ARTFEED — Contemporary Art Intelligence

SDFlow: Non-Autoregressive Time Series Generation via Flow Matching

other · 2026-05-09

Researchers propose SDFlow (Similarity-Driven Flow Matching), a non-autoregressive framework for time series generation that operates entirely in a frozen VQ latent space. Unlike autoregressive models, SDFlow uses a global transport map to avoid exposure bias, enabling parallel sequence generation. Key innovations include a low-rank manifold decomposition with a learned anchor prior to handle high-dimensional VQ token spaces, and discrete supervision integration. The method addresses quality degradation in long-horizon generation by eliminating sequential error accumulation. The paper is available on arXiv under ID 2605.05736.

Key facts

  • SDFlow stands for Similarity-Driven Flow Matching.
  • It is a non-autoregressive framework for time series generation.
  • Operates entirely in a frozen VQ latent space.
  • Uses flow matching for parallel sequence generation.
  • Eliminates exposure bias via a global transport map.
  • Mitigates high-dimensionality with low-rank manifold decomposition and learned anchor prior.
  • Incorporates discrete supervision into the process.
  • Paper available on arXiv: 2605.05736.

Entities

Institutions

  • arXiv

Sources