Lingxiao Du

MCPMark: A Benchmark for Stress-Testing Realistic and Comprehensive MCP Use

MM-PRM: Enhancing Multimodal Mathematical Reasoning with Scalable Step-Level Supervision

MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning

CPGD: Toward Stable Reinforcement Learning for Language Models

OWMM-Agent: Open World Mobile Manipulation With Multi-modal Agentic Data Synthesis