SDFlow：面向时间序列生成的相似度驱动流匹配框架

View PDF HTML (experimental)

Abstract:Vector quantization (VQ) with autoregressive (AR) token modeling is a widely adopted and highly competitive paradigm for time-series generation. However, such models are fundamentally limited by exposure bias: during inference, errors can accumulate across sequential predictions, leading to pronounced quality degradation in long-horizon generation. To address this, we propose SDFlow ($\textbf{S}$imilarity-$\textbf{D}$riven $\textbf{Flow}$ Matching), a non-autoregressive framework that operates entirely in the frozen VQ latent space and enables parallel sequence generation via flow matching. We tackle three key challenges in making this transition: (1) eliminating exposure bias by replacing step-wise token prediction with a global transport map; (2) mitigating the high-dimensionality of VQ token spaces via a low-rank manifold decomposition with a learned anchor prior over the latent manifold; and (3) incorporating discrete supervision into continuous transport dynamics by introducing a categorical posterior over codebook indices within a variational flow-matching formulation. Extensive experiments show that SDFlow achieves state-of-the-art performance, improving Discriminative Score and substantially reducing Context-FID, particularly for challenging long-sequence generation. Moreover, SDFlow provides significant inference speedups over autoregressive baselines, offering both high fidelity and computational efficiency. Code is available at this https URL

Submission history

From: Shibo Feng [view email]
[v1] Thu, 7 May 2026 06:28:18 UTC (11,656 KB)
[v2] Mon, 11 May 2026 06:04:49 UTC (11,655 KB)
[v3] Tue, 6 Oct 2026 08:27:32 UTC (11,652 KB)