arXiv:2610.33822v1 Announce Type: cross
Abstract: A central challenge in multivariate forecasting is deciding what to share across channels and where to specialize. Mixture-of-experts models offer fl...
By Bashar Khoury, Shadi Omari, Assaf Schuster
AdaCast introduces a conditional parameter generation framework that tailors time‑series forecasting models to each input by producing low‑rank updates for a frozen pretrained foundation model. Unlike static adaptation methods that apply a single set of updates to all inputs, AdaCast generates input‑specific updates during both training and inference. Experiments on six public benchmarks show that AdaCast consistently outperforms static baselines in in‑domain forecasting and improves zero‑shot generalization to unseen datasets across domains.
By Darahaas Nallagatla, Darryl Cherian Jacob, Pan He
arXiv:2606. 10678v1 Announce Type: new Abstract: Transformer-based models have emerged as leading paradigms in time-series forecasting in recent years, employing self-attention mechanisms to capture long-range dependencies.
By Amrijit Biswas, Mustafa Kamal, Robin Krambroeckers, M. M. Lutfe Elahi, Sifat Momen, Nabeel Mohammed, Shafin Rahman
The paper introduces Chameleon, a channel‑dependent state space model for multivariate time series forecasting that allows data‑dependent, fine‑grained interactions across variables while maintaining linear scaling with the number of variables. By integrating selective state space models with a Kalman filter and adapting GatedDeltaNet as the backbone, Chameleon improves generalization and achieves lower MSE and MAE on strongly dependent ODE and PEMS datasets compared to both channel‑independent and prior channel‑dependent methods. Across 28 benchmark settings, it outperforms baselines in the majority of cases and demonstrates competitive training‑time and memory efficiency on Traffic and ETT datasets.
By Yu-Cheng Wu, Fan-Keng Sun, Li-Chun Lu, Duane S. Boning
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
arXiv:2607. 18899v1 Announce Type: new Abstract: Forecasting under real-world conditions is inherently non-stationary, as the conditional distribution of future observations evolves over time.
By Giuseppe Soriano, Nicola Tonellotto, Alberto Gotta