Probabilistic Time Series Forecasting

Follow this topic Ask about this topic

Momentum

14 papers in the last four weeks, up 56% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 112

All topics

Seq-Flow: Efficient Probabilistic Forecasting with Self-Rollout Error Control
Oct 7, 2026Yinan Huang, Shitij Govil, Bo Dai +1Probabilistic Forecasting Probabilistic Time Series Forecasting
Georgia Institute of Technology
From Shared Demand Patterns to Local Uncertainty: Probabilistic Load Forecasting by Mixing Compact Adaptations
Oct 6, 2026Haoran Li, Zhe Cheng, Yang WengElectricity Load Forecasting Probabilistic Time Series Forecasting
Machine Learning for German Redispatch Forecasting under Data Delays and Temporal Distribution Shift
Oct 6, 2026Faraz Shamim, Faris ShamimDistribution Shift Robustness Time Series Forecasting
KIST Medical College and Teaching Hospital, Nepal · OTH Regensburg
MercerFlow: Flow Matching in a Kernel-Induced Latent Space for Probabilistic Forecasting
Oct 5, 2026Ilya Kuleshov, Egor Serov, Alexey ZaytsevMultivariate Time Series Forecasting Conditional Flow Matching
Applied AI Institute Moscow, Russia
Skillful Data-Driven Subseasonal Soil Moisture Forecasting: Prospects and Limits for Flash Drought Prediction
Oct 5, 2026Noelia Otero, Atahan Özer, Miguel-Ángel Fernández-Torres +1Spatiotemporal Forecasting Probabilistic Time Series Forecasting
Applied Machine Learning Group, Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute, Berlin, Germany · Department of Signal Theory and Communications, Universidad Carlos III de Madrid (UC3M), Madrid, Spain
Pythia: Toward Foundation World Models for Multimodal Time Series
Oct 4, 2026Xilin Dai, Hongzhou Chen, Yifan Hu +3Multivariate Time Series Forecasting World Model Learning
Ant International
GARDiff: Graph-Aligned Residual Diffusion for Probabilistic Multivariate Time-Series Forecasting
Sep 29, 2026Rui Han, Min Yang, Xu Zhang +3Multivariate Time Series Forecasting Graph Structure Learning
Shandong University, Jinan, China · Macquarie University, Sydney, Australia · China University of Petroleum (East China), Qingdao, China +1
KiT: A Foundation Model for Financial Time-Series Forecasting using DiffusionTransformers
Sep 28, 2026Boyu Zhang, Haorui LiDiffusion Transformer Financial Forecasting
University of California, Los Angeles · Southeast University
ViBR-WM: Visual Bayesian Regression for World Modeling
Sep 27, 2026Jifan Li, Ning NingWorld Model Learning Time Series Forecasting
Department of Statistics, Texas A&M University College Station, TX 77843
fable.intermittent: benchmarking probabilistic forecasting methods for intermittent time series
Sep 23, 2026Stefano Damato, Lorenzo Zambon, Giorgio Corani +1Time Series Forecasting Forecasting Benchmarks
SUPSI, Istituto Dalle Molle di Studi sull’Intelligenza Artificiale (IDSIA), Lugano, Switzerland
Time-Series Foundation Models That Understand Data Revisions
Sep 23, 2026Taimoor AhmadTime Series Forecasting Temporal Data Leakage
Superior University Lahore, Pakistan
Transfer Learning with Conformalized Quantile Regression for Solar PV Forecasting Under Load-Shedding-Driven Data Scarcity
Sep 22, 2026Rakib Abdullah, K. M. Tahlil Mahfuz FarukSolar Power Forecasting Transfer Learning
Department of AI and Data Science Green University of Bangladesh
PROSWIN: Probabilistic Solar Wind Speed Forecasting Using Deep Distributional Regression From Solar Images
Sep 22, 2026Daniel Collin, Yuri Shprits, Luca Chiarabini +3Time Series Forecasting Probabilistic Time Series Forecasting
Space Physics and Space Weather, GFZ Helmholtz Centre for Geosciences, Potsdam, Germany · Department of Electrical Engineering and Computer Science, Technical University of Berlin, Berlin, Germany · Institute of Physics and Astronomy, University of Potsdam, Potsdam, Germany +5
Interweaving Marginals into Multivariate Sample Paths: Training-Free Dependence Construction for Probabilistic Time Series Foundation Models
Sep 22, 2026Jinmyeong Choi, Jinkwan Jang, Seul Lee +1Probabilistic Forecasting Time-Series Foundation Models
Graduate School of Data Science Seoul National University
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 +6Multivariate Time Series Forecasting Zero-Shot Time Series Forecasting
The Forecasting Company · Macrocosm
TEMPER: Temporal Encoder-Masked Probabilistic Ensemble Regressor for Time-Series Forecasting
Sep 20, 2026Giancarlo VercellinoTime Series Forecasting Probabilistic Time Series Forecasting
Independent researcher
Halo: Improving forecast accuracy through heteroscedastic estimation
Sep 11, 2026Adam CataldoTime Series Forecasting Heteroscedastic Regression
AI Quant Researcher
Distillation of Synthetic Data for Time Series Foundation Models
Sep 9, 2026Niloy Biswas, Noureddine El KarouiSynthetic Data Pretraining Time-Series Foundation Models
Meta AI
DynG-Diff: A State-Aware Dynamic Guidance Diffusion Framework for Probabilistic Time Series Forecasting
Sep 2, 2026Zhente Zhang, Zhengwei Ni, Wei FanMultivariate Time Series Forecasting Diffusion Model Guidance
School of Information and Electronic Engineering (Sussex Artificial Intelligence Institute), Zhejiang Gongshang University, Hangzhou, Zhejiang, China · School of Computer Science, University of Auckland, Auckland, New Zealand
OutageDiT: A Generative Foundation Model for Power Outage Forecasting and Scenario Simulation
Sep 1, 2026Yunqin Zhu, Feng Qiu, Yao XieConditional Generative Modeling Time-Series Foundation Models
H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology · Argonne National Laboratory
Poisson-Gamma Dynamical Systems with Time-varying Transition Dynamics
Sep 1, 2026Jiahao Wang, Yijun Wang, Nan Fang +1Dynamical Systems Probabilistic Time Series Forecasting
Department of Electrical and Computer Engineering, University of Arizona, US · School of Computing and Information Technology, Great Bay University, China · Tsinghua University, China +1
DecoVAE: a Lightweight Interpretable Trend-Seasonal VAE Framework for Efficient Probabilistic Time Series Forecasting
Aug 20, 2026Alexander Marusov, Dmitry Anikin, Alexey ZaytsevVariational Autoencoders Time Series Forecasting
Applied AI Institute Moscow, Russia
CLaST: Context-aware Contrastive VAE for Probabilistic Time Series Forecasting
Aug 20, 2026Alexander Marusov, Dmitry Anikin, Petr Sokerin +3Variational Autoencoders Multivariate Time Series Forecasting
Applied AI Institute Moscow, Russia
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
Long-Horizon Forecasting of Complete Financial Statements with Forma
Aug 11, 2026Travis L. Johnson, Jiannan Jiang, Soumyabrata Chaudhuri +3Long-Term Time Series Forecasting Financial Forecasting
University of Texas at Austin, Austin, TX, USA
Two-stage Odd Residual Flows for Mean-Preserving Probabilistic Time Series Forecasting
Aug 11, 2026Kiran Madhusudhanan, Christian Klötergens, Lars Schmidt-Thieme +1Long-Term Time Series Forecasting Normalizing Flows
Institute of Computer Science University of Hildesheim Hildesheim, Germany
Evaluating Generative Time-Series Models on Data with Point Masses
Aug 10, 2026Jian XuTime Series Forecasting Time Series Generation
RIKEN iTHEMS, Wako, Japan · RIKEN Center for Advanced Intelligence Project (AIP), Tokyo, Japan
KReF: Training-Free Retrieval for Long-Term Time-Series Forecasting and Predictive Uncertainty
Aug 7, 2026Yang Zhang, Rui SuLong-Term Time Series Forecasting Retrieval-Augmented Time Series Forecasting
FarSky: Task-Aware Latent-Space Coupling for Generative Intra-Hour Solar Forecasting
Aug 6, 2026Yann Fabel, Bijan Nouri, Milon Miah +4Time Series Forecasting Solar Power Forecasting
1DLR, Institute of Solar Research · 2RWTH Aachen University · 3CIEMAT, Energy Department, Renewable Energy Division

