Zero-Shot Time Series Forecasting

Follow this topic Ask about this topic

Zero-shot time series forecasting studies whether models pretrained on diverse real or synthetic sequences can predict new datasets without updating their parameters. Approaches include transformer and recurrent foundation models, synthetic-data training, covariate-aware prediction, and inference-time methods such as retrieval, context selection, and forecast correction. Benchmarks such as GIFT-Eval and fev-bench test performance across domains, while applications include energy, traffic, health, and finance. Results are often competitive when data are scarce or patterns transfer, but performance can lag specialized models when covariates, domain shifts, extreme events, or calibration matter; when and how to adapt a pretrained model remains an open question.

Latest papers

83 papers11 papers in the last four weeks, down 15% on the four weeks before. 0.1% of all new papers.

GAS-PFN: Graph-Aware Spatiotemporal Prior-Data Fitted Networks for Zero-Shot Traffic Forecasting
Oct 27, 2026Joseph Natter, Long Vu, Yifan Zhang +3Traffic Forecasting Spatiotemporal Forecasting
Kennesaw State University · Missouri State University
Sustainability of TSFM Deployment and Pretraining: From Carbon Footprint Analysis to Mitigation via Pruning
Oct 23, 2026Cécile Luc, Nathanaël Lemonnier, Ievgen RedkoTime-Series Foundation Models Energy-Efficient ML
Strategy & Innovation, AI Hub, Schneider Electric, Rueil-Malmaison, France · Strategy & Innovation, AI Hub, Schneider Electric, Grenoble, France
Zero-Shot Forecasting of In-Situ Soil Moisture and Temperature with a Time-Series Foundation Model
Oct 22, 2026Mohammad Talaei, Mohammad Goudarzi, Maille Todd +2Zero-Shot Time Series Forecasting Spatiotemporal Forecasting
Faculty of Information Technology, Monash University, Australia · School of Earth, Atmosphere and Environment, Monash University, Australia · The Environmental Informatics Hub, Data Science and AI, Monash University, Australia
Foundation-Style Pretraining for Scalable and Transferable Distributed PV Forecasting
Oct 20, 2026Dayin Chen, Xiaodan Shi, Xin Xu +6Solar Power Forecasting Time-Series Foundation Models
Department of Building Environment and Energy Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, China · International Centre of Urban Energy Nexus, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong SAR, China · Ningbo Institute of Digital Twin, Eastern Institute of Technology, Ningbo, 315200, China +2
WhatIf-Bench: Benchmarking Intervention-Aware Time Series Forecasting
Oct 19, 2026Arjun Ashok, Mihir Parmar, Palash Goyal +6Time Series Forecasting Time Series Forecasting with Covariates
Google · Mila - Quebec AI Institute · Université de Montréal +1
VaryST: Generalizable Spatio-Temporal Forecasting Beyond the Closed-World Setting
Oct 14, 2026Shengnan Guo, Jinjun Cheng, Xiaowei Mao +7Spatiotemporal Forecasting Time Series Forecasting
School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China · Key Laboratory of Big Data & Artificial Intelligence in Transportation, Ministry of Education, Beijing, China · Department of Computer Science, Aalborg University, Aalborg, Denmark +1
AdaCast: Conditional Parameter Generation for Adaptive Time Series Forecasting
Oct 8, 2026Darahaas Nallagatla, Darryl Cherian Jacob, Pan HeTime Series Forecasting Time-Series Foundation Models
Auburn University
Timer-M1: A Multivariate Time Series Foundation Model via Learning Primitives
Oct 8, 2026Haoran Zhang, Haixuan Liu, Xingjian Su +5Multivariate Time Series Forecasting Time-Series Foundation Models
School of Software, BNRist, Tsinghua University · ByteDance, Beijing, China
Benchmarking Time Series Foundation Models for Load Forecasting Under Covariate Uncertainty
Oct 5, 2026Tomas Kaljevic, Ivan Arzola, Yu ZhangZero-Shot Time Series Forecasting Time Series Forecasting
Department of Electrical and Computer Engineering University of California, Santa Cruz
GRAM: Correcting Frozen Time-Series Foundation Models via Graph-Retrieved Amplitude Memory
Oct 4, 2026Xiaoyun Yu, Xiangfei Qiu, Yonggui Huang +7Time Series Forecasting Retrieval-Augmented Time Series Forecasting
East China Normal University · Peking University · The Chinese University of Hong Kong +3
KALEIDO: Input-Space Adaptation of a Vision Model for Time-Series Forecasting Through Gated Fold Geometries
Oct 3, 2026Xiangyu Shi, Qinghua Liu, Sam Heshmati +1Time Series Forecasting Zero-Shot Time Series Forecasting
Northwestern University · Ohio State University · Bosch Research North America
Foundations without Fundamentals: Zero-Shot Blind Spots in Time Series FMs
Oct 1, 2026Nafiseh Ghoroghchian, Haipeng Zhang, Shuyi Han +2Multivariate Time Series Forecasting Zero-Shot Time Series Forecasting
Layer6 AI
Fracast-0: Fractal Weight Sharing for a Time Series Foundation Model with Only 85K Parameters
Sep 26, 2026Tianxiang Zhan, Huanyao Zhang, Yuanpeng HeTime-Series Foundation Models Probabilistic Time Series Forecasting
University of Electronic Science and Technology of China · Peking University
Just for FUNS: LLM-Guided Spatio-Temporal Graph Node Generation for Forecasting Unobserved Node States
Sep 24, 2026Shuhao Li, Weidong Yang, Changan Liu +4Spatiotemporal Forecasting Conditional Generative Modeling
Fudan University Shanghai, China · Fudan University Shanghai, China Zhuhai Fudan Innovation Research Institute Zhuhai, China · College of Computing and Data Science Nanyang Technological University Singapore +2
