Imagen de Portada

Is There Knowledge Left to Extract? Evidence of Fragility in Medically Fine-Tuned Vision-Language Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	McLaughlin, Oliver, Shubin, Daniel, Eickhoff, Carsten, Singh, Ritambhara, Rudman, William, Golovanevsky, Michal
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Pixels Versus Priors: Controlling Knowledge Priors in Vision-Language Models through Visual Counterfacts
por: Golovanevsky, Michal, et al.
Publicado: (2025)

Mechanisms of Prompt-Induced Hallucination in Vision-Language Models
por: Rudman, William, et al.
Publicado: (2026)

What Do VLMs NOTICE? A Mechanistic Interpretability Pipeline for Gaussian-Noise-free Text-Image Corruption and Evaluation
por: Golovanevsky, Michal, et al.
Publicado: (2024)

Forgotten Polygons: Multimodal Large Language Models are Shape-Blind
por: Rudman, William, et al.
Publicado: (2025)

PiCME: Pipeline for Contrastive Modality Evaluation and Encoding in the MIMIC Dataset
por: Golovanevsky, Michal, et al.
Publicado: (2025)

Less is More: Label-Guided Summarization of Procedural and Instructional Videos
por: Rajpal, Shreya, et al.
Publicado: (2026)

When to Call an Apple Red: Humans Follow Introspective Rules, VLMs Don't
por: Nemitz, Jonathan, et al.
Publicado: (2026)

One-Versus-Others Attention: Scalable Multimodal Integration for Biomedical Data
por: Golovanevsky, Michal, et al.
Publicado: (2023)

Stable Anisotropic Regularization
por: Rudman, William, et al.
Publicado: (2023)

Outlier Dimensions Encode Task-Specific Knowledge
por: Rudman, William, et al.
Publicado: (2023)

Retrieval Augmented Zero-Shot Text Classification
por: Abdullahi, Tassallah, et al.
Publicado: (2024)

TRIM: Achieving Extreme Sparsity with Targeted Row-wise Iterative Metric-driven Pruning
por: Beck, Florentin, et al.
Publicado: (2025)

APP: Accelerated Path Patching with Task-Specific Pruning
por: Andersen, Frauke, et al.
Publicado: (2025)

The Persona Paradox: Medical Personas as Behavioral Priors in Clinical Language Models
por: Abdullahi, Tassallah, et al.
Publicado: (2026)

AEGIS: Anchor-Enforced Gradient Isolation for Knowledge-Preserving Vision-Language-Action Fine-Tuning
por: Singh, Guransh
Publicado: (2026)

From Topology to Retrieval: Decoding Embedding Spaces with Unified Signatures
por: Rottach, Florian, et al.
Publicado: (2025)

Fairness-Aware Fine-Tuning of Vision-Language Models for Medical Glaucoma Diagnosis
por: Gu, Zijian, et al.
Publicado: (2025)

Layer-Specific Fine-Tuning for Improved Negation Handling in Medical Vision-Language Models
por: Abbasi, Ali, et al.
Publicado: (2026)

Hard-label based Small Query Black-box Adversarial Attack
por: Park, Jeonghwan, et al.
Publicado: (2024)

UbuntuGuard: A Culturally-Grounded Policy Benchmark for Equitable AI Safety in African Languages
por: Abdullahi, Tassallah, et al.
Publicado: (2026)

Vision-Language Semantic Aggregation Leveraging Foundation Model for Generalizable Medical Image Segmentation
por: Yu, Wenjun, et al.
Publicado: (2025)

Visual Representations inside the Language Model
por: Liu, Benlin, et al.
Publicado: (2025)

Toward Effective Reinforcement Learning Fine-Tuning for Medical VQA in Vision-Language Models
por: Zhu, Wenhui, et al.
Publicado: (2025)

Your other Left! Vision-Language Models Fail to Identify Relative Positions in Medical Images
por: Wolf, Daniel, et al.
Publicado: (2025)

MERGETUNE: Continued Fine-Tuning of Vision-Language Models
por: Wang, Wenqing, et al.
Publicado: (2026)

UnLearning from Experience to Avoid Spurious Correlations
por: Mitchell, Jeff, et al.
Publicado: (2024)

Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models
por: Schlarmann, Christian, et al.
Publicado: (2024)

Fine-tuning Vision Language Models with Graph-based Knowledge for Explainable Medical Image Analysis
por: Li, Chenjun, et al.
Publicado: (2025)

PubMed-Ophtha: An open resource for training ophthalmology vision-language models on scientific literature
por: Hallitschke, Verena Jasmin, et al.
Publicado: (2026)

Hierarchy-Aware Fine-Tuning of Vision-Language Models
por: Li, Jiayu, et al.
Publicado: (2025)

Remodeling Semantic Relationships in Vision-Language Fine-Tuning
por: Wu, Xiangyang, et al.
Publicado: (2025)

The War Correspondent - Second Edition
por: McLaughlin, Greg
Publicado: (2016)

Edge of Catastrophe: Erich Fromm, Fascism, and the HolocaustBy Roger Frie, Oxford University Press, 2024. 216 pp. $35 (cloth). ISBN: 9780197748770.
por: Neil McLaughlin
Publicado: (2025)

Priority Projects: Constituent Spending Demand and the Benefits of Congressional Credit Claiming
por: Peter T. McLaughlin
Publicado: (2025)

La era de Klein / Patricia McLaughlin
por: McLaughlin, Patricia

Using Play‐Doh to teach creative data collection
por: Sarah McLaughlin
Publicado: (2024)

Visionaries and Crackpots, Maniacs and Saints: Existential Risk and the Politics of Longtermism
por: Alex McLaughlin
Publicado: (2025)

Kids, Kulture, and Us
por: McLaughlin, Frank
Publicado: (1972)

Managing Computer Software Collections. ERIC Digest.
por: McLaughlin, Pamela
Publicado: (1984)

Media Specialists and the Curriculum: A Selected ERIC Bibliography.
por: McLaughlin, Pamela
Publicado: (1985)