arXiv:2606. 02276v1 Announce Type: cross Abstract: Vision-language models (VLMs) trained on paired chest radiographs and radiology reports learn a shared embedding space that can preserve instance-level image-report correspondence.
The paper investigates how medical vision‑language models (VLMs) behave when faced with distribution shifts such as changes in acquisition domain, supervision, or evaluation protocol. Using datasets like NIH ChestXray14, CheXpert, PadChest, and OpenI, the authors isolate cross‑dataset visual transfer, evaluate multimodal alignment, and quantify source‑proxy leakage in frozen embeddings. They find that self‑supervised visual initialization improves transfer, adversarial adaptation is only marginally helpful, and that multimodal retrieval performance drops under external stress tests while source‑proxy information remains recoverable, highlighting hidden failure modes in medical VLMs.
arXiv:2608.00231v2 Announce Type: replace Abstract: Volumetric CT vision-language pretraining learns 3D representations from scan-report pairs, but global and anatomy-aware objectives supervise only...
arXiv:2608.28923v1 Announce Type: cross Abstract: Data augmentation is a cornerstone of deep learning pipelines, yet existing strategies treat it as a static, model-agnostic preprocessing step, eithe...
arXiv:2607. 20274v1 Announce Type: cross Abstract: Medical image encoders from different groups are increasingly treated as interchangeable, on the assumption that scale and clinical supervision concentrate their representations onto a shared structure.
arXiv:2607. 03103v1 Announce Type: cross Abstract: Clinical cardiac imaging pipelines currently deploy separate models for each dataset and modality, incurring redundant training costs and precluding knowledge sharing across anatomically related tasks.
arXiv:2608. 19788v1 Announce Type: cross Abstract: Trustworthy multimodal fusion in clinical settings requires handling incomplete and heterogeneous modality subsets across institutions, where privacy constraints prohibit centralized data sharing.
PANDA (Prototype‑Anchored Data Alignment) is a two‑stage framework that enables a primary‑modality model to benefit from auxiliary modalities even when those modalities are only partially paired or absent at inference. In Stage 1, a shared embedding is learned from the paired subset and class prototypes are estimated from the auxiliary data; in Stage 2, the primary encoder is trained on all subjects using cross‑entropy and alignment to the frozen prototypes. PANDA was evaluated on Alzheimer’s MRI and TCGA‑Lung pathology, achieving significant AUC gains and improved survival prediction while requiring no auxiliary inputs during deployment.
arXiv:2606. 10066v1 Announce Type: cross Abstract: Medical vision-language models (VLMs) are evaluated on public benchmarks whose images and question-answer pairs have been freely downloadable for years, yet reported accuracy assumes these examples were absent from pretraining.
Med-AR introduces two autoregressive vision‑language models, Med‑AR‑8B and Med‑AR‑2B, pretrained on structured radiology reports, abnormality‑focused text, and region annotations to address long‑tailed chest X‑ray classification. The models outperform existing contrastive, self‑supervised, and supervised encoders—including Med‑CLIP, CheXFound, EVA‑Base, ARK, and BioViL‑T—across PadChest, MIMIC‑CXR, and CheXpert, achieving higher mean AUROC and AUPRC for head, medium, and tail findings and lower excess area under the risk‑coverage curve. Med‑AR also demonstrates improved selective‑prediction performance, with Med‑AR‑8B raising tail‑label mean AUPRC on MIMIC‑CXR from 0.1033 to 0.1441 and Med‑AR‑2B delivering the strongest discrimination on PadChest.
The paper evaluates federated learning with Low‑Rank Adaptation (LoRA) for fine‑tuning the BiomedCLIP vision‑language model on chest X‑ray classification across four international cohorts. Federated LoRA improves shared‑class AUC from 0.687 to 0.802, outperforming isolated single‑cohort training and approaching a centralized reference. The study shows that SVD‑based product‑space aggregation (FlexLoRA) is crucial for performance, while FedProx offers no advantage over FedAvg in this setting.
arXiv:2606. 24716v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) are increasingly used to extract interpretable concepts from vision and vision language models, yet existing evaluation methods largely rely on proxy metrics or qualitative inspection rather than measuring semantic correspondence.