Evaluating Accuracy and Probabilistic Reliability of Zero-Shot Time Series Foundation Models
Sep 22, 2026Panagiotis Michael, Moysis Symeonides, Demetris TrihinasZero-Shot Time Series Forecasting Time Series Transformers
Department of Computer Science, University of Nicosia, Cyprus · Department of Computer Science, University of Cyprus, Cyprus
$t_0$ : A Time-Series Foundation Model for Forecasting with Context
Sep 21, 2026Lucas Meyer, Claudio Sole, Huikan Xiang +6Time Series Forecasting Zero-Shot Time Series Forecasting
The Forecasting Company · Macrocosm
DualCast: A Dual-Path Language Model for Bimodal Financial Time-Series Forecasting
Sep 18, 2026Wentao Zhao, Hongqiang Wu, Shanghang Liu +3Financial Forecasting Time Series Forecasting
Department of Automation, Tsinghua University, Beijing, 100084, China · School of Software, Tsinghua University, Beijing, 100084, China · School of Computer Science, Northwestern Polytechnical University, Xi’an, 710129, China +1
Tracing the Evidence Behind Zero-Shot Time-Series Forecasting: A Source-First Taxonomy and Audit Framework
Sep 18, 2026Delun Kong, Wanyun Ling, Chenxi Liu +1Zero-Shot Time Series Forecasting LLM-Based Time Series Forecasting
Department of Operations and Technology Technical University of Munich Heilbronn, Germany · Hong Kong Institute of Science & Innovation Chinese Academy of Sciences Hong Kong, China
QUALS: Corpus Equilibrium for Universal Forecasting via Pattern Quantization and Learnability Synchronization
Sep 17, 2026Yujie Li, Zezhi Shao, Chengqing Yu +7Zero-Shot Time Series Forecasting Data Selection
State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China · University of Chinese Academy of Sciences, Beijing, China · School of Data Science and Engineering, East China Normal University, Shanghai, China
SOTER: A Generative Time-Series Foundation Model for Wearable Human Physiological Signals
Sep 15, 2026Fangke Chen, Sirry Chen, Wei Chen +1Irregular Time-Series Modeling Time Series Imputation
School of Integrated Circuits, Zhejiang University Hangzhou, China · Shanghai Innovation Institute Shanghai, China · School of Data Science, Fudan University Shanghai, China +1
Tabby: An Open Pretraining Recipe for Time Series Foundation Models
Sep 12, 2026Shifeng Xie, Bahaeddine Abdessalem, Zehao Xiao +9Time-Series Foundation Models Time Series Transformers
Huawei Noah’s Ark Lab, Paris, France · LIPADE, Université Paris Cité, Paris, France · École Polytechnique, France +3
A Multi-Resolution Multi-Domain Pre-Training Framework for Universal Traffic Forecasting
Sep 12, 2026Zhouyang Liu, Jindong Han, Hao Wang +4Traffic Forecasting Spatiotemporal Forecasting
PDL Lab, National University of Defense Technology, Hunan, China · Shandong University, Shandong, China · HKUST (GZ) +2
Evaluating Time-Series Foundation Models and Multimodal Dietary Context for CGM Forecasting
Sep 10, 2026Bowen Zhang, Hsiu-Wen Cheng, Hongyu Yang +9Zero-Shot Time Series Forecasting Blood Glucose Forecasting
University of California, Los Angeles, Los Angeles, CA, U.S.A. · Union County Magnet High School, Scotch Plain, NJ, U.S.A. · Huntington Beach High School, Huntington Beach, CA, U.S.A. +3
A Later Test Set Is Not a New Domain: Pretraining Familiarity Survives a Contamination-Free Hold-Out
Sep 9, 2026Mahdi Naser Moghadasi, Faezeh GhaderiZero-Shot Time Series Forecasting Domain Generalization
BrightMind AI · University of Texas at Arlington
Assessing Covariate-Informed Grid Load Forecasting with a Time-Series Foundation Model
Sep 6, 2026Varsha Pendyala, Yiwei Fu, Weizhong Yan +1Exogenous Time Series Forecasting Electricity Load Forecasting
Artificial Intelligence Team GE Vernova Advanced Research Center, Niskayuna, NY, USA
LLMODE: Aligning ODEs with LLMs via Gated Token Injection for Irregular Spatio-Temporal Forecasting
Aug 30, 2026Di Zhang, Jingyang Zhang, Ziqian Wang +4Irregular Time-Series Modeling Zero-Shot Time Series Forecasting
Beihang University Beijing, China
In-Context Inpainting for Time Series Forecasting
Aug 24, 2026Thang Nguyen, Dung Nguyen, Romero Morais +1Time Series Forecasting Zero-Shot Time Series Forecasting
Applied Artificial Intelligence Initiative, Deakin University, Geelong, Victoria 3216, Australia
Systematic Evaluation of TabPFN-TS and Chronos-2 for Zero-Shot Heat Load Forecasting in District Heating Networks
Aug 20, 2026Ben Spoek, Karim K. Ben Hicham, Kai Derzsi +3Zero-Shot Time Series Forecasting Time Series Forecasting
Chair of Energy Efficient Buildings and Indoor Climate, RWTH Aachen University, Mathieustr. 10, 52074 Aachen, Germany · Process Systems Engineering, RWTH Aachen University, Forckenbeckstr. 51, 52074 Aachen, Germany
LiveHouse-TS: An Open-world Living Benchmark for Time Series Foundation Models
Aug 18, 2026Haomin Wen, Ziyu Zhou, Qingxiang Liu +2Forecasting Benchmarks Time-Series Foundation Models
Shanghai Innovation Institute · The Hong Kong University of Science and Technology (Guangzhou)
Deep Learning for Cross-Border Electricity Price Forecasting: A Comparative Study
Aug 17, 2026Hadeer Elashhab, Sai Srijan Papineni, Marvin Dorn +2Electricity Price Forecasting Time Series Forecasting
Institute for Automation and Applied Informatics, Karlsruhe Institute of Technology, Karlsruhe, Germany · Department of Computer Science, Karlsruhe Institute of Technology, Karlsruhe, Germany

