arXiv:2606. 05107v1 Announce Type: cross Abstract: We propose a label-free approach to adapt powerful but generic vision foundation models to specialized scientific domains.
arXiv:2403. 07008v3 Announce Type: replace-cross Abstract: The evaluation of machine learning models using human-labeled validation data can be expensive and time-consuming.
arXiv:2607. 17653v1 Announce Type: cross Abstract: Source-free universal domain adaptation (SF-UniDA) adapts a pre-trained source model to an unlabeled target domain under both covariate and label shifts, without access to source data.
arXiv:2608. 07705v1 Announce Type: new Abstract: Clinical foundation models trained on large-scale patient data are increasingly used for decision support, screening, and public health.
Medical foundation models learn latent representations of clinically meaningful phenotypes, yet their ability to support controllable image generation remains largely unexplored. We evaluate four retinal foundation models within the representation tokenizer framework and examine whether demographic and clinical information encoded in latent representations from foundation models is preserved during synthetic image generation.
arXiv:2607. 04013v1 Announce Type: cross Abstract: Learning from few labeled examples is a central challenge in tabular machine learning, and it becomes the binding constraint in domains where labeling is costly, such as crowd monitoring during Hajj and Umrah.
arXiv:2607. 05052v1 Announce Type: cross Abstract: Human value detection is commonly formulated as sentence-level multi-label classification over the 19 refined Schwartz values, typically predicted as independent labels.
arXiv:2608. 20069v1 Announce Type: new Abstract: While generalist VLMs are expensive to train, creating domain experts is widely assumed to require fine-tuning increasingly large foundation models.
arXiv:2505. 23593v4 Announce Type: replace Abstract: Post-training of foundation language models has emerged as a promising research domain in federated learning (FL) with the goal to enable privacy-preserving model improvements and adaptations to user's downstream tasks.
arXiv:2608. 10195v1 Announce Type: cross Abstract: Human vision organizes what it sees into wholes: same-colored points group into series, similar marks cohere into categories, and shapes complete into recognizable objects.
arXiv:2606. 07630v1 Announce Type: cross Abstract: Real-world datasets across image and text domains are often characterized by skewed class distributions and noisy annotations, which jointly degrade model performance, particularly on minority classes.
arXiv:2607. 15455v1 Announce Type: cross Abstract: Researchers increasingly use automated classifiers to label unstructured data for statistical analysis.