Yiyun Su
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yiyun Su has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
Baihua Li
Loughborough University
1 shared publicationChangruo Zhao
Rensselaer Polytechnic Institute
1 shared publication- Chao Li
Georgetown University, New York, USA
1 shared publication - Fang Sun
The George Washington University, Washington, USA
1 shared publication Huiying Zhu
Bytedance
1 shared publicationJiaqing Shen
1 shared publication
Latest Publications
- Open Access
- 24 March 2026
- Published by Wiley
Agentic-SQL Taxonomy: A Survey of Autonomous and Interactive Text-to-SQL with LLMs
Text-to-SQL systems have transitioned from simple machine translation models to complex reasoning frameworks as database schemas grow in scale and ambiguity. Despite the impressive capabilities of Large Language Models, one-shot generation often fails to produce correct SQL in real-world scenarios. This survey introduces the Agentic-SQL Taxonomy, an autonomy-based classification [21] that reevaluates existing methods through the lens of inference complexity. We categorize research into single-turn generation, iterative refinement, and multi-agent collaboration to highlight the shift toward interactive debugging and collective reasoning. We analyze how these sophisticated pipelines bridge the performance gap on challenging benchmarks. Current evaluations show that leading models can result in incorrect execution in nearly 40 % of cases when instructions are vague or incomplete. Our work identifies executionguided feedback and modular agent architectures as the primary drivers of future progress in building robust and reliable database interfaces.
- 24 March 2026
- Published by Wiley
Open AccessAgentic-SQL Taxonomy: A Survey of Autonomous and Interactive Text-to-SQL with LLMs
Text-to-SQL systems have transitioned from simple machine translation models to complex reasoning frameworks as database schemas grow in scale and ambiguity. Despite the impressive capabilities of Large Language Models, one-shot generation often fails to produce correct SQL in real-world scenarios. This survey introduces the Agentic-SQL Taxonomy, an autonomy-based classification [21] that reevaluates existing methods through the lens of inference complexity. We categorize research into single-turn generation, iterative refinement, and multi-agent collaboration to highlight the shift toward interactive debugging and collective reasoning. We analyze how these sophisticated pipelines bridge the performance gap on challenging benchmarks. Current evaluations show that leading models can result in incorrect execution in nearly 40 % of cases when instructions are vague or incomplete. Our work identifies executionguided feedback and modular agent architectures as the primary drivers of future progress in building robust and reliable database interfaces.
- Open Access
- 25 February 2026
- Published by Wiley
Intelligent Anti-Money Laundering on Cryptocurrency A CNN-GNN Fusion Approach
The decentralized structure of cryptocurrency has changed modern finance, but its anonymity also allows for many illegal acts such as money laundering, phishing, and other frauds. This paper presents a hybrid detection system. It combines Convolutional Neural Networks (CNN) and Graph Neural Networks (GNN) to find suspicious Ethereum transactions. We use data from May 2022, June 2022, and July 2024. CNNs pull out local transaction details. GNNs map how accounts connect. The node features are then classified with ensemble tools like Random Forest and XGBoost. This brings clear gains over older models-up to 5.79% higher precision and 18.1% higher recall. Tests on July 2024 data spotted new fraud types, including NFT scams and WazirX hack-linked transfers. This shows the model works well for protecting DeFi systems. CCS CONCEPTS Mathematics of computing ~Probability and statistics ~Probabilistic inference problems
- 25 February 2026
- Published by Wiley
Open AccessIntelligent Anti-Money Laundering on Cryptocurrency A CNN-GNN Fusion Approach
The decentralized structure of cryptocurrency has changed modern finance, but its anonymity also allows for many illegal acts such as money laundering, phishing, and other frauds. This paper presents a hybrid detection system. It combines Convolutional Neural Networks (CNN) and Graph Neural Networks (GNN) to find suspicious Ethereum transactions. We use data from May 2022, June 2022, and July 2024. CNNs pull out local transaction details. GNNs map how accounts connect. The node features are then classified with ensemble tools like Random Forest and XGBoost. This brings clear gains over older models-up to 5.79% higher precision and 18.1% higher recall. Tests on July 2024 data spotted new fraud types, including NFT scams and WazirX hack-linked transfers. This shows the model works well for protecting DeFi systems. CCS CONCEPTS Mathematics of computing ~Probability and statistics ~Probabilistic inference problems
- Open Access
- 9 January 2026
- Published by Association for Computing Machinery (ACM)
- p. 625-629
Intelligent Anti-Money Laundering on Cryptocurrency: A CNN-GNN Fusion Approach
The decentralized structure of cryptocurrency has changed modern finance, but its anonymity also allows for many illegal acts such as money laundering, phishing, and other frauds. This paper presents a hybrid detection system. It combines Convolutional Neural Networks (CNN) and Graph Neural Networks (GNN) to find suspicious Ethereum transactions. We use data from May 2022, June 2022, and July 2024. CNNs pull out local transaction details. GNNs map how accounts connect. The node features are then classified with ensemble tools like Random Forest and XGBoost. This brings clear gains over older models—up to 5.79% higher precision and 18.1% higher recall. Tests on July 2024 data spotted new fraud types, including NFT scams and WazirX hack-linked transfers. This shows the model works well for protecting DeFi systems.
- 9 January 2026
- Published by Association for Computing Machinery (ACM)
- p. 625-629
Open AccessIntelligent Anti-Money Laundering on Cryptocurrency: A CNN-GNN Fusion Approach
The decentralized structure of cryptocurrency has changed modern finance, but its anonymity also allows for many illegal acts such as money laundering, phishing, and other frauds. This paper presents a hybrid detection system. It combines Convolutional Neural Networks (CNN) and Graph Neural Networks (GNN) to find suspicious Ethereum transactions. We use data from May 2022, June 2022, and July 2024. CNNs pull out local transaction details. GNNs map how accounts connect. The node features are then classified with ensemble tools like Random Forest and XGBoost. This brings clear gains over older models—up to 5.79% higher precision and 18.1% higher recall. Tests on July 2024 data spotted new fraud types, including NFT scams and WazirX hack-linked transfers. This shows the model works well for protecting DeFi systems.
- Open Access
- 26 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 916-921
Task-Gated Attentive Multi-Task Ensemble Learning for Joint Energy and Latency Prediction in Cloud Telemetry
- 26 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 916-921
Open AccessTask-Gated Attentive Multi-Task Ensemble Learning for Joint Energy and Latency Prediction in Cloud Telemetry