Forward Gaussian corruption
Eight components, radius 3, component standard deviation 0.25. Change the path and time; fixed paired particles show Xₜ = αX₀ + σε. Forward time runs from data to noise. Arrows use the exact marginal score.
Explore probability paths, scores, transport and generative models. The analytic panels calculate exact mixture quantities in your browser; trained galleries expose the published experiments and their limitations.
Repository guide · Learning curriculum · Review and comparisonsEight components, radius 3, component standard deviation 0.25. Change the path and time; fixed paired particles show Xₜ = αX₀ + σε. Forward time runs from data to noise. Arrows use the exact marginal score.
The noisy observation used below is (1, −0.5). Tweedie gives a conditional mean, which can fall between mixture modes. It is neither a fresh conditional sample nor a guaranteed denoised ground truth.
Definitions, time conventions and runtime codeDistances use the declared representation and sample counts. Do not rank different datasets or feature spaces together. Historical runs include development/test reuse and documented invalidated diagnostics; see their reports before making a claim.