DiffPTS rethinks the evidence lower bound (ELBO) for diffusion-based probabilistic time‑series forecasting by adopting a Location‑Scale Noise Model, which yields a Gaussian negative log‑likelihood objective and a unified joint training objective. The framework enables end‑to‑end optimization of all components within the ELBO, unlike prior methods that treat estimator training as separate regression tasks. On multiple benchmarks, DiffPTS achieves state‑of‑the‑art performance, reducing CRPS/MSE by over 14.53%/16.55% compared to existing diffusion‑based models.
By Weiwei Ye, Dongyuan Li, Hangchen Liu, Haotong Jiang, Yoshihide Sekimoto, Renhe Jiang
arXiv:2606.21036v2 Announce Type: replace-cross
Abstract: In many domains, practitioners seek models that produce accurate forecasts while faithfully capturing latent system dynamics. Existing approa...
By Jack Ruder, Michael Wojnowicz
arXiv:2607. 17972v1 Announce Type: new Abstract: The prevailing inference framework for diffusion models formulates generation fundamentally as a problem of numerical integration.
By Shigui Li, Delu Zeng
Just Weather Scoring (JWS) is a single‑stage, end‑to‑end diffusion model that forecasts precipitation directly in radar space, eliminating the need for separate compression or deterministic components. By combining Masked Asynchronous Diffusion with a scoring‑rule objective, JWS adapts diffusion training to high‑dimensional spatio‑temporal data and enables few‑step generation. On SEVIR and MeteoNet benchmarks, JWS achieves state‑of‑the‑art probabilistic forecasting while using fewer parameters and delivering over 17× faster inference than existing methods.
By Jannik Wiese, Johannes Schusterbauer, Tommaso Martorella, Bj\"orn Ommer
The paper introduces a new diffusion-based approach for probabilistic weather forecasting that incorporates auxiliary conditional denoising tasks. By predicting future states from both clean and corrupted contexts, the model reduces ambiguity and learns conditional distributions across noise levels using a proper scoring rule. Experiments demonstrate improved one‑step forecasting, especially at longer horizons, and better calibration in high‑dimensional global weather scenarios.
By Joonhyeong Park, Giung Nam, Hyungi Lee, Kyunghyun Cho, Byoungwoo Park, Juho Lee
arXiv:2607. 22599v1 Announce Type: new Abstract: Diffusion models have become a widely used framework for probabilistic time series forecasting, modeling the distribution of future values given an observed history.
By Chen Su, Yuanhe Tian, Yan Song
DiTS introduces a Multimodal Diffusion Transformer designed for time‑series forecasting that incorporates heterogeneous exogenous covariates. The model treats endogenous targets and exogenous covariates as separate modalities, jointly conditioning future generation on target history and available covariates. By employing flow matching and Time‑aligned Modulation, DiTS achieves strong deterministic and probabilistic forecasting performance across diverse covariate‑aware tasks.
By Haoran Zhang, Haixuan Liu, Yong Liu, Yunzhong Qiu, Yuxuan Wang, Jianmin Wang, Mingsheng Long
KiT is a K‑line Diffusion Transformer foundation model designed for financial time‑series forecasting. It reframes future prediction as conditional path generation via flow matching, producing ensembles of plausible OHLCV trajectories from a historical context window. Trained on billions of candlestick bars across multiple markets and timescales, KiT achieves superior RankIC scores compared to task‑specific forecasters and general time‑series models.
Probabilistic multivariate time series (MTS) forecasting is crucial for modeling complex dynamical systems. However, existing diffusion-based methods rely on task-specific conditional paradigms that l...
arXiv:2607. 12391v1 Announce Type: new Abstract: We present a diffusion based model for asynchronous time series prediction, where the goal is to predict the next inter event time and event type.
By Saiyue Lyu, Zhitian Zhang, Ruizhi Deng, Thibaut Durand
arXiv:2601.21151v3 Announce Type: replace
Abstract: Machine-learning approaches to weather forecasting often employ a monolithic architecture in which distinct physical mechanisms, such as advection,...
By Carlos A. Pereira, St\'ephane Gaudreault, Valentin Dallerit, Christopher Subich, Shoyon Panday, Siqi Wei, Sasa Zhang, Siddharth Rout, Eldad Haber, Raymond J. Spiteri, David Millard
arXiv:2609.37038v1 Announce Type: cross
Abstract: Precipitation nowcasting demands accurate short-term forecasts under strong spatiotemporal variability. Diffusion models are well suited to modeling...
By Haoran Xu, Xingzhuo Guo, Yuchen Zhang, Jincheng Zhong, Jianmin Wang, Mingsheng Long