32948v1)  
Feed7 permalink: https://feed7.dev/p/2610-32948v1-0hbava6  
Published: 2026-10-23T17:40:58.000Z  
Trust: Needs Review (needs_review)

## Why Included

HAD-VLM combines text generation with diffusion-based continuous predictions for medical image measurements. On evaluated ultrasound and X-ray tasks, it reduced measurement error against the reported baselines.

## Source Summary

HAD-VLM pairs autoregressive text generation with diffusion-based prediction of measurement coordinates and lengths. Across four echocardiographic tasks, it reported **21.4–37.6% lower error** than a Vicuna-based autoregressive baseline; for X-ray vertebral measurement, error fell from **11.4 to 6.7 pixels**.

## Practical Implication

For builders handling images with precise numeric outputs, the paper is an example of separating language generation from continuous measurement prediction while sharing a model backbone. It also reports that medical question-answering performance was preserved on the evaluated dataset.

## Agent-Ready Context

HAD-VLM pairs autoregressive text generation with diffusion-based prediction of measurement coordinates and lengths. Across four echocardiographic tasks, it reported **21.4–37.6% lower error** than a Vicuna-based autoregressive baseline; for X-ray vertebral measurement, error fell from **11.4 to 6.7 pixels**.

For builders handling images with precise numeric outputs, the paper is an example of separating language generation from continuous measurement prediction while sharing a model backbone. It also reports that medical question-answering performance was preserved on the evaluated dataset.

The findings cover specific medical image tasks and datasets. The abstract does not establish performance beyond those evaluations or provide deployment details.

## Connected Context

Feed7 judgment across 910 accumulated Signals:

This narrows multimodal medical measurement toward a split output design: language remains autoregressive while coordinates and lengths use diffusion, with gains reported on the evaluated tasks. It complements broader medical image understanding work with a specific approach to continuous measurements; the evidence does not establish performance beyond those datasets.

- [ClinFusion: A Vision-Centric Multimodal LLM System for Holistic Medical Understanding](https://feed7.dev/p/2607-24743v1-15vx95s) — Both address medical image models, but ClinFusion focuses on holistic 2D and 3D understanding while HAD-VLM separates precise continuous measurement from text generation.

## Context Map

- Layer: model
- Domains: image, research
- Topics: None

## Uncertainty

- The findings cover specific medical image tasks and datasets. The abstract does not establish performance beyond those evaluations or provide deployment details.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.