Contrast-X benchmark and FlowMI model enable synthesis of contrast-enhanced images from arbitrary non-contrast modality inputs using multi-modal flow matching.
Learning patient-specific disease dynamics with latent flow matching for longitudinal imaging generation.arXiv preprint arXiv:2512.09185, 2025
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3roles
background 1polarities
background 1representative citing papers
Training-inference input alignment outweighs framework choice for longitudinal retinal image prediction, with deterministic regression matching complex models when acquisition variability dominates disease progression.
citing papers explorer
-
Contrast-X: A Multi-Modal Contrast Image Synthesis Benchmark and Universal Modality Flow Matching
Contrast-X benchmark and FlowMI model enable synthesis of contrast-enhanced images from arbitrary non-contrast modality inputs using multi-modal flow matching.
-
Training-inference input alignment outweighs framework choice in longitudinal retinal image prediction
Training-inference input alignment outweighs framework choice for longitudinal retinal image prediction, with deterministic regression matching complex models when acquisition variability dominates disease progression.
- Divergence is Uncertainty: A Closed-Form Posterior Covariance for Flow Matching