Skip to content

Author

Guoliang Li

We have 5 of 33 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Open access Sep 2026

HeraDB: Towards Real-time Analysis of Transaction-Centric HTAP with CPU-GPU Hybrid Query Execution

Modern OLTP applications, such as financial fraud detection and stock risk management, rely on analytical queries for real-time decision-making. In these scenarios, queries must access the freshest data without disrupting the performance of mission-critical transactions. We characterize them as transaction-centric...

Ze-Shun Peng, Qin-Cheng Cai, Si-Yuan Wei et al. · 0 citations
Aug 2026

MoDora: A Multimodal Document AI Assistant Harness

MoDora is presented, an interactive, tree-structured multimodal document analysis agent harness designed to make the document analysis process transparent and controllable, and introduces an end-to-end user experience through three core functionalities.

Yu-Kai Wu, Bang-Rui Xu, Shao-Lin Yu et al. · 0 citations
Review Aug 2026

Data Management for Agentic Memory: Foundations, Systems, and Challenges

This tutorial introduces the workflow and architecture of agentic memory systems, and summarizes their operators, storage, and optimization techniques, aiming to inspire further innovation and progress in this exciting field.

Guo-Liang Li, Jia-Qi Tian, Xuan-He Zhou · 0 citations
Aug 2026

DBCooker : A Database Kernel-Specialized Coding Agent Harness

Conference attendees will experience how DBCooker seamlessly transforms high-level SQL function requests into validated, kernel-ready code for mainstream databases (e.g., SQLite, PostgreSQL, DuckDB).

Wei Zhou, Xuan-He Zhou, Qi-Kang He et al. · 1 citation
Aug 2026

Bridging NL2SQL for CAN Signal Analytics at NIO: From Externalized Schemas to CTE Pipelines

NIO-Weaver is presented, an end-to-end CAN signal analytics system within a graph-augmented multi-agent framework that outperforms baselines by up to 67.2% and an optimized retrieval method that extracts terms from queries and performs hybrid retrieval is proposed.

Wei Zhou, Hao-Yu Zhao, Rui-Guang Zhong et al. · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.