2 papers
stat.ML2026
Can Deep Generative Models Reproduce Non-Stationary Gaussian Random Fields?
Daniel Kua, Yan Song
Deep generative models (DGMs) are widely used for complex high-dimensional data and increasingly applied to spatial and spatio-temporal modeling. Their generated samples implicitly…
cs.SD2026
Enhancing Flow Matching with A Unified Guidance Framework for Efficient and Robust Speech Synthesis
Zuda Yu, Qianhui Xu, Ting Chen +5
Flow Matching (FM) has emerged as a powerful paradigm for speech generation but remains constrained by high inference latency and timbre leakage. To address these bottlenecks, we p…