Oct 27, 2026J/K move · Enter open · S save

GAS-PFN: Graph-Aware Spatiotemporal Prior-Data Fitted Networks for Zero-Shot Traffic Forecasting

Joseph Natter, Long Vu, Yifan Zhang, Bobin Deng+2

Kennesaw State University · Missouri State University

Traffic Forecasting Spatiotemporal Forecasting Zero-Shot Time Series Forecasting Prior-Data Fitted Networks Spatiotemporal Transformers

Open paper AskPDF arXiv

Traffic forecasting requires modeling complex temporal dynamics and the spatial dependencies imposed by road topology. Supervised graph-based models achieve strong performance, but are often trained for a particular dataset and sensor graph, making deployment to new or evolving networks costly. Prior-Data Fitted Networks (PFNs) offer a zero-shot alternative by learning in-context inference from synthetic task priors, which provide an explicit mechanism for encoding domain-specific assumptions. Existing forecasting PFNs, however, do not explicitly represent the graph-structured dependencies governing traffic dynamics. To combine graph-aware traffic modeling with zero-shot adaptation, we introduce the Graph-Aware Spatiotemporal Prior-Data Fitted Network (GAS-PFN). GAS-PFN incorporates sampled road topology into its synthetic task prior through random-walk diffusion, teaching the model to learn graph-coupled dynamics during pretraining. Its co-designed inference architecture uses two mask-conditioned passes through a shared Transformer backbone to separately model sensor-specific temporal dynamics and spatiotemporal interactions among neighboring sensors before integrating their representations for prediction. This design enables GAS-PFN to use target-network structure and context without parameter updates. Across six benchmarks at the 90-minute horizon, GAS-PFN reduces MSE by 34.0% on average relative to TimePFN, its closest PFN-based predecessor. It also reduces MSE by 27.7% on average relative to four recent industry-developed general-purpose zero-shot forecasters. In this comparison, all models receive 90 minutes of contiguous recent history, and any additional context is drawn from each dataset's chronological training split. These results indicate that aligning PFN priors and inference architectures with graph structure improves in-context learning for zero-shot traffic forecasting.