Copertina

Lost in the Hype: Revealing and Dissecting the Performance Degradation of Medical Multimodal Large Language Models in Image Classification

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhu, Xun, Mo, Fanbin, Chen, Xi, Zheng, Kaili, Yang, Shaoshuai, Shi, Yiming, Gao, Jian, Li, Miao, Wu, Ji
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Enhancing Multi-task Learning Capability of Medical Generalist Foundation Model via Image-centric Multi-annotation Data
di: Zhu, Xun, et al.
Pubblicazione: (2025)

Uni-Med: A Unified Medical Generalist Foundation Model For Multi-Task Learning Via Connector-MoE
di: Zhu, Xun, et al.
Pubblicazione: (2024)

MedM-VL: What Makes a Good Medical LVLM?
di: Shi, Yiming, et al.
Pubblicazione: (2025)

Connector-S: A Survey of Connectors in Multi-modal Large Language Models
di: Zhu, Xun, et al.
Pubblicazione: (2025)

Med-2E3: A 2D-Enhanced 3D Medical Multimodal Large Language Model
di: Shi, Yiming, et al.
Pubblicazione: (2024)

Case-Aware Medical Image Classification with Multimodal Knowledge Graphs and Reliability-Guided Refinement
di: Xu, Yiming, et al.
Pubblicazione: (2026)

Degradation-Robust Fusion: An Efficient Degradation-Aware Diffusion Framework for Multimodal Image Fusion in Arbitrary Degradation Scenarios
di: Shi, Yu, et al.
Pubblicazione: (2026)

Towards Metric-Aware Multi-Person Mesh Recovery by Jointly Optimizing Human Crowd in Camera Space
di: Wang, Kaiwen, et al.
Pubblicazione: (2025)

InterMesh: Explicit Interaction-Aware End-to-End Multi-Person Human Mesh Recovery
di: Zheng, Kaili, et al.
Pubblicazione: (2026)

VN-Net: Vision-Numerical Fusion Graph Convolutional Network for Sparse Spatio-Temporal Meteorological Forecasting
di: Xiong, Yutong, et al.
Pubblicazione: (2024)

BoxComm: Benchmarking Category-Aware Commentary Generation and Narration Rhythm in Boxing
di: Wang, Kaiwen, et al.
Pubblicazione: (2026)

Revolution or Hype? Seeking the Limits of Large Models in Hardware Design
di: Xu, Qiang, et al.
Pubblicazione: (2025)

Multimodal Imaging and Clinical Features of Aortic Dissection in a Cat
di: Yewon Ji, et al.
Pubblicazione: (2025)

Embedding Radiomics into Vision Transformers for Multimodal Medical Image Classification
di: Yang, Zhenyu, et al.
Pubblicazione: (2025)

Mamba? Catch The Hype Or Rethink What Really Helps for Image Registration
di: Jian, Bailiang, et al.
Pubblicazione: (2024)

Coupled Degradation Modeling and Fusion: A VLM-Guided Degradation-Coupled Network for Degradation-Aware Infrared and Visible Image Fusion
di: Zhang, Tianpei, et al.
Pubblicazione: (2025)

MIPS: a Multimodal Infinite Polymer Sequence Pre-training Framework for Polymer Property Prediction
di: Wang, Jiaxi, et al.
Pubblicazione: (2025)

TinyLLaVA Factory: A Modularized Codebase for Small-scale Large Multimodal Models
di: Jia, Junlong, et al.
Pubblicazione: (2024)

Dissecting Role Cognition in Medical LLMs via Neuronal Ablation
di: Liang, Xun, et al.
Pubblicazione: (2025)

LKA: Large Kernel Adapter for Enhanced Medical Image Classification
di: Zhu, Ziquan, et al.
Pubblicazione: (2025)

Dissecting Failure Dynamics in Large Language Model Reasoning
di: Zhu, Wei, et al.
Pubblicazione: (2026)

Dissecting Dissonance: Benchmarking Large Multimodal Models Against Self-Contradictory Instructions
di: Gao, Jin, et al.
Pubblicazione: (2024)

Beyond the Hype: Embeddings vs. Prompting for Multiclass Classification Tasks
di: Kokkodis, Marios, et al.
Pubblicazione: (2025)

Dissecting Performance Degradation in Audio Source Separation under Sampling Frequency Mismatch
di: Imamura, Kanami, et al.
Pubblicazione: (2026)

Hypeful worlds
di: Tom Neumark
Pubblicazione: (2024)

Enhancing Spatial Reasoning in Multimodal Large Language Models through Reasoning-based Segmentation
di: Ning, Zhenhua, et al.
Pubblicazione: (2025)

HypeMed: Enhancing Medication Recommendations with Hypergraph-Based Patient Relationships
di: Zhang, Xiangxu, et al.
Pubblicazione: (2026)

VP-Hype: A Hybrid Mamba-Transformer Framework with Visual-Textual Prompting for Hyperspectral Image Classification
di: Sellam, Abdellah Zakaria, et al.
Pubblicazione: (2026)

Harnessing the Power of Natural Products for Targeted Protein Degradation
di: Bo Zhu, et al.
Pubblicazione: (2025)

Lost in Multilinguality: Dissecting Cross-lingual Factual Inconsistency in Transformer Language Models
di: Wang, Mingyang, et al.
Pubblicazione: (2025)

Decoding Visual Neural Representations by Multimodal with Dynamic Balancing
di: sun, Kaili, et al.
Pubblicazione: (2025)

Nexus-INR: Diverse Knowledge-guided Arbitrary-Scale Multimodal Medical Image Super-Resolution
di: Zhang, Bo, et al.
Pubblicazione: (2025)

COMET: Concept Space Dissection of the Modality Gap in Audio-Text Multimodal Contrastive Embeddings
di: Zhu, Yonggang, et al.
Pubblicazione: (2026)

Foundation Models in Biomedical Imaging: Turning Hype into Reality
di: Muneer, Amgad, et al.
Pubblicazione: (2025)

GoIRL: Graph-Oriented Inverse Reinforcement Learning for Multimodal Trajectory Prediction
di: Pei, Muleilan, et al.
Pubblicazione: (2025)

Medical Image Classification with KAN-Integrated Transformers and Dilated Neighborhood Attention
di: Manzari, Omid Nejati, et al.
Pubblicazione: (2025)

Rethinking the Unpretentious U-net for Medical Ultrasound Image Segmentation
di: Chen, Gongping, et al.
Pubblicazione: (2022)

MultiFair: Multimodal Balanced Fairness-Aware Medical Classification with Dual-Level Gradient Modulation
di: Zubair, Md, et al.
Pubblicazione: (2025)

Assessing Large Multimodal Models for One‐Shot Learning and Interpretability in Biomedical Image Classification
di: Wenpin Hou, et al.
Pubblicazione: (2025)

Linear Image Regridding and Coaddition with Oversampled Point Spread Functions: Lessons from 1D
di: Cao, Kaili
Pubblicazione: (2025)