3 papers
cs.LG2025
TimeExpert: Boosting Long Time Series Forecasting with Temporal Mix of Experts
Xiaowen Ma, Shuning Ge, Fan Yang +5
Transformer-based architectures dominate time series modeling by enabling global attention over all timestamps, yet their rigid 'one-size-fits-all' context aggregation fails to add…
cs.LG2025
From Noise to Precision: A Diffusion-Driven Approach to Zero-Inflated Precipitation Prediction
Wentao Gao, Jiuyong Li, Lin Liu +6
Zero-inflated data pose significant challenges in precipitation forecasting due to the predominance of zeros with sparse non-zero events. To address this, we propose the Zero Infla…
cs.CL2025
TAG-INSTRUCT: Controlled Instruction Complexity Enhancement through Structure-based Augmentation
He Zhu, Zhiwen Ruan, Junyou Su +4
High-quality instruction data is crucial for developing large language models (LLMs), yet existing approaches struggle to effectively control instruction complexity. We present TAG…