3 papers
cs.CV2025
GeneVA: A Dataset of Human Annotations for Generative Text to Video Artifacts
Jenna Kang, Maria Silva, Patsorn Sangkloy +3
Recent advances in probabilistic generative models have extended capabilities from static image synthesis to text-driven video generation. However, the inherent randomness of their…
q-bio.QM2025
NEUBORN: The Neurodevelopmental Evolution framework Using BiOmechanical RemodelliNg
Nashira Baena, Mariana da Silva, Irina Grigorescu +4
Understanding individual cortical development is essential for identifying deviations linked to neurodevelopmental disorders. However, current normative modelling frameworks strugg…
eess.IV2024
Efficient Semantic Diffusion Architectures for Model Training on Synthetic Echocardiograms
David Stojanovski, Mariana da Silva, Pablo Lamata +2
We investigate the utility of diffusion generative models to efficiently synthesise datasets that effectively train deep learning models for image analysis. Specifically, we propos…