The open-source method generates 3D molecular conformers.
Michael Bronstein#199
Introducing Strong Stochastic Flow Maps
TLDR: Stochastic Flow Maps where we learn the stochastic solution path.
Work led by Sam McCallum, @zwblasingame, with Timothy Herschelll, @AlexanderTong7, and @JamesFosterBath
Arxiv: https://arxiv.org/pdf/2606.01086 Code: https://github.com/sammccallum/ssfm
This looks neat! Flow maps are deterministic by default. You can make them stochastic by conditioning on a noise variable (e.g. meta flow maps, diamond maps). But if you want to get the exact same samples with fewer steps, you need to condition on the entire noise trajectory!
Introducing Strong Stochastic Flow Maps
TLDR: Stochastic Flow Maps where we learn the stochastic solution path.
Work led by Sam McCallum, @zwblasingame, with Timothy Herschelll, @AlexanderTong7, and @JamesFosterBath
Arxiv: https://arxiv.org/pdf/2606.01086 Code: https://github.com/sammccallum/ssfm
The open-source method generates 3D molecular conformers.
Michael Bronstein#199Introducing Strong Stochastic Flow Maps
TLDR: Stochastic Flow Maps where we learn the stochastic solution path.
Work led by Sam McCallum, @zwblasingame, with Timothy Herschelll, @AlexanderTong7, and @JamesFosterBath
Arxiv: https://arxiv.org/pdf/2606.01086 Code: https://github.com/sammccallum/ssfm
Users are excited by researchers introducing Strong Stochastic Flow Maps for Stochastic Paths because they find the work very cool and great.