Wenzhe Niu

Ranking is Reward: Intra-Group Preference Ranking for Group Relative Policy Optimization

Adapting LLMs to Time Series Forecasting via Temporal Heterogeneity Modeling and Semantic Alignment

One Instruction Is a Benchmark: End-to-End Instruction-Following Evaluation with FlexBench

LangTime: A Language-Guided Unified Model for Time Series Forecasting with Proximal Policy Optimization

Token-by-Token Election: Improving Language Model Reasoning through Token-Level Multi-model Collaboration