Time Series Representation Learning

Follow this topic Ask about this topic

Momentum

10 papers in the last four weeks, up 100% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 61

All topics

Representing Time Series as Structured Programs for LLM Reasoning
Jun 10, 2026Jaeho Kim, Changhun Oh, Seokhyun Lee +2Time Series Reasoning Time Series QA
Korea University · Mila, University of Montreal
One Step Closer to Ground Truth: A Multi-Scale Residual-Aware Representation Learning Pipeline for Predicting Time Series Data
Jun 9, 2026Amrijit Biswas, Mustafa Kamal, Robin Krambroeckers +4Multivariate Time Series Forecasting Residual Learning
Artificial Intelligence Department, RobotBulls Labs Geneva, Switzerland · Department of Electrical and Computer Engineering, North South University Dhaka, Bangladesh
LakeFM: Toward a Foundation Model for Aquatic Ecosystems Using Irregular Multivariate Multi-depth Time Series Data
Jun 9, 2026Abhilash Neog, Sepideh Fatemi, Medha Sawhney +9Irregular Time-Series Modeling Multivariate Time Series Forecasting
Virginia Tech Blacksburg, VA, USA · Grand Valley State University Muskegon, MI, USA · University of Wisconsin - Madison Madison, WI, USA +2
PAI: Preserving Amplitude Information in Representation-Based Time-Series Anomaly Detection
Jun 8, 2026Kang Zhang, Wei Jian Lau, Shoushou Ren +3Time Series Representation Learning Time-Series Anomaly Detection
1HUAWEI · 2KAIST
Generating Financial Time Series by Matching Random Convolutional Features
Jun 3, 2026Konrad J. Mueller, Nikita Zozoulenko, Ben Wood +2Time Series Generation Random Feature Methods
Imperial College London · JPMorgan Chase & Co.‡
An explainable hierarchical self attention-based approach for tremor detection in the time domain
May 30, 2026Timothy Odonga, Jeanne M. Powell, Mark Saad +5Time Series Classification Time Series Representation Learning
Department of Biomedical Informatics, School of Medicine, Emory University, Atlanta, GA, USA · Jean and Paul Amos Parkinson’s Disease and Movement Disorders Program, Department of Neurology, School of Medicine, Emory University, Atlanta, GA, USA · Wallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology, Atlanta, GA, USA
Giving Sensors a Voice: Multimodal JEPA for Semantic Time-Series Embeddings
May 29, 2026Utsav Dutta, Gerardo Pastrana, Sina Khoshfetrat Pakazad +1Multivariate Time Series Forecasting Joint-Embedding Predictive Architecture
C3 AI, Redwood City, CA, USA
Learning Hyperspherical Time-Frequency Representations for Time-Series Out-of-Distribution Detection
May 29, 2026Willian T. Lunardi, Samridha Shrestha, Martin AndreoniHyperspherical Representation Learning Distribution Shift Detection
Technology Innovation Institute, Abu Dhabi, United Arab Emirates · Khalifa University, Abu Dhabi, United Arab Emirates
Learning Transferable Predictability Representations
May 28, 2026Diyali Goswami, Auroop R. GangulyDynamical Systems Ordinal Regression
Sustainability and Data Sciences Laboratory (SDS Lab), Northeastern University, Boston, MA, USA · AI4CaS: AI for Climate and Sustainability, Institute for Experiential AI, Northeastern University, Boston, MA, USA · Pacific Northwest National Laboratory (PNNL), Richland, WA, USA
Faithful Embeddings of Irregular and Asynchronous Data for Online Log-NCDEs
May 28, 2026Benjamin Walker, Alexandre Bloch, Lingyi Yang +2Irregular Time-Series Modeling Neural Controlled Differential Equations
Mathematical Institute University of Oxford · School of Mathematical Sciences University of Nottingham · Department of Mathematics, Imperial College London
QuITE: Query-Based Irregular Time Series Embedding
May 27, 2026Junghoon LimIrregular Time-Series Modeling Multivariate Time Series Forecasting
SK Shieldus, Seongnam, Republic of Korea
STaT: Resolving Shape Distortion in Non-Stationary Time Series via Tri-Modal Synergy
May 25, 2026Hui Cheng, Jinsheng Guo, Zhenhao Weng +2Non-Stationary Time Series Forecasting Multimodal Fusion
Hefei University of Technology Hefei, China
Continuity and Ordinality Matter: Constraining Time Series Tokens for Effective Time Series Analysis with Large Language Models
May 22, 2026Musheng Li, Ziying Zhang, Cheng jin +1Time Series Forecasting Time Series Representation Learning
Department of Electronic Engineering Tsinghua University
Dynamic Hypergraph Representation Learning for Multivariate Time Series without Prior Knowledge
May 21, 2026Marco Gregnanin, Johannes De Smedt, Giorgio Gnecco +1Multivariate Time Series Forecasting Graph Structure Learning
IMT School for Advanced Studies Lucca · KU Leuven · University of Chieti-Pescara
