DAC · Flagship Product

FlashDiffusion

// Coifman–Lafon · sparse eigensolver · B300 GPU

Diffusion maps at 100M-sample scale. The intrinsic geometry of your data — conformational landscapes, reaction coordinates, latent structure — in hours, not weeks.

1Mframes
MD Trajectory
64,000 features · 30 min
100Msamples
Max dataset size
Nyström approximation
O(N·D)
Effective scaling
sparse eigensolver
B300GPU
Native hardware
flash kernel

N vs. wall-clock time

Eigenvector compute time as dataset size grows.

Minutes to compute · log scale
FlashDiffusion
Dense O(N²)
Method

Two-stage pipeline

Geometric analysis first. Guided learning second.

01
Upload dataset

MD trajectories (.xtc), cryo-EM stacks, XFEL diffraction, or any high-dimensional scientific data. Stored on R2.

R2 · no size limit
02
FlashDiffusion

Sparse Coifman–Lafon diffusion map. B300-native eigensolver computes the intrinsic geometry of your data.

B300 · hours not weeks
03
Guided NN optional

Train a neural network guided by the eigenvectors — MLP, DiT, or autoregressive. Physically meaningful, not a black box.

MLP · DiT · AR
Applications

Built for scientific data

MD Trajectories

Conformational landscapes of proteins, polymers, and materials. Identify slow collective variables from millions of frames.

FORMAT · .xtc .dcd .h5
Cryo-EM

Heterogeneity analysis of particle stacks. Map conformational continua without discrete class assumptions.

FORMAT · .mrcs .star .cs
XFEL Diffraction

Single-particle and serial crystallography datasets. Geometry-aware analysis of femtosecond snapshots.

FORMAT · .cxi .h5 .cbf

Private beta.
Apply now.

If you have a dataset and a problem that needs diffusion maps at scale, we want to hear from you.

// No spam. We respond personally.