Hugging Face Blog
Can foundation models label data like humans?
Read the original on Hugging Face Blog →The Flow has not summarised this story yet — read it at Hugging Face Blog.
Related stories
arXiv AI
Jun 4
Who Needs Labels? Adapting Vision Foundation Models With the Metadata You Already Have
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 AI
Jun 2
AutoEval Done Right: Using Synthetic Data for Model Evaluation
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 Machine Learning
Jul 21
LFM: Leveraging Foundation Models for Source-Free Universal Domain Adaptation
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 AI
Aug 11
Protecting patient privacy in clinical foundation models: Technical and legal perspectives
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.
Hugging Face Trending Papers
Aug 13
Evaluation of Clinically Steerable Retinal Image Generation from Foundation Model Latent Spaces
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 AI
Jul 7
When Does Small Data Work? Accuracy and Efficiency Trade-offs Between Tabular Foundation Models and Conventional Methods for Crowd-State Classification at Hajj and Umrah
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.