CASE-NET: Deep Spatio-Temporal Representation Learning via Causal Attention and Channel Recalibration for Multivariate Time Series Classification
May 21, 2026Fan Zhang, Yating Cui, Hua WangMultivariate Time Series Classification Time Series Classification
Shandong Technology and Business University · Ludong University
LLM Pretraining Shapes a Generalizable Manifold: Insights into Cross-Modal Transfer to Time Series
May 19, 2026Alexis Roger, Prateek Humane, Zhenghan Tai +4Cross-Modal Learning Language Model Pretraining
Université de Montréal Mila - Quebec AI Institute
PIMSM: Physics-Informed Multi-Scale Mamba for Stable Neural Representations under Distribution Shift
May 8, 2026Sangyoon Bae, Shinjae Yoo, Jiook ChaDomain Generalization Physics-Informed ML
Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul, South Korea, 08826 · Department of Psychology Seoul National University Seoul, South Korea, 08826
Preliminary Insights in Chronos Frequency Data Understanding and Reconstruction
May 7, 2026Alessandro Pagani, Marco Cominelli, Liying Han +11Frequency-Domain Feature Learning Time Series Representation Learning
DII, University of Brescia, Italy. · DEIB, Politecnico di Milano, Italy. · ECE Department, University of California, Los Angeles, USA. +6
The Predictive-Causal Gap: An Impossibility Theorem and Large-Scale Neural Evidence
May 6, 2026Kejun LiuCausal Representation Learning Predictive Representation Learning
State Key Laboratory of Bioinspired Interface Material Science, Institute of Nano & Functional Materials, Soochow University, Suzhou 215123, China
From Packets to Patterns: Interpreting Encrypted Network Traffic as Longitudinal Behavioral Signals
May 2, 2026Rameen Mahmood, Omar El Shahawy, Souptik Barua +5Encrypted Network Traffic Analysis Time Series Representation Learning
New York University, New York, New York, USA · NYU Langone Health, New York, New York, USA · NYU Grossman School of Medicine, New York, New York, USA +3
Continuous Temporal Representations of Event-Based Signals via Interference-Based Wave Modeling
May 2, 2026Magnus BengtssonRepresentation Learning Time Series Representation Learning
Department of Engineering, University of Borås, Borås, Sweden
CGM-JEPA: Learning Consistent Continuous Glucose Monitor Representations via Predictive Self-Supervised Pretraining
May 1, 2026Hada Melino Muhammad, Zechen Li, Flora Salim +1Cross-Modal Representation Learning Self-Supervised Time Series Representation Learning
University of New South Wales · Google Research
Learning Fingerprints for Medical Time Series with Redundancy-Constrained Information Maximization
Apr 30, 2026Huayu Li, ZhengXiao He, Xiwen Chen +4Disentangled Representation Learning Rate-Distortion Theory
University of Arizona, AZ, USA · Morgan Stanley, NY, USA · Clemson University, SC, USA +2
VTBench: A Multimodal Framework for Time-Series Classification with Chart-Based Representations
Apr 29, 2026Madhumitha Venkatesan, Xuyang Chen, Dongyu LiuData Visualization Time Series Classification
University of California, Davis Davis, United States
Leveraging Imperfect Medical Data: A Manifold-Consistent Spatio-Temporal Network for Sensor-based Human Activity Recognition
Apr 29, 2026Jiangtao Fan, Anish Jindal, Amir Atapour-AbarghoueiHuman Activity Recognition Wearable Sensing
Department of Computer Science, Durham University, Durham, DH1 3LE, UK
EvoTSC: Evolving Feature Learning Models for Time Series Classification via Genetic Programming
Apr 28, 2026Xuanhao Yang, Bing Xue, Mengjie ZhangTime Series Classification Genetic Programming
Centre for Data Science and Artificial Intelligence & School of Engineering and Computer Science, Victoria University of Wellington, PO Box 600, Wellington 6140, New Zealand
Continuous ageing trajectory representations for knee-aware lifetime prediction of lithium-ion batteries across heterogeneous dataset
Apr 17, 2026Agnieszka Pregowska, Stefan MarynowiczRUL Estimation Domain Generalization
Hyperspectral Trajectory Image for Multi-Month Trajectory Anomaly Detection
Mar 26, 2026Md Awsafur Rahman, Chandrakanth Gudavalli, Hardik Prajapati +1Anomaly Localization Transformer Attention
UC Santa Barbara, USA
PaAno: Patch-Based Representation Learning for Time-Series Anomaly Detection
Feb 1, 2026Jinju Park, Seokho KangSelf-Supervised Time Series Representation Learning Time Series Representation Learning
Department of Industrial Engineering, Sungkyunkwan University
Unlocking Pretrained Vision Transformers for Time Series Classification
Jun 10, 2025Simon Roschmann, Quentin Bouniot, Vasilii Feofanov +2Time Series Classification Vision Transformer
Helmholtz Munich · Technical University of Munich · Munich Center for Machine Learning +2