Oct 7, 2026, cs.LGJ/K move · Enter open · S save

Seq-Flow: Efficient Probabilistic Forecasting with Self-Rollout Error Control

Yinan Huang, Shitij Govil, Bo Dai, Pan Li

Georgia Institute of Technology

Probabilistic Forecasting Probabilistic Time Series Forecasting Flow-Based Generative Modeling Continuous Normalizing Flows

Open paper AskPDF arXiv

Many scientific forecasting tasks require updating a distribution over future trajectories as new observations arrive. Conventional diffusion and flow models generate each forecast from Gaussian noise, often at the cost of many sampling steps. Warm-start methods reuse earlier predictions to reduce this cost, but their models are not trained to perform the forecast update itself, which can compromise quality under few-step sampling. In this work, we introduce Seq-Flow, a conditional flow model whose ODE transports samples from the previous forecast distribution to the updated one. Because successive forecasts often differ only modestly, this transport starts from an informative distribution and can produce accurate updates with few flow evaluations. Recursive reuse also creates a challenge: errors in one forecast become errors in the initial states of subsequent flows. We address this with self-rollout training, in which a moving average copy of the model generates forecasts that initialize later training updates. Unlike self-forcing methods, which reuse generated outputs as conditioning context, Seq-Flow reuses them as the source of the next flow. Experiments On particle-accelerator beam spill forecasting show Seq-Flow reduces CRPS by 65% under a few-NFE sampling budget, while remaining competitive with strong baselines on fluid-dynamics forecasting tasks. Although trained on self-rollouts of at most four updates, Seq-Flow remains accurate over more than 400 consecutive updates. Our code is available at https://github.com/Graph-COM/Seq-Flow.

Momentum

Related topics

Latest papers 112