arXiv:2511.17844v2 Announce Type: replace-cross
Abstract: Fine-tuning large-scale text-to-video diffusion models to add new generative controls, such as those over physical camera parameters (e.g., shutter speed or aperture), typically requires vast, high-fidelity datasets that are difficult to acquire. In this work, we propose a data-efficient fine-tuning strategy that learns these controls from sparse, low-quality synthetic data. We show that not only does fine-tuning on such simple data enable the desired controls, it actually yields superior results to models fine-tuned on photorealistic “real” data. Beyond demonstrating these results, we provide a framework that justifies this phenomenon both intuitively and quantitatively.
Development and Validation of a Revised Multidimensional Digital Health Literacy Scale: Secondary Analysis Using Cross-Sectional Data From the 2022 GetCheckedOnline Community Survey In British Columbia, Canada
Background: Digital technologies are reshaping health care, making digital health literacy (DHL) a critical competency for navigating online health information. Although widely conceived and measured