Conditional Mean Flows: Few-Step Densities for Simulation-Based Inference
arXiv:2610.21657v1 Announce Type: new Abstract: Flow matching has emerged as a powerful generative family for simulation-based inference (SBI). However, sampling and density evaluation require numerical integration at inference time. This makes posterior sampling in neural posterior estimation cost…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-10-16 04:00 · arXiv stat.ML
Conditional Mean Flows: Few-Step Densities for Simulation-Based Inference