AI RESEARCH

SDFlow: Similarity-Driven Flow Matching for Time Series Generation

arXiv CS.AI

ArXi:2605.05736v1 Announce Type: new 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.