AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

MedVTok: A General-Purpose Medical Visual Tokenizer

Chenglong Ma, Yuanfeng Ji, Junzhi Ning, Jiyao Liu, Yujie Wei, Shaohao Rui, Chaoyang Zhang, Wenjie Li, Wenhao Tang, Cheng Tang, Wei Li, Shujian Gao and 9 more

NeurIPS 2026 · Vision-language and multimodal › Human and embodied modeling · approach: Medical vision-language models · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Introduces MedVTok, a general-purpose visual tokenizer intended to map 2D medical images and 3D volumes into a shared token interface for multimodal medical AI.

Problem

Existing medical visual tokenizers are tied to a specific dimensionality (2D or 3D) and imaging modality, so multimodal medical systems rely on fragmented, poorly reusable representations.

Approach

A single visual tokenizer that unifies 2D images and 3D volumes across imaging modalities into a common visual interface for patient condition modeling. Only the abstract was available, so the specific mechanism is not stated.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add multi-expert shared-space alignment instead of a single expert (MedImageInsight) (ablation)MedVTok (stage 1, 3M images) · classification and segmentationaccuracy / DiceImproved
add shared-space contrastive alignment with a single expert (ablation)MedVTok (stage 1, 3M images) · classification and segmentationaccuracy / DiceImproved
add expert-space complementary alignment L_expert (ablation)MedVTok (stage 1, 3M images) · classificationaccuracy: +1.53%Improved
replace attention pooling with mean pooling plus linear layer (ablation)MedVTok aggregation head · segmentation and classificationDice / accuracyImproved
scale training data from 3M to 28M images (ablation)MedVTok · downstream tasksclassification and segmentationImproved
add slice differential regularization (SliDR) (ablation)MedVTok stage 2 · 3D reconstructionPSNR / SSIMImproved
align to multiple experts instead of text-supervised semantic encoder (no image-text pairs)MedVTok vs MedITok · VQA average (LLaVA-Med)accuracy (%): 45.39 -> 46.48Improved
use MedVTok tokens instead of MedITok tokensLaMed report generation · AMOS-MM GREEN avgGREEN: 0.386 -> 0.413Improved
MedVTok vs specialist expert on pathologyMedVTok · Pathology classification and segmentationaccuracy / Dice: Dice 77.74 vs Conch 83.77Hurt
MedVTok vs MedSigLIP on pathology and X-ray segmentationMedVTok · Linear segmentationDice: X-ray 61.13 vs 62.48Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy