MedVol-R1 is an RL framework that decouples 2D evidence grounding from 3D mask generation for volumetric reasoning segmentation and reports SOTA results on M3D-Seg benchmarks.
arXiv preprint arXiv:2508.08177 (2025)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
MedVeriSeg is a training-free framework that analyzes similarity maps from the [SEG] token and uses GPT-4o to verify whether a segmentation query targets an object actually present in a medical image.
citing papers explorer
-
MedVol-R1: Reward-Driven Evidence Grounding for Volumetric Reasoning Segmentation
MedVol-R1 is an RL framework that decouples 2D evidence grounding from 3D mask generation for volumetric reasoning segmentation and reports SOTA results on M3D-Seg benchmarks.
-
MedVeriSeg: Teaching MLLM-Based Medical Segmentation Models to Verify Query Validity Without Extra Training
MedVeriSeg is a training-free framework that analyzes similarity maps from the [SEG] token and uses GPT-4o to verify whether a segmentation query targets an object actually present in a medical image.