From the 1 of 3 linked papers with an AI index.
3 papers
cs.LG2026
Velocity Scheduled Flow Matching
Vitalii Bondar
The paper introduces Velocity Scheduled Flow Matching (VSFM), a method that lets a pretrained flow‑matching model be sampled with arbitrary non‑uniform velocity profiles, improving…
eess.SP2025
FlowECG: Using Flow Matching to Create a More Efficient ECG Signal Generator
Vitalii Bondar, Serhii Semenov, Vira Babenko +1
Synthetic electrocardiogram generation serves medical AI applications requiring privacy-preserving data sharing and training dataset augmentation. Current diffusion-based methods a…
cs.LG2025
Deep generative models as the probability transformation functions
Vitalii Bondar, Vira Babenko, Roman Trembovetskyi +2
This paper introduces a unified theoretical perspective that views deep generative models as probability transformation functions. Despite the apparent differences in architecture…