Cover Image

T3: Test-Time Model Merging in VLMs for Zero-Shot Medical Imaging Analysis

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Imam, Raza, Wang, Hu, Mahapatra, Dwarikanath, Yaqub, Mohammad
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Decoupling Clinical and Class-Agnostic Features for Reliable Few-Shot Adaptation under Shift
by: Rahman, Umaima, et al.
Published: (2025)

Can language-guided unsupervised adaptation improve medical image classification using unpaired images and texts?
by: Rahman, Umaima, et al.
Published: (2024)

VGS-Decoding: Visual Grounding Score Guided Decoding for Hallucination Mitigation in Medical VLMs
by: Kolli, Govinda, et al.
Published: (2026)

Envisioning MedCLIP: A Deep Dive into Explainability for Medical Vision-Language Models
by: Hashmi, Anees Ur Rehman, et al.
Published: (2024)

DiMPLe -- Disentangled Multi-Modal Prompt Learning: Enhancing Out-Of-Distribution Alignment with Invariant and Spurious Feature Separation
by: Rahman, Umaima, et al.
Published: (2025)

On the Robustness of Medical Vision-Language Models: Are they Truly Generalizable?
by: Imam, Raza, et al.
Published: (2025)

Stride-Net: Fairness-Aware Disentangled Representation Learning for Chest X-Ray Diagnosis
by: Rashid, Darakshan, et al.
Published: (2026)

Noise is an Efficient Learner for Zero-Shot Vision-Language Models
by: Imam, Raza, et al.
Published: (2025)

In-Model Merging for Enhancing the Robustness of Medical Imaging Classification Models
by: Wang, Hu, et al.
Published: (2025)

MedMerge: Merging Models for Effective Transfer Learning to Medical Imaging Tasks
by: Almakky, Ibrahim, et al.
Published: (2024)

LATA: Laplacian-Assisted Transductive Adaptation for Conformal Uncertainty in Medical VLMs
by: Bozorgtabar, Behzad, et al.
Published: (2026)

Density-Aware Translation of Spurious Correlations in Zero-Shot VLMs
by: Hasanebrahimi, Afsaneh, et al.
Published: (2026)

Test-Time Low Rank Adaptation via Confidence Maximization for Zero-Shot Generalization of Vision-Language Models
by: Imam, Raza, et al.
Published: (2024)

Efficient Parameter Adaptation for Multi-Modal Medical Image Segmentation and Prognosis
by: Saeed, Numan, et al.
Published: (2025)

Beyond Training: Dynamic Token Merging for Zero-Shot Video Understanding
by: Zhang, Yiming, et al.
Published: (2024)

CLIP meets DINO for Tuning Zero-Shot Classifier using Unlabeled Image Collections
by: Imam, Mohamed Fazli, et al.
Published: (2024)

PEMMA: Parameter-Efficient Multi-Modal Adaptation for Medical Image Segmentation
by: Saadi, Nada, et al.
Published: (2024)

Characterizing Continual Learning Scenarios and Strategies for Audio Analysis
by: Bhatt, Ruchi, et al.
Published: (2024)

CodeMerge: Codebook-Guided Model Merging for Robust Test-Time Adaptation in Autonomous Driving
by: Yang, Huitong, et al.
Published: (2025)

Zero-Shot Medical Phrase Grounding with Off-the-shelf Diffusion Models
by: Vilouras, Konstantinos, et al.
Published: (2024)

Rethinking Weight-Averaged Model-merging
by: Wang, Hu, et al.
Published: (2024)

DynaMMo: Dynamic Model Merging for Efficient Class Incremental Learning for Medical Images
by: Qazi, Mohammad Areeb, et al.
Published: (2024)

Just Shift It: Test-Time Prototype Shifting for Zero-Shot Generalization with Vision-Language Models
by: Sui, Elaine, et al.
Published: (2024)

Online Zero-Shot Classification with CLIP
by: Qian, Qi, et al.
Published: (2024)

Automatic Quality Assessment of First Trimester Crown-Rump-Length Ultrasound Images
by: Cengiz, Sevim, et al.
Published: (2025)

Tied Prototype Model for Few-Shot Medical Image Segmentation
by: Kim, Hyeongji, et al.
Published: (2025)

ORIGEN: Zero-Shot 3D Orientation Grounding in Text-to-Image Generation
by: Min, Yunhong, et al.
Published: (2025)

MedNNS: Supernet-based Medical Task-Adaptive Neural Network Search
by: Mecharbat, Lotfi Abdelkrim, et al.
Published: (2025)

Navigating Data Scarcity using Foundation Models: A Benchmark of Few-Shot and Zero-Shot Learning Approaches in Medical Imaging
by: Woerner, Stefano, et al.
Published: (2024)

Test-Time Spectrum-Aware Latent Steering for Zero-Shot Generalization in Vision-Language Models
by: Dafnis, Konstantinos M., et al.
Published: (2025)

EDUE: Expert Disagreement-Guided One-Pass Uncertainty Estimation for Medical Image Segmentation
by: Abutalip, Kudaibergen, et al.
Published: (2024)

MINGLE: Mixture of Null-Space Gated Low-Rank Experts for Test-Time Continual Model Merging
by: Qiu, Zihuan, et al.
Published: (2025)

Zero-Shot Video Restoration and Enhancement Using Pre-Trained Image Diffusion Model
by: Cao, Cong, et al.
Published: (2024)

Grounding Descriptions in Images informs Zero-Shot Visual Recognition
by: Halbe, Shaunak, et al.
Published: (2024)

Enhancing Zero-Shot Image Recognition in Vision-Language Models through Human-like Concept Guidance
by: Liu, Hui, et al.
Published: (2025)

Boundary-Aware Test-Time Adaptation for Zero-Shot Medical Image Segmentation
by: Xu, Chenlin, et al.
Published: (2025)

A Survey on Generative Modeling with Limited Data, Few Shots, and Zero Shot
by: Abdollahzadeh, Milad, et al.
Published: (2023)

Time-to-Event Pretraining for 3D Medical Imaging
by: Huo, Zepeng, et al.
Published: (2024)

Learning to Adapt Frozen CLIP for Few-Shot Test-Time Domain Adaptation
by: Chi, Zhixiang, et al.
Published: (2025)

AdaMerging: Adaptive Model Merging for Multi-Task Learning
by: Yang, Enneng, et al.
Published: (2023)