3 papers
cs.LG2025
RI-Loss: A Learnable Residual-Informed Loss for Time Series Forecasting
Jieting Wang, Xiaolei Shang, Feijiang Li +1
Time series forecasting relies on predicting future values from historical data, yet most state-of-the-art approaches-including transformer and multilayer perceptron-based models-o…
cs.CL2025
ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization
Zhensheng Jin, Xinze Li, Yifan Ji +7
Recent advances in Chain-of-Thought (CoT) prompting have substantially improved the reasoning capabilities of Large Language Models (LLMs). However, these methods often suffer from…
cs.LG2024
TSC: A Simple Two-Sided Constraint against Over-Smoothing
Furong Peng, Kang Liu, Xuan Lu +3
Graph Convolutional Neural Network (GCN), a widely adopted method for analyzing relational data, enhances node discriminability through the aggregation of neighboring information.…