| 2025 | AAAI | E4: Energy-Efficient DNN Inference for Edge Video Analytics via Early Exiting and DVFS. | Ziyang Zhang, Yang Zhao, Ming-Ching Chang, Changyao Lin, Jie Liu |
| 2025 | SENSYS | E3: Early Exiting with Explainable AI for Real-Time and Accurate DNN Inference in Edge-Cloud Systems. | Changyao Lin, Zhenming Chen, Ziyang Zhang, Jie Liu |
| 2025 | SENSYS | Exploiting Operator-Level Concurrency Control to Guide Deployment for Real-Time Tasks in Edge AI Cluster. | Changyao Lin, Ziyang Zhang, Jie Liu |
| 2024 | ICPR | StressViT: Splitting and Compressing Vision Transformer Through Edge-Cloud Collaboration. | Changyao Lin, Yi Liu, Xiangyu Li, Chengxiang Li, Hao Zhang, Jing Jin, Jie Liu |
| 2024 | IWQoS | COS: Cross-Processor Operator Scheduling for Multi-Tenant Deep Learning Inference. | Changyao Lin, Jie Liu |
| 2024 | IWQoS | A QoS-Aware Training Framework for ViT Compression, Partition, and Distillation. | Changyao Lin, Chengxiang Li, Jie Liu |
| 2021 | ICPADS | Choosing Appropriate AI-enabled Edge Devices, Not the Costly Ones. | Ziyang Zhang, Feng Li, Changyao Lin, Shihui Wen, Xiangyu Liu, Jie Liu |
| 2021 | SENSYS | ECSRL: A Learning-Based Scheduling Framework for AI Workloads in Heterogeneous Edge-Cloud Systems. | Changyao Lin, Ziyang Zhang, Huan Li, Jie Liu |