FUSE: FK-Steered Multi-Modal Flow Matching for Efficient Simulation-Based Posterior Estimation
2026-07-06 • Machine Learning
Machine Learning
AI summaryⓘ
The authors present FUSE, a new method to help computers better understand complex scientific data by keeping different types of information separate but connected. Their approach uses a special way to guide the computer's guessing process, improving accuracy when figuring out hidden details from simulations. They tested FUSE on standard benchmarks and a real exoplanet task, showing it works better than previous methods, especially in tricky situations with overlapping parameters. This could help scientists make discoveries faster in fields like astrophysics.
Simulation-Based InferenceGenerative ModelsMultimodal ModelingFeynman-Kac FormulaFlow MatchingPosterior EstimationMarkov Chain Monte CarloExoplanet Orbital EstimationParameter DegeneracyScientific Discovery
Authors
Weichen Qin, Yufan Xie, Peihao Wang, Chia-Jui Chou, Minghui Du, Peng Xu, Ziren Luo, Yi Yang, Jingyi Yu, Bo Liang, Jiakai Zhang
Abstract
Simulation-Based Inference (SBI) is critical for scientific discovery, with generative models offering a promising path toward efficient inference. However, existing methods struggle with effective multimodal modeling. They often rely on brute-force fusion strategies that ignore the structural disparities between parameters and observations, thus limiting estimation fidelity. In this work, we introduce FUSE (Feynman-Kac steered mUlti-modal flow matching for efficient Simulation-based posterior Estimation). Unlike prior work, FUSE employs a dual-track architecture that preserves the distinct features of multimodal inputs while facilitating dynamic interaction. Additionally, we propose an FK-steered sampling strategy that leverages intermediate observation likelihoods to guide the generative trajectories, effectively improving the sample quality during inference. Our approach outperforms state-of-the-art baselines on standard SBI benchmarks, producing posteriors that closely match ground-truth MCMC. Furthermore, in a real-world exoplanet orbital estimation task, FUSE successfully resolves complex parameter degeneracies that challenge existing methods, highlighting its potential to accelerate complex scientific discoveries in astrophysics and beyond.