AI RESEARCH

Parallel Complex Diffusion for Scalable Time Series Generation

arXiv CS.LG

ArXi:2602.17706v2 Announce Type: replace Diffusion models learn data distributions indirectly through denoising, making the difficulty of generative modeling closely tied to the dependency structure of data. For time series, strong temporal dependence forces the noise / score estimator to recover highly entangled cross-time relationships, leading to the curse of entanglement.