Wei Shen

TreePO: Enhancing Policy Efficacy and Inference Efficiency with Tree Modeling

AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning

HPSERec: A Hierarchical Partitioning and Stepwise Enhancement Framework for Long-tailed Sequential Recommendation

AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning

What Do Latent Action Models Actually Learn?

Policy Filtration for RLHF to Mitigate Noise in Reward Models

AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidence

Exploring Data Scaling Trends and Effects in Reinforcement Learning from Human Feedback

Policy Filtration in RLHF to Fine-Tune LLM for Code Generation