Imagen de Portada

Unveiling and Bridging the Functional Perception Gap in MLLMs: Atomic Visual Alignment and Hierarchical Evaluation via PET-Bench

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ye, Zanting, Niu, Xiaolong, Wu, Xuanbin, Han, Xu, Liu, Shengyuan, Hao, Jing, Peng, Zhihao, Sun, Hao, Lv, Jieqin, Wang, Fanghu, Huang, Yanchao, Wu, Hubing, Yuan, Yixuan, Zaidi, Habib, Rahmim, Arman, Zheng, Yefeng, Lu, Lijun
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Self is the Best Learner: CT-free Ultra-Low-Dose PET Organ Segmentation via Collaborating Denoising and Segmentation Learning
por: Ye, Zanting, et al.
Publicado: (2025)

MDAA-Diff: CT-Guided Multi-Dose Adaptive Attention Diffusion Model for PET Denoising
por: Niu, Xiaolong, et al.
Publicado: (2025)

Segmentation-Free Outcome Prediction from Head and Neck Cancer PET/CT Images: Deep Learning-Based Feature Extraction from Multi-Angle Maximum Intensity Projections (MA-MIPs)
por: Toosi, Amirhosein, et al.
Publicado: (2024)

Semi-KAN: KAN Provides an Effective Representation for Semi-Supervised Learning in Medical Image Segmentation
por: Ye, Zanting, et al.
Publicado: (2025)

Topology-Guided Biomechanical Profiling: A White-Box Framework for Opportunistic Screening of Spinal Instability on Routine CT
por: Ye, Zanting, et al.
Publicado: (2026)

IgCONDA-PET: Weakly-Supervised PET Anomaly Detection using Implicitly-Guided Attention-Conditional Counterfactual Diffusion Modeling -- a Multi-Center, Multi-Cancer, and Multi-Tracer Study
por: Ahamed, Shadab, et al.
Publicado: (2024)

OmniBrainBench: A Comprehensive Multimodal Benchmark for Brain Imaging Analysis Across Multi-stage Clinical Tasks
por: Peng, Zhihao, et al.
Publicado: (2025)

PSMA PET/CT as a predictive tool for sub-regional importance estimates in the parotid gland
por: Sample, Caleb, et al.
Publicado: (2023)

Beyond Conventional Parametric Modeling: Data-Driven Framework for Estimation and Prediction of Time Activity Curves in Dynamic PET Imaging
por: Zakariaei, Niloufar, et al.
Publicado: (2024)

MedPruner: Training-Free Hierarchical Token Pruning for Efficient 3D Medical Image Understanding in Vision-Language Models
por: Liu, Shengyuan, et al.
Publicado: (2026)

Towards Routine AI-Based PET/CT and SPECT/CT Lesion Segmentation and Tracking in PSMA Theranostics
por: Yousefirizi, Fereshteh, et al.
Publicado: (2026)

Novel Method to Estimate Kinetic Microparameters from Dynamic Whole-Body Imaging in Regular-Axial Field-of-View PET Scanners
por: Lee, Kyung-Nam, et al.
Publicado: (2024)

Neural blind deconvolution for deblurring and supersampling PSMA PET
por: Sample, Caleb, et al.
Publicado: (2023)

What is Implementation Science; and Why It Matters for Bridging the Artificial Intelligence Innovation-to-Application Gap in Medical Imaging
por: Fayaz-Bakhsh, Ahmad, et al.
Publicado: (2025)

GeoPQA: Bridging the Visual Perception Gap in MLLMs for Geometric Reasoning
por: Chen, Guizhen, et al.
Publicado: (2025)

Development of the quantitative PET prostate phantom (Q3P) for improved quality assurance of 18F‐PSMA PET imaging in metastatic prostate cancer
por: Roberto Fedrigo, et al.
Publicado: (2024)

Impact of tracer uptake rate on quantification accuracy of myocardial blood flow in PET: A simulation study
por: Xiaotong Hong, et al.
Publicado: (2025)

