Can MLLMs Perceive and Describe Medical Image Quality Beyond Scores?
cs.CV
Submitted: 2025-10-02
Updated: 2026-10-31
Comments: EMNLP 2026 Outstanding paper award
DOI: 10.18653/2026.emnlp-main.1129
Code: https://github.com/liujiyaoFDU/MedQBench
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- IQAGPT: Image Quality Assessment with Vision-language and ChatGPT Models
- Emerging Properties in Unified Multimodal Pretraining
- Mistral 7B
- Ultrasound-QBench: Can LLMs Aid in Quality Assessment of Ultrasound Imaging?
- GPT-4 Technical Report
- A Multiband T-Shaped Antenna Array for 6G Mobile Communication
- Gemini: A Family of Highly Capable Multimodal Models
- Magnitude homology and homotopy type of metric fibrations
- GMAI-VL-R1: Harnessing Reinforcement Learning for Multimodal Medical Reasoning
- Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
- Probing out-of-distribution generalization in machine learning for materials
- Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model
- MedGround-R1: Advancing Medical Image Grounding via Spatial-Semantic Rewarded Group Relative Policy Optimization
- MedIQA: A Scalable Foundation Model for Prompt-Driven Medical Image Quality Assessment
- SA-Med2D-20M Dataset: Segment Anything in 2D Medical Imaging with 20 Million masks
- fastMRI: An Open Dataset and Benchmarks for Accelerated MRI
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs