Saved in:
Bibliographic Details
Main Authors: Qiu, Jiaxing, Guo, Dongliang, Sullivan, Brynne, Henry, Teague R., Hartvigsen, Thomas
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.01504
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915796707442688
author Qiu, Jiaxing
Guo, Dongliang
Sullivan, Brynne
Henry, Teague R.
Hartvigsen, Thomas
author_facet Qiu, Jiaxing
Guo, Dongliang
Sullivan, Brynne
Henry, Teague R.
Hartvigsen, Thomas
contents In time series editing, we aim to modify some properties of a given time series without altering others. For example, when analyzing a hospital patient's blood pressure, we may add a sudden early drop and observe how it impacts their future while preserving other conditions. Existing diffusion-based editors rely on rigid, predefined attribute vectors as conditions and produce all-or-nothing edits through sampling. This attribute- and sampling-based approach limits flexibility in condition format and lacks customizable control over editing strength. To overcome these limitations, we introduce Instruction-based Time Series Editing, where users specify intended edits using natural language. This allows users to express a wider range of edits in a more accessible format. We then introduce InstructTime, the first instruction-based time series editor. InstructTime takes in time series and instructions, embeds them into a shared multi-modal representation space, then decodes their embeddings to generate edited time series. By learning a structured multi-modal representation space, we can easily interpolate between embeddings to achieve varying degrees of edit. To handle local and global edits together, we propose multi-resolution encoders. In our experiments, we use synthetic and real datasets and find that InstructTime is a state-of-the-art time series editor: InstructTime achieves high-quality edits with controllable strength, can generalize to unseen instructions, and can be easily adapted to unseen conditions through few-shot learning.
format Preprint
id arxiv_https___arxiv_org_abs_2508_01504
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Instruction-based Time Series Editing
Qiu, Jiaxing
Guo, Dongliang
Sullivan, Brynne
Henry, Teague R.
Hartvigsen, Thomas
Machine Learning
In time series editing, we aim to modify some properties of a given time series without altering others. For example, when analyzing a hospital patient's blood pressure, we may add a sudden early drop and observe how it impacts their future while preserving other conditions. Existing diffusion-based editors rely on rigid, predefined attribute vectors as conditions and produce all-or-nothing edits through sampling. This attribute- and sampling-based approach limits flexibility in condition format and lacks customizable control over editing strength. To overcome these limitations, we introduce Instruction-based Time Series Editing, where users specify intended edits using natural language. This allows users to express a wider range of edits in a more accessible format. We then introduce InstructTime, the first instruction-based time series editor. InstructTime takes in time series and instructions, embeds them into a shared multi-modal representation space, then decodes their embeddings to generate edited time series. By learning a structured multi-modal representation space, we can easily interpolate between embeddings to achieve varying degrees of edit. To handle local and global edits together, we propose multi-resolution encoders. In our experiments, we use synthetic and real datasets and find that InstructTime is a state-of-the-art time series editor: InstructTime achieves high-quality edits with controllable strength, can generalize to unseen instructions, and can be easily adapted to unseen conditions through few-shot learning.
title Instruction-based Time Series Editing
topic Machine Learning
url https://arxiv.org/abs/2508.01504