Semi-supervised learning towards automated segmentation of PET images with limited annotations: Application to lymphoma patients
por: Yousefirizi, Fereshteh, et al.
Publicado: (2022)

Examining Wildlife Safeguards for Linear Infrastructure Development in India: Bridging Policy and Practice Gaps
por: Yanmei Lin, et al.
Publicado: (2025)

Characterization of artificial intelligence performance for lesion detection using synthetic lesions in PET imaging
por: Quinn de Bourbon, et al.
Publicado: (2025)

SLQ: Bridging Modalities via Shared Latent Queries for Retrieval with Frozen MLLMs
por: Lou, Haoran, et al.
Publicado: (2026)

Adaptive Voxel-Weighted Loss Using L1 Norms in Deep Neural Networks for Detection and Segmentation of Prostate Cancer Lesions in PET/CT Images
por: Dzikunu, Obed Korshie, et al.
Publicado: (2025)

Strategies for deep learning‐based attenuation and scatter correction of brain 18F‐FDG PET images in the image domain
por: Reza Jahangir, et al.
Publicado: (2024)

How to Segment in 3D Using 2D Models: Automated 3D Segmentation of Prostate Cancer Metastatic Lesions on PET Volumes Using Multi-angle Maximum Intensity Projections and Diffusion Models
por: Toosi, Amirhosein, et al.
Publicado: (2024)

StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding
por: Lin, Junming, et al.
Publicado: (2024)

Multi-Kernel Gated Decoder Adapters for Robust Multi-Task Thyroid Ultrasound under Cross-Center Shift
por: Sabouri, Maziar, et al.
Publicado: (2026)

InViC: Intent-aware Visual Cues for Medical Visual Question Answering
por: Wang, Zhisong, et al.
Publicado: (2026)

ReactBench: A Benchmark for Topological Reasoning in MLLMs on Chemical Reaction Diagrams
por: Xu, Qiang, et al.
Publicado: (2026)

Unlocking the Potential of MLLMs in Referring Expression Segmentation via a Light-weight Mask Decoder
por: Wang, Jingchao, et al.
Publicado: (2025)

EndoBench: A Comprehensive Evaluation of Multi-Modal Large Language Models for Endoscopy Analysis
por: Liu, Shengyuan, et al.
Publicado: (2025)

PunchBench: Benchmarking MLLMs in Multimodal Punchline Comprehension
por: Ouyang, Kun, et al.
Publicado: (2024)

Reusing Fusion-Time Spectral Reliability for Adaptive Fusion and Expert Routing in RGB-Infrared Object Detection
por: Wu, Yefeng
Publicado: (2026)

PostAlign: Multimodal Grounding as a Corrective Lens for MLLMs
por: Wu, Yixuan, et al.
Publicado: (2025)

Comprehensive Evaluation of Quantitative Measurements from Automated Deep Segmentations of PSMA PET/CT Images
por: Dzikunu, Obed Korshie, et al.
Publicado: (2025)

Anomalous thermodiffusion, absolute negative mobility and reverse heat transport in a single quantum dot
por: Zhang, Yanchao, et al.
Publicado: (2024)

FSDA-DG: Improving Cross-Domain Generalizability of Medical Image Segmentation with Few Source Domain Annotations
por: Ye, Zanting, et al.
Publicado: (2023)

Seeing More, Treating Smarter: Role of Long-Axial Field-of-View PET-CT in The Evolution of Theranostics
por: Esquinas, Pedro L., et al.
Publicado: (2025)

Assessment of dual time point protocols to produce parametric Ki images in FDG PET/CT: A virtual clinical study
por: Niloufar Reshtebar, et al.
Publicado: (2024)

University Rankings Are Hurting Academia in Developing Countries: An Urgent Call to Action
por: Mohamed L. Seghier, et al.
Publicado: (2024)

Bridging the Perception-Cognition Gap:Re-engineering SAM2 with Hilbert-Mamba for Robust VLM-based Medical Diagnosis
por: Wu, Hao, et al.
Publicado: (2025)