Topic
acceleration
Artificial Intelligence #generative modeling#artificial intelligence
Bi-Anchor Interpolation Solver Cuts Generative Modeling Steps from 100 to 10, Researchers Show
Researchers introduce the Bi-Anchor Interpolation Solver (BA-solver) for accelerating flow matching generative models. It achieves quality comparable to 100+ step solvers in just 10 steps, using a small SideNet (1-2% of backbone size) and novel bidirectional temporal perception. The method is plug-and-play with existing pipelines.
Jul 8, 2026 1 source
Artificial Intelligence #topology optimization#convolutional neural network
New CNN Model eCNNTO Cuts Topology Optimization Iterations by Up to 97%
Researchers propose eCNNTO, a convolutional neural network that accelerates density-based topology optimization by predicting near-optimal densities from early iteration histories. The model achieves up to 90% reduction in iterations for 2D problems and 97% for 3D, requiring only small training datasets and generalizing to diverse boundary conditions and geometries.
Jun 20, 2026 1 source