Fanqi Wan

SPELL: Self-Play Reinforcement Learning for Evolving Long-Context Language Models

SoLoPO: Unlocking Long-Context Capabilities in LLMs via Short-to-Long Preference Optimization

FuseRL: Dense Preference Optimization for Heterogeneous Model Fusion

Advantage-Guided Distillation for Preference Alignment in Small Language Models

FuseChat: Knowledge Fusion of Chat Models

Weighted-Reward Preference Optimization for Implicit Model Fusion

Let Large Language Models Find the Data to Train Themselves