Image Synthesis as an Intermediate for Controllable Time Series Generation

Excerpt

arXiv:2610.05211v1 Announce Type: new Abstract: Semantic-driven time-series generation offers a promising way to improve downstream learning in few-shot forecasting, but directly generating numerical sequences from language often fails to preserve the intended temporal structure. We propose VisualBridge, which uses time-series plots as a visual intermediate to bridge high-level temporal semantics and numerical sequences. An MLLM first converts plotted series into structured semantic representati