Flow Matching for Scalable Simulation-Based Inference
–Neural Information Processing Systems
Figure 1: Comparison of network architectures (left) and flow trajectories (right). Discrete flows (NPE, top) require a specialized architecture for the density estimator. Continuous flows (FMPE, bottom) are based on a vector field parametrized with an unconstrained architecture.
Neural Information Processing Systems
Nov-15-2025, 05:51:21 GMT
- Country:
- Europe > Germany
- Bavaria > Upper Bavaria > Munich (0.04)
- North America
- Canada > Quebec
- Montreal (0.04)
- United States (0.04)
- Canada > Quebec
- Europe > Germany
- Genre:
- Research Report > New Finding (0.46)
- Technology: