MMODELYST
People/Haiyang Xu
PPL

Haiyang Xu

Papers (3)
STAMP: Training Explicit Memory for Mobile GUI Agents in Controllable and Scalable Virtual EnvironmentsBeyond Trajectory-Level Attribution: Graph-Based Credit Assignment for Agentic Reinforcement LearningToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents