AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

VoxTell: Free-Text Promptable Universal 3D Medical Image Segmentation

Maximilian Rokuss, Moritz Langenberg, Yannick Kirchhoff, Fabian Isensee, Benjamin Hamm, Constantin Ulrich, Sebastian Regnery, Lukas Bauer, Efthimios Katsigiannopulos, Tobias Norajitra, Klaus Maier-Hein

CVPR 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Open-vocabulary alignment from VLMs · 21 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add multi-stage fusion (3 decoder stages) instead of single-stage late fusion (ablation)VoxTell · Validation splitDice: 55.11 -> 60.16Improved
increase fusion stages from 3 to 5 (ablation)VoxTell · Validation splitDice: 60.16 -> 61.54Improved
add deep supervision across decoder stages (ablation)VoxTell · Validation splitDice: 61.54 -> 62.55Improved
scale training batch size from 2 to 128 (ablation)VoxTell · Validation splitDice: 62.55 -> 69.43Improved
use MaskFormer-style fusion (SAT) instead of Mask2Former (ablation)single-stage fusion baselines · Validation splitDice: 51.68 -> 55.11Improved
use VoxTell instead of SAT on report-derived promptsVoxTell vs SAT · In-house SBRT lung tumor cohortDice: 0.0 -> 50.2Improved
use VoxTell multi-stage fusion instead of SAT single-stage after fine-tuningVoxTell vs SAT · ReXGroundingCT validationDice: 13.1 -> 28.2Improved
use VoxTell instead of SAT on hit rateVoxTell vs SAT · ReXGroundingCT validationHIT5%: 49.8 -> 67.8Improved
Qwen3-Embedding-4B text encoder instead of SAT's original encoder (ablation)SAT · Validation splitDiceImproved

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