Cover Image

Med-R2: An Adversarial Benchmark for Evidence-Grounded Reasoning in Medical VLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ma, Wen, Niu, Fucheng, Fan, Zhiting, Xiao, Zikai, Liu, Jiaxiang, Liu, Zuozhu
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

HICT: High-precision 3D CBCT reconstruction from a single X-ray
by: Ma, Wen, et al.
Published: (2026)

MedCoT: Medical Chain of Thought via Hierarchical Expert
by: Liu, Jiaxiang, et al.
Published: (2024)

MedThink: Explaining Medical Visual Question Answering via Multimodal Decision-Making Rationale
by: Gai, Xiaotang, et al.
Published: (2024)

Med-GLIP: Advancing Medical Language-Image Pre-training with Large-scale Grounded Dataset
by: Deng, Ziye, et al.
Published: (2025)

R-LLaVA: Improving Med-VQA Understanding through Visual Region of Interest
by: Chen, Xupeng, et al.
Published: (2024)

PX2Tooth: Reconstructing the 3D Point Cloud Teeth from a Single Panoramic X-ray
by: Ma, Wen, et al.
Published: (2024)

3D-RAD: A Comprehensive 3D Radiology Med-VQA Dataset with Multi-Temporal Analysis and Diverse Diagnostic Tasks
by: Gai, Xiaotang, et al.
Published: (2025)

MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning
by: Pan, Jiazhen, et al.
Published: (2025)

MedSG-Bench: A Benchmark for Medical Image Sequences Grounding
by: Yue, Jingkun, et al.
Published: (2025)

Fair-MoE: Fairness-Oriented Mixture of Experts in Vision-Language Models
by: Wang, Peiran, et al.
Published: (2025)

KPL: Training-Free Medical Knowledge Mining of Vision-Language Models
by: Liu, Jiaxiang, et al.
Published: (2025)

MedConcept: Unsupervised Concept Discovery for Interpretability in Medical VLMs
by: Haque, Md Rakibul, et al.
Published: (2026)

SurgBench: A Unified Large-Scale Benchmark for Surgical Video Analysis
by: Wei, Jianhui, et al.
Published: (2025)

Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Models
by: Jiang, Songtao, et al.
Published: (2024)

MedProbeBench: Systematic Benchmarking at Deep Evidence Integration for Expert-level Medical Guideline
by: Liu, Jiyao, et al.
Published: (2026)

MedVol-R1: Reward-Driven Evidence Grounding for Volumetric Reasoning Segmentation
by: Wang, Zichun, et al.
Published: (2026)

MedSeg-R: Medical Image Segmentation with Clinical Reasoning
by: Shao, Hao, et al.
Published: (2025)

MedVLThinker: Simple Baselines for Multimodal Medical Reasoning
by: Huang, Xiaoke, et al.
Published: (2025)

Med-CMR: A Fine-Grained Benchmark Integrating Visual Evidence and Clinical Logic for Medical Complex Multimodal Reasoning
by: Gong, Haozhen, et al.
Published: (2025)

How Auxiliary Reasoning Unleashes GUI Grounding in VLMs
by: Li, Weiming, et al.
Published: (2025)

MedGround: Bridging the Evidence Gap in Medical Vision-Language Models with Verified Grounding Data
by: Zhang, Mengmeng, et al.
Published: (2026)

CXR-ContraBench: Benchmarking Negated-Option Attraction in Medical VLMs
by: Fang, Zhengru, et al.
Published: (2026)

Datasets and Recipes for Video Temporal Grounding via Reinforcement Learning
by: Chen, Ruizhe, et al.
Published: (2025)

MedAD-R1: Eliciting Consistent Reasoning in Interpretible Medical Anomaly Detection via Consistency-Reinforced Policy Optimization
by: Zhang, Haitao, et al.
Published: (2026)

Self-Calibrated Consistency can Fight Back for Adversarial Robustness in Vision-Language Models
by: Liu, Jiaxiang, et al.
Published: (2025)

MedGround-R1: Advancing Medical Image Grounding via Spatial-Semantic Rewarded Group Relative Policy Optimization
by: Xu, Huihui, et al.
Published: (2025)

DDX-TRACE: A Benchmark for Medical Diagnostic Trajectories in VLMs
by: Pan, Jiazhen, et al.
Published: (2026)

Modest-Align: Data-Efficient Alignment for Vision-Language Models
by: Liu, Jiaxiang, et al.
Published: (2025)

Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language Models
by: Lai, Yuxiang, et al.
Published: (2025)

MedSeg-R: Reasoning Segmentation in Medical Images with Multimodal Large Language Models
by: Huang, Yu, et al.
Published: (2025)

MedFrameQA: A Multi-Image Medical VQA Benchmark for Clinical Reasoning
by: Yu, Suhao, et al.
Published: (2025)

MedQ-Deg: A Multidimensional Benchmark for Evaluating MLLMs Across Medical Image Quality Degradations
by: Liu, Jiyao, et al.
Published: (2026)

MedFact-R1: Towards Factual Medical Reasoning via Pseudo-Label Augmentation
by: Li, Gengliang, et al.
Published: (2025)

Anatomical Region-Guided Contrastive Decoding: A Plug-and-Play Strategy for Mitigating Hallucinations in Medical VLMs
by: Liang, Xiao, et al.
Published: (2025)

MedObvious: Exposing the Medical Moravec's Paradox in VLMs via Clinical Triage
by: Khan, Ufaq, et al.
Published: (2026)

PRS-Med: Position Reasoning Segmentation in Medical Imaging
by: Trinh, Quoc-Huy, et al.
Published: (2025)

MedLoc-R1: Performance-Aware Curriculum Reward Scheduling for GRPO-Based Medical Visual Grounding
by: Yang, Guangjing, et al.
Published: (2026)

Probing the Reliability of Driving VLMs: From Inconsistent Responses to Grounded Temporal Reasoning
by: Chang, Chun-Peng, et al.
Published: (2026)

Benchmarking VLMs' Reasoning About Persuasive Atypical Images
by: Malakouti, Sina, et al.
Published: (2024)

Thinking with Gaze: Sequential Eye-Tracking as Visual Reasoning Supervision for Medical VLMs
by: Li, Yiwei, et al.
Published: (2026)