Copertina

On the Cone Effect and Modality Gap in Medical Vision-Language Embeddings

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Restrepo, David, Martins, Miguel L, Wu, Chenwei, Nakayama, Luis Filipe, Lopez, Diego M, Christodoulidis, Stergios, Vakalopoulou, Maria, Ferrante, Enzo
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Medical Context Distorts Decisions in Clinical Vision Language Models
di: Restrepo, David, et al.
Pubblicazione: (2026)

On the Risk of Misleading Reports: Diagnosing Textual Biases in Multimodal Clinical AI
di: Restrepo, David, et al.
Pubblicazione: (2025)

Fairness and Robustness of CLIP-Based Models for Chest X-rays
di: Sourget, Théo, et al.
Pubblicazione: (2025)

PVeRA: Probabilistic Vector-Based Random Matrix Adaptation
di: Fillioux, Leo, et al.
Pubblicazione: (2025)

Mask-HybridGNet: Graph-based segmentation with emergent anatomical correspondence from pixel-level supervision
di: Gaggion, Nicolás, et al.
Pubblicazione: (2026)

ViG-Bias: Visually Grounded Bias Discovery and Mitigation
di: Marani, Badr-Eddine, et al.
Pubblicazione: (2024)

Full Conformal Adaptation of Medical Vision-Language Models
di: Silva-Rodríguez, Julio, et al.
Pubblicazione: (2025)

SGPMIL: Sparse Gaussian Process Multiple Instance Learning
di: Lolos, Andreas, et al.
Pubblicazione: (2025)

CAPRMIL: Context-Aware Patch Representations for Multiple Instance Learning
di: Lolos, Andreas, et al.
Pubblicazione: (2025)

Multimodal Deep Learning for Low-Resource Settings: A Vector Embedding Alignment Approach for Healthcare Applications
di: Restrepo, David, et al.
Pubblicazione: (2024)

BayesAdapter: enhanced uncertainty estimation in CLIP few-shot adaptation
di: Morales-Álvarez, Pablo, et al.
Pubblicazione: (2024)

OCTOPUS: Enhancing the Spatial-Awareness of Vision SSMs with Multi-Dimensional Scans and Traversal Selection
di: Mahatha, Kunal, et al.
Pubblicazione: (2026)

Controllable Latent Space Augmentation for Digital Pathology
di: Boutaj, Sofiène, et al.
Pubblicazione: (2025)

DF-DM: A foundational process model for multimodal data fusion in the artificial intelligence era
di: Restrepo, David, et al.
Pubblicazione: (2024)

Class Adaptive Conformal Training
di: Marani, Badr-Eddine, et al.
Pubblicazione: (2026)

SoC: Semantic Orthogonal Calibration for Test-Time Prompt Tuning
di: Fillioux, Leo, et al.
Pubblicazione: (2026)

Open Challenges on Fairness of Artificial Intelligence in Medical Imaging Applications
di: Ferrante, Enzo, et al.
Pubblicazione: (2024)

Multimodal Carotid Risk Stratification with Large Vision-Language Models: Benchmarking, Fine-Tuning, and Clinical Insights
di: Tsolissou, Daphne, et al.
Pubblicazione: (2025)

Are foundation models for computer vision good conformal predictors?
di: Fillioux, Leo, et al.
Pubblicazione: (2024)

THUNDER: Tile-level Histopathology image UNDERstanding benchmark
di: Marza, Pierre, et al.
Pubblicazione: (2025)

Information Maximization for Long-Tailed Semi-Supervised Domain Generalization
di: Fillioux, Leo, et al.
Pubblicazione: (2026)

Analyzing Diversity in Healthcare LLM Research: A Scientometric Perspective
di: Restrepo, David, et al.
Pubblicazione: (2024)

Distributionally Robust Alignment for Medical Federated Vision-Language Pre-training Under Data Heterogeneity
di: Shuai, Zitao, et al.
Pubblicazione: (2024)

REMIND: Rethinking Medical High-Modality Learning under Missingness--A Long-Tailed Distribution Perspective
di: Wu, Chenwei, et al.
Pubblicazione: (2026)

Efficient In-Context Medical Segmentation with Meta-driven Visual Prompt Selection
di: Wu, Chenwei, et al.
Pubblicazione: (2024)

CDG-MAE: Learning Correspondences from Diffusion Generated Views
di: Belagali, Varun, et al.
Pubblicazione: (2025)

Emergent structures in open EFTs
di: Christodoulidis, Perseas
Pubblicazione: (2025)

Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models
di: Schrodi, Simon, et al.
Pubblicazione: (2024)

Bridging Modality Gaps in e-Commerce Products via Vision-Language Alignment
di: Zhang, Yipeng, et al.
Pubblicazione: (2025)

Cross-Modal Redundancy and the Geometry of Vision-Language Embeddings
di: Dhimoïla, Grégoire, et al.
Pubblicazione: (2026)

Bridge the Modality and Capability Gaps in Vision-Language Model Selection
di: Yi, Chao, et al.
Pubblicazione: (2024)

Do Vision-Language Models Truly Perform Vision Reasoning? A Rigorous Study of the Modality Gap
di: Xu, Yige, et al.
Pubblicazione: (2026)

Beyond Cross-Modal Alignment: Measuring and Leveraging Modality Gap in Vision-Language Models
di: Yan, Hanqi, et al.
Pubblicazione: (2025)

Covariant Electromagnetism in Past-Light-Cone Formalism
di: Nakayama, Daiju, et al.
Pubblicazione: (2024)

Semantic-Preserving Cross-Style Visual Reasoning for Robust Multi-Modal Understanding in Large Vision-Language Models
di: Nakayama, Aya, et al.
Pubblicazione: (2025)

Inference-Time Toxicity Mitigation in Protein Language Models
di: Burda, Manuel Fernández, et al.
Pubblicazione: (2026)

Source Matters: Source Dataset Impact on Model Robustness in Medical Imaging
di: Juodelyte, Dovile, et al.
Pubblicazione: (2024)

ADAPT: Multimodal Learning for Detecting Physiological Changes under Missing Modalities
di: Mordacq, Julie, et al.
Pubblicazione: (2024)

BM-CL: Bias Mitigation through the lens of Continual Learning
di: Mansilla, Lucas, et al.
Pubblicazione: (2025)

Fairness of Deep Ensembles: On the interplay between per-group task difficulty and under-representation
di: Claucich, Estanislao, et al.
Pubblicazione: (2025)