Users share appreciation for a paper demonstrating that stochastic perturbations fix flow matching degradation in high-dimensional generative models, thanking collaborators for the advance.
We propose to densify the supervision with stochastic injections - pre-train noise→target, then fine-tune onto source→target - jitter source samples with Gaussian noise - perturb the interpolant path
All three are training-time only, basically computationally free, no architecture changes, and you can sample with a plain ODE (no expensive SDE solver).
Beats vanilla flow by 13 FID & baselines by 9, across diverse scientific domains: 🔬🌄🛰️🩻🌌.
Paper: https://openaccess.thecvf.com/content/CVPR2026F/papers/Su_Stochastic_Perturbations_Improve_Distribution-to-Distribution_Generative_Models_CVPRF_2026_paper.pdf
Many thanks to my collaborators @Zhang_Yu_hui @linqi_zhou Rajesh Ranganath @yeung_levy!
We're presenting at #CVPR2026 Findings in Denver — come say hi at Poster #67, ExHall A, 7:30 – 9:00 AM tomorrow 👋
Why the problem? With finite samples on both ends, the training signal lives only along thin lines between source–target pairs.
In high dimensions they have vanishing cover over the space, so the velocity field suffers from sparse supervision and hence poor generalisation.