| 2026 | EACL | DRAGON: Domain-specific Robust Automatic Data Generation for RAG Optimization. | Haiyang Shen, Hang Yan, Zhongshi Xing, Mugeng Liu, Yue Li, Zhiyang Chen, Yuxiang Wang, Jiuzheng Wang, Yun Ma |
| 2026 | WWW | LaTune: Lightweight and Adaptive Configuration Tuning for LLM Inference on Edge Devices. | Siqi Zhong, Mugeng Liu, Haiyang Shen, Chongyang Pan, Yun Ma |
| 2026 | SIGIR | MCP-Focus: Leveraging Function-Oriented Document Enhancement for MCP Server Retrieval. | Wenchun Jing, Haiyang Shen, Haoran Wang, Qi Liu, Ningyuan Li, Chaoran Luo, Ning Zhang, Yun Ma |
| 2025 | ICLR | ShortcutsBench: A Large-Scale Real-world Benchmark for API-based Agents. | Haiyang Shen, Yue Li, Desong Meng, Dongqi Cai, Sheng Qi, Li Zhang, Mengwei Xu, Yun Ma |
| 2025 | WWW | WeInfer: Unleashing the Power of WebGPU on LLM Inference in Web Browsers. | Zhiyang Chen, Yun Ma, Haiyang Shen, Mugeng Liu |
| 2023 | ICWS | ADPal: Automatic Detection of Troubled Users in Online Service Systems via Page Access Logs. | Haiyang Shen, Yun Ma, Yue Li, Xiaoling Wang, Deyu Tian, Tong Jia, Tengfei He, Shenghua Luo |
| 2022 | Mobisys | Parallelizing DNN inference in mobile web browsers on heterogeneous hardware. | Deyu Tian, Haiyang Shen, Yun Ma |