Showing cs.CVShow all
2 papers · 1 filter
cs.CV2025
DINO-MX: A Modular & Flexible Framework for Self-Supervised Learning
Mahmut Selman Gokmen, Cody Bumgardner
Vision Foundation Models (VFMs) have advanced representation learning through self-supervised methods. However, existing training pipelines are often inflexible, domain-specific, o…
cs.CV2025
Poisson Flow Consistency Training
Anthony Zhang, Mahmut Gokmen, Dennis Hein +4
The Poisson Flow Consistency Model (PFCM) is a consistency-style model based on the robust Poisson Flow Generative Model++ (PFGM++) which has achieved success in unconditional imag…