跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 7 天前AI 評分41

MedJev:實現快速醫學影像理解的單次視覺語言決策模型

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

AI 導讀

MedJev 將醫學影像、問題及候選答案直接映射為決策,無需自回歸生成,在單次多模態前向傳遞中完成判斷。基於 Qwen3.5-4B 的 MedJev-4B,在四項醫學影像分類及視覺問答基準上,準確率絕對提升 7.93%,端到端速度提升 6.04 倍;與 20 個模型比較,在 4B–9B 通用及醫學 VLM 中取得最先進的效能及推理速度。

正文

Abstract

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 latency and decision errors. To this end, we introduce MedJev, a system one vision-language decision model that maps medical images, questions, and candidate answers directly to decisions in a single multimodal forward pass, without any autoregressive generation process. For fast inference, MedJev removes the upper language layers and the generative output pathway, while keeping the full vision pathway and all visual tokens. On this shortened backbone, a decision head scores each candidate by pretrained query--key matching and refines the scores with a lightweight multilayer perceptron (MLP) residual, coupling the pretrained matching structure with task-specific nonlinear discrimination. Built on Qwen3.5-4B, MedJev-4B improves both accuracy and speed over the original model on each of four medical image classification and visual question answering benchmarks, with an absolute accuracy gain of 7.93\% and a 6.04times end-to-end speedup. Further comparison with 20 cutting-edge models shows that MedJev-4B achieves state-of-the-art performance and inference speed among 4B--9B general and medical VLMs, indicating that direct multimodal decision making is an effective route to fast and effective medical image understanding.

View arXiv page View PDF GitHub Add to collection

Get this paper in your agent:

hf papers read 2611.20992

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2611.20992 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2611.20992 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2611.20992 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co