3 papers
cs.CL2025
Proof2Hybrid: Automatic Mathematical Benchmark Synthesis for Proof-Centric Problems
Yebo Peng, Zixiang Liu, Yaoming Li +6
Evaluating the mathematical capability of Large Language Models (LLMs) is a critical yet challenging frontier. Existing benchmarks fall short, particularly for proof-centric proble…
cs.LG2025
ReFocus: Reinforcing Mid-Frequency and Key-Frequency Modeling for Multivariate Time Series Forecasting
Guoqi Yu, Yaoming Li, Juncheng Wang +4
Recent advancements have progressively incorporated frequency-based techniques into deep learning models, leading to notable improvements in accuracy and efficiency for time series…
cs.LG2025
LiNo: Advancing Recursive Residual Decomposition of Linear and Nonlinear Patterns for Robust Time Series Forecasting
Guoqi Yu, Yaoming Li, Xiaoyu Guo +4
Forecasting models are pivotal in a data-driven world with vast volumes of time series data that appear as a compound of vast Linear and Nonlinear patterns. Recent deep time series…