On the Stability and Convergence of Flow Map Training
arXiv:2610.20674v1 Announce Type: new Abstract: Flow maps are a recent method of probabilistic generation that amortize diffusion trajectories into one-step samplers, unlocking efficient generation. While progress has been made in improving their empirical performance, there is still a lack of unde…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-10-16 04:00 · arXiv stat.ML
On the Stability and Convergence of Flow Map Training