提出可同时控制时间序列点与段落的编辑框架，解决生成时序数据难精准修改的问题。
How to Unlock Time Series Editing? Diffusion-Driven Approach with Multi-Grained Control
- 用置信度加权锚点控制实现点级精确修改
- 通过分类器控制段落统计属性如均值与总和
- 兼容任意条件扩散模型，适合人机协同编辑场景
时间序列生成近年取得进展，但对生成序列的属性控制仍具挑战。时间序列编辑（TSE）需在保持时间连贯性的同时进行精准修改，涵盖点级约束与段级控制，现有方法难以兼顾。本文提出CocktailEdit框架，支持多粒度约束的并行灵活控制。该框架融合两项关键技术：基于置信度加权的锚点控制，用于点级约束；基于分类器的控制机制，用于管理段落层面的统计属性（如和、均值）。该方法在去噪推理阶段实现精确局部控制，保持时间连贯性，并可无缝集成至任意条件扩散模型中。在多个数据集与模型上的实验验证了其有效性。本工作弥合了纯生成建模与真实世界时序编辑需求之间的差距，为人类参与的时序生成与编辑提供灵活解决方案。代码与演示已公开。
原文摘要 · Abstract (English)
Recent advances in time series generation have shown promise, yet controlling properties in generated sequences remains challenging. Time Series Editing (TSE) - making precise modifications while preserving temporal coherence - consider both point-level constraints and segment-level controls that current methods struggle to provide. We introduce the CocktailEdit framework to enable simultaneous, flexible control across different types of constraints. This framework combines two key mechanisms: a confidence-weighted anchor control for point-wise constraints and a classifier-based control for managing statistical properties such as sums and averages over segments. Our methods achieve precise local control during the denoising inference stage while maintaining temporal coherence and integrating seamlessly, with any conditionally trained diffusion-based time series models. Extensive experiments across diverse datasets and models demonstrate its effectiveness. Our work bridges the gap between pure generative modeling and real-world time series editing needs, offering a flexible solution for human-in-the-loop time series generation and editing. The code and demo are provided for validation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。