collaborators

5 papers

cs.IR2026

MAGE-RAG: Multigranular Adaptive Graph Evidence for Agentic Multimodal RAG in Long-Document QA

Yilong Zuo, Xunkai Li, Jing Yuan +3

Long-document multimodal question answering requires a system to locate sparse evidence in long PDFs and integrate clues from text, tables, images, charts, and complex layouts. Exi…

cs.LG2026

When LLM Agents Meet Graph Optimization: An Automated Data Quality Improvement Approach

Zhihan Zhang, Xunkai Li, Yilong Zuo +5

Text-attributed graphs (TAGs) have become a key form of graph-structured data in modern data management and analytics, combining structural relationships with rich textual semantic…

cs.LG2026

RoleMAG: Learning Neighbor Roles in Multimodal Graphs

Yilong Zuo, Xunkai Li, Zhihan Zhang +2

Multimodal attributed graphs (MAGs) combine multimodal node attributes with structured relations. However, existing methods usually perform shared message passing on a single graph…

cs.LG2026

OpenMAG: A Comprehensive Benchmark for Multimodal-Attributed Graph

Chenxi Wan, Xunkai Li, Yilong Zuo +6

Multimodal-Attributed Graph (MAG) learning has achieved remarkable success in modeling complex real-world systems by integrating graph topology with rich attributes from multiple m…

cs.LG2026

OptiMAG: Structure-Semantic Alignment via Unbalanced Optimal Transport

Yilong Zuo, Xunkai Li, Zhihan Zhang +3

Multimodal Attributed Graphs (MAGs) have been widely adopted for modeling complex systems by integrating multi-modal information, such as text and images, on nodes. However, we ide…