2

FaaSLearner: Resource-Efficient Edge Video Analytics via Correlation-aware Multi-model Continual Learning
FaaSLearner: Resource-Efficient Edge Video Analytics via Correlation-aware Multi-model Continual Learning. Published in IEEE Trans. on Mobile Computing. To appear.
InfSquad: SLO-aware Serverless Machine Learning Inference with Wasm-assisted Hybrid Functions
InfSquad: SLO-aware Serverless Machine Learning Inference with Wasm-assisted Hybrid Functions. Published in IEEE Trans. on Services Computing. To appear.
AI-Native Computing for Distributed Cloud-Edge-Device Collaboration
AI-Native Computing for Distributed Cloud-Edge-Device Collaboration. Published in Computing, Vol. 1, Issue 8, pp. 38-45.
PDF Source Document
Real-Batch: Real-time Adaptive Batch Processing for Accurate Object Detection in Autonomous Driving
Real-Batch: Real-time Adaptive Batch Processing for Accurate Object Detection in Autonomous Driving. Published in IEEE Trans. on Mobile Computing. To appear.
Jarvis: Zero-code Prototyping of IoT Applications with Composable Hardware-Software Abstractions
Jarvis: Zero-code Prototyping of IoT Applications with Composable Hardware-Software Abstractions. Published in ACM Trans. on