2 papers
cs.LG2026
Plan and Budget: Effective and Efficient Test-Time Scaling on Reasoning Large Language Models
Junhong Lin, Xinyue Zeng, Jie Zhu +4
Large Language Models (LLMs) have achieved remarkable success in complex reasoning tasks, but their inference remains computationally inefficient. We observe a common failure mode…
cs.LG2025
Gradient Boosting Decision Tree with LSTM for Investment Prediction
Chang Yu, Fang Liu, Jie Zhu +5
This paper proposes a hybrid framework combining LSTM (Long Short-Term Memory) networks with LightGBM and CatBoost for stock price prediction. The framework processes time-series f…