Jun 10, 2026, cs.LGJ/K move · Enter open · S save

Representing Time Series as Structured Programs for LLM Reasoning

Jaeho Kim, Changhun Oh, Seokhyun Lee, Irina Rish+1

Korea University · Mila, University of Montreal

Time Series Reasoning Time Series QA Time Series Representation Learning LLM Reasoning

Open paper AskPDF arXiv

Large language models (LLMs) have demonstrated strong reasoning and instruction-following capabilities, making them potentially powerful tools for time-series analysis. However, time series lie outside their native textual modality, raising a fundamental question: how should time series be represented so that LLMs can reason about them effectively? Existing work typically serializes raw numerical sequences or fine-tunes pre-trained LLMs on time-series data. These approaches place the burden of extracting temporal structure directly on the LLM, creating a modality mismatch that often degrades performance on long sequences and introduces substantial computational overhead. In this work, we introduce Time-Series-to-Structured-Program representation (T2SP), a deterministic, training-free method that represents a time series as a structured symbolic program. T2SP decomposes time series into trends, periods, and salient events, expressing them in a program-friendly format aligned with the textual and code-like modalities on which LLMs are natively trained. By shifting temporal-structure extraction from the model to the representation itself, T2SP enables off-the-shelf LLMs to leverage their existing reasoning capabilities for time-series understanding. We evaluate T2SP on three reasoning tasks -- editing, captioning, and question answering -- where it consistently improves performance, reduces reasoning time, and lowers failure rates compared with raw-string representations. Our results demonstrate that T2SP provides an effective interface between time series and LLMs.

Momentum

Related topics

Latest papers 61