PPL
Xin Chen
Papers (6)
InternLM2 Technical ReportOn-Policy Replay for Continual Supervised Fine-TuningSCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-based Humanoid ControlMulti-Objective and Mixed-Reward Reinforcement Learning via Reward-Decorrelated Policy OptimizationRELO: Reinforcement Learning to Localize for Visual Object TrackingPreference Instability in Reward Models: Detection and Mitigation via Sparse Autoencoders