PPL
Han Xiao
Papers (5)
ReaderLM-v2: Small Language Model for HTML to Markdown and JSONUI-KOBE: Knowledge-Oriented Behavior Exploration for Lightweight Graph-Guided GUI AgentsMobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent ResearchTest-Time Compute for Dense Retrieval: Agentic Program Generation with Frozen Embedding ModelsPiCA: Pivot-Based Credit Assignment for Search Agentic Reinforcement Learning