Image de couverture de livre

MedSAE: Dissecting MedCLIP Representations with Sparse Autoencoders

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Renzulli, Riccardo, Lepoutre, Colas, Cassano, Enrico, Grangetto, Marco
Format:	Preprint
Publié:	2025
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

SAEmnesia: Erasing Concepts in Diffusion Models with Supervised Sparse Autoencoders
par: Cassano, Enrico, et autres
Publié: (2025)

When Does Pruning Benefit Vision Representations?
par: Cassano, Enrico, et autres
Publié: (2025)

Capsule Networks Do Not Need to Model Everything
par: Renzulli, Riccardo, et autres
Publié: (2022)

Hierarchical Object-Centric Learning with Capsule Networks
par: Renzulli, Riccardo
Publié: (2024)

SAE-RNA: A Sparse Autoencoder Model for Interpreting RNA Language Model Representations
par: Kim, Taehan, et autres
Publié: (2025)

AI-Assisted Diagnosis for Covid-19 CXR Screening: From Data Collection to Clinical Validation
par: Barbano, Carlo Alberto, et autres
Publié: (2024)

Integrating MedCLIP and Cross-Modal Fusion for Automatic Radiology Report Generation
par: Han, Qianhao, et autres
Publié: (2024)

Group-SAE: Efficient Training of Sparse Autoencoders for Large Language Models via Layer Groups
par: Ghilardi, Davide, et autres
Publié: (2024)

ReSAE: Residualized Sparse Autoencoders for Multi-Layer Transformer Interventions
par: Poduval, Prathyush, et autres
Publié: (2026)

Envisioning MedCLIP: A Deep Dive into Explainability for Medical Vision-Language Models
par: Hashmi, Anees Ur Rehman, et autres
Publié: (2024)

MedCLIP-SAMv2: Towards Universal Text-Driven Medical Image Segmentation
par: Koleilat, Taha, et autres
Publié: (2024)

MedCLIP-SAM: Bridging Text and Image Towards Universal Medical Image Segmentation
par: Koleilat, Taha, et autres
Publié: (2024)

LouvreSAE: Sparse Autoencoders for Interpretable and Controllable Style Transfer
par: Panda, Raina, et autres
Publié: (2025)

MedG-KRP: Medical Graph Knowledge Representation Probing
par: Rosenbaum, Gabriel R., et autres
Publié: (2024)

Interpreting CLIP with Hierarchical Sparse Autoencoders
par: Zaigrajew, Vladimir, et autres
Publié: (2025)

Backdoor Attack on Unpaired Medical Image-Text Foundation Models: A Pilot Study on MedCLIP
par: Jin, Ruinan, et autres
Publié: (2024)

ProtSAE: Disentangling and Interpreting Protein Language Models via Semantically-Guided Sparse Autoencoders
par: Liu, Xiangyu, et autres
Publié: (2025)

FaithfulSAE: Towards Capturing Faithful Features with Sparse Autoencoders without External Dataset Dependencies
par: Cho, Seonglae, et autres
Publié: (2025)

Automated Prediction of Paravalvular Regurgitation before Transcatheter Aortic Valve Implantation
par: Cannito, Michele, et autres
Publié: (2026)

MedProbCLIP: Probabilistic Adaptation of Vision-Language Foundation Model for Reliable Radiograph-Report Retrieval
par: Elallaf, Ahmad, et autres
Publié: (2026)

MedGemma 1.5 Technical Report
par: Sellergren, Andrew, et autres
Publié: (2026)

MedCalc-Eval and MedCalc-Env: Advancing Medical Calculation Capabilities of Large Language Models
par: Mao, Kangkun, et autres
Publié: (2025)

Med42-v2: A Suite of Clinical LLMs
par: Christophe, Clément, et autres
Publié: (2024)

VisionCLIP: An Med-AIGC based Ethical Language-Image Foundation Model for Generalizable Retina Image Analysis
par: Wei, Hao, et autres
Publié: (2024)

MedVAE: Efficient Automated Interpretation of Medical Images with Large-Scale Generalizable Autoencoders
par: Varma, Maya, et autres
Publié: (2025)

AutoML-Med: A Framework for Automated Machine Learning in Medical Tabular Data
par: Francia, Riccardo, et autres
Publié: (2025)

QuarkMed Medical Foundation Model Technical Report
par: Li, Ao, et autres
Publié: (2025)

MedGrad E-CLIP: Enhancing Trust and Transparency in AI-Driven Skin Lesion Diagnosis
par: Kamal, Sadia, et autres
Publié: (2025)

RegionMed-CLIP: A Region-Aware Multimodal Contrastive Learning Pre-trained Model for Medical Image Understanding
par: Fang, Tianchen, et autres
Publié: (2025)

GeoSAE: Geometric Prior-Guided Layer-Wise Sparse Autoencoder Annotation of Brain MRI Foundation Models
par: Nerrise, Favour, et autres
Publié: (2026)

Dissecting Chronos: Sparse Autoencoders Reveal Causal Feature Hierarchies in Time Series Foundation Models
par: Mishra, Anurag
Publié: (2026)

MedGemma Technical Report
par: Sellergren, Andrew, et autres
Publié: (2025)

MedRep: Medical Concept Representation for General Electronic Health Record Foundation Models
par: Kim, Junmo, et autres
Publié: (2025)

Boost Your NeRF: A Model-Agnostic Mixture of Experts Framework for High Quality and Efficient Rendering
par: Di Sario, Francesco, et autres
Publié: (2024)

SOLVE-Med: Specialized Orchestration for Leading Vertical Experts across Medical Specialties
par: Di Marino, Roberta, et autres
Publié: (2025)

Benchmarking PNW Model for MedMNIST to 100% Accuracy
par: Deng, Bo
Publié: (2026)

MedPAO: A Protocol-Driven Agent for Structuring Medical Reports
par: Vaidya, Shrish Shrinath, et autres
Publié: (2025)

MedBLINK: Probing Basic Perception in Multimodal Language Models for Medicine
par: Bigverdi, Mahtab, et autres
Publié: (2025)

OctoMed: Data Recipes for State-of-the-Art Multimodal Medical Reasoning
par: Ossowski, Timothy, et autres
Publié: (2025)

Med-VRAgent: A Framework for Medical Visual Reasoning-Enhanced Agents
par: Guo, Guangfu, et autres
Publié: (2025)