🍓 Simulation-free, GPU-first generative modeling in PyTorch ⚡ Composable primitives for scalable, stable training of modern EBMs, diffusion, flow matching, and Schrödinger bridges.
deep-learning gpu cuda pytorch hamiltonian-monte-carlo optimal-transport sampling-methods langevin-dynamics generative-models contrastive-divergence diffusion-models mcmc-sampling probabilistic-machine-learning score-matching energy-based-models flow-matching schrodinger-bridge equilibrium-matching simulation-free
-
Updated
Sep 2, 2026 - Python