Multivariate time series forecasting remains a challenge due to the complexity of local temporal dynamics and global dependencies across multiple variables. In this paper, we propose \textbf{N}eighboring \textbf{P}atching \textbf{Mixer} (\textbf{NPMixer}), a hierarchical architec…
Multivariate time series forecasting remains a challenge due to the complexity of local temporal dynamics and global dependencies across multiple variables. In this paper, we propose \textbf{N}eighboring \textbf{P}atching \textbf{Mixer} (\textbf{NPMixer}), a hierarchical architec…
arXiv:2605.05540v1 Announce Type: new 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. Neural operators provid…
arXiv:2605.05685v1 Announce Type: new Abstract: Unlike MLPs, Kolmogorov-Arnold Networks (KANs) expose explicit learnable edge functions on every connection, enabling mechanistic explanation in time-series forecasting. This paper introduces Temporal Functional Circuits, a framewor…
arXiv:2605.06310v1 Announce Type: new Abstract: Local temporal patterns in real-world time series continuously shift, rendering globally shared transformations suboptimal. Current deep forecasting models, despite their scale and complexity, rely on fixed weight matrices applied u…
arXiv cs.LG
TIER_1English(EN)·Zheng Li, Jerry Cheng, Huanying Gu·
arXiv:2602.02288v2 Announce Type: replace Abstract: Current time-series forecasting models are primarily based on transformer-style neural networks. These models achieve long-term forecasting mainly by scaling up the model size rather than through genuinely autoregressive (AR) ro…
arXiv cs.AI
TIER_1English(EN)·Christine P. Lee, Min Kyung Lee, Bilge Mutlu·
arXiv:2605.03078v1 Announce Type: new Abstract: While AI is often introduced into organizations to drive innovation and efficiency, many adoption efforts fail as workers resist and struggle to integrate these systems. These failures point to a deeper issue: workers, the very peop…
arXiv:2605.03789v1 Announce Type: cross Abstract: We propose Conformal Seasonal Pools (CSP), a training-free probabilistic time-series forecaster that mixes same-season empirical draws with signed residual draws around a seasonal naive forecast. In an audited rolling-origin bench…
We propose Conformal Seasonal Pools (CSP), a training-free probabilistic time-series forecaster that mixes same-season empirical draws with signed residual draws around a seasonal naive forecast. In an audited rolling-origin benchmark on the six time-series datasets where DeepNPT…
arXiv:2507.15774v2 Announce Type: replace Abstract: While deep learning is facing an homogenization across modalities led by Transformers, they are still challenged by shallow linear models in the time-series forecasting task. Our hypothesis is that models should learn a direct l…
Unlike MLPs, Kolmogorov-Arnold Networks (KANs) expose explicit learnable edge functions on every connection, enabling mechanistic explanation in time-series forecasting. This paper introduces Temporal Functional Circuits, a framework that transforms KAN edge functions from latent…
arXiv cs.CV
TIER_1English(EN)·Siyang Li, Yize Chen, Zijie Zhu, Yuxin Pan, Yan Guo, Ming Huang, Hui Xiong·
arXiv:2605.00015v1 Announce Type: cross Abstract: Time Series Foundation Models (TSFMs) advance generalization and data efficiency in time series forecasting by unified large-scale pretraining. But TSFMs remain lacking when adapting to specific downstream forecasting tasks for tw…
