Lang Feng

Hierarchy-of-Groups Policy Optimization for Long-Horizon Agentic Tasks

AnomSeer: Reinforcing Multimodal LLMs to Reason for Time-Series Anomaly Detection

REAR: Scalable Test-time Preference Realignment through Reward Decomposition

Policy Regularization on Globally Accessible States in Cross-Dynamics Reinforcement Learning

Towards Efficient Online Tuning of VLM Agents via Counterfactual Soft Reinforcement Learning

Group-in-Group Policy Optimization for LLM Agent Training

ASOR: Anchor State Oriented Regularization for Policy Optimization under Dynamics Shift