PathFM is a trajectory-based forecasting model that uses flow matching to generate complete future paths for multivariate time series. It distills the sampling process to one or two steps, sharing a history attention cache across draws, allowing multiple path generation in roughly the time of a single quantile query. The model achieves competitive marginal accuracy on fev-bench and TIME, and outperforms baselines on the new Forecast Path Score Bench (fps‑bench) with energy, variogram, and downstream metrics, while maintaining long‑run variability in chaotic systems.
By Jiachen Yao, Xiyuan Zhang, Annan Yu, Boran Han, Abdul Fatir Ansari, Shuai Zhang, Michael Bohlke-Schneider, Bernie Wang
arXiv:2609.13640v1 Announce Type: new
Abstract: Encoder-based time series foundation models (TSFMs) typically rely on deep stacks of independently parameterized Transformer layers, where only the fin...
By Bahaeddine Abdessalem, Shifeng Xie, Zehao Xiao, Youssef Attia El Hili, Ambroise Odonnat, Jianfeng Zhang, Lujia Pan, Keli Zhang, Malik Tiomoko
Irregular multivariate time series forecasting (IMTSF) requires capturing temporal dynamics and cross-variable dependencies from sparse, asynchronous observations. Existing methods often rely on learn...
The paper introduces Quantile-Guided Diffusion for Probabilistic Time-Series Forecasting, showing that integrating predicted quantiles as distributional controls can guide a pretrained diffusion forecaster. The authors find that applying residual control throughout the denoising network yields the most consistent improvements, leading to the Control-TS model that learns a quantile-control pathway while keeping the backbone frozen. Across eight benchmarks, Control-TS improves the backbone’s CRPS, competes with state‑of‑the‑art models, and retains gains in capacity‑matched comparisons, with further analyses on quantile granularity, predictor choice, and forecast quality. The study also presents the Conditional Linear Predictive Score (CLPS) to evaluate downstream forecasting utility of generated futures.
By Shadi Omari, Bashar Khoury, Assaf Schuster
Aurora‑X is a billion‑parameter time‑series foundation model designed for extreme forecasting tasks. It employs a progressive curriculum that starts with channel‑independent pretraining, then adds cross‑variable dependencies, variable context and horizon lengths, and optional future covariates during mid‑training. A variable‑resolution post‑training stage allows adjustable temporal spans per token at inference, while a pattern‑guided mixture‑of‑experts expands capacity through sparse activation and expert specialization. An implicit quantile network head predicts arbitrary quantiles, enhancing probabilistic forecasting flexibility. Experiments on GIFT‑Eval, TIME, FEV‑Bench, TFB, and DAG‑Bench show state‑of‑the‑art performance against both pretrained TSFMs and task‑specific supervised models.
By Xingjian Wu, Chenjuan Guo, Xiangfei Qiu, Zhigang Hu, Hanyin Cheng, Peng Chen, Yang Shu, Jilin Hu, Bin Yang
The paper introduces DV-Flow, a flow‑matching framework that treats deterministic prediction as a parallel velocity component instead of embedding it within the generative process. This design stabilizes end‑to‑end training and unifies several existing methods as special cases, enabling direct comparison. Experiments on six real‑world datasets show that DV‑Flow consistently outperforms strong baselines in probabilistic time‑series forecasting.
arXiv:2605. 05540v2 Announce Type: replace Abstract: Fast surrogate modeling for high-dimensional physical dynamics requires more than low short-term error: useful models must roll out efficiently while preserving the statistical structure of long trajectories.
By Tianyue Yang, Xiao Xue
arXiv:2606. 03184v1 Announce Type: cross Abstract: Financial forecasting is difficult due to low signal-to-noise ratios, latent factors, heavy tails, regime shifts, and jumps.
By Jiaze Sun, Kelvin J. L. Koa, Ruiyang Ni, Yize Liu, Haonan Chen, Ke-Wei Huang
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
ProtoFlow is a new multivariate time series forecasting framework that combines vector‑quantized autoencoding with prototype‑guided flow matching. It maps sequences into a discrete latent space, constructs a structured prior from the learned VQ codebook, and trains a DiT‑based rectified flow to transport samples from this prior to future latent representations conditioned on past observations. By replacing generic Gaussian noise with a learned prototype prior, ProtoFlow eliminates autoregressive rollout mismatch and achieves faster training convergence while delivering superior forecasting performance on benchmark datasets.
By Shibo Feng, Wanjin Feng, Yang Qiu, Deheng Ye, Peilin Zhao, Chunyan Miao
FLAME is a lightweight Time Series Foundation Model that uses Legendre Memory variants (LegT and LegS) in its encoding and decoding stages to capture inductive biases and perform efficient long‑range forecasting. It incorporates a normalizing‑flow forecasting head to generate complex probabilistic distributions over future horizons. Experiments on TSFM‑Bench, ProbTS, and TFB show FLAME performs strongly as an out‑of‑the‑box tool for decision intelligence.
By Xingjian Wu, Zhengyu Li, Hanyin Cheng, Xiangfei Qiu, Jilin Hu, Chenjuan Guo, Bin Yang
GateTS introduces a streamlined univariate forecasting model that merges sparse Mixture-of-Experts computation with an attention-inspired gating mechanism, eliminating the need for auxiliary load‑balancing losses. The architecture achieves superior predictive accuracy across both short‑ and long‑term horizons, including intermittent signals, while using far fewer parameters than leading transformer models such as PatchTST. Empirical tests on diverse datasets show GateTS is computationally more efficient than LSTM, enabling cost‑effective inference for real‑world time‑series applications.
By Kyrylo Yemets, Mykola Lukashchuk, Ivan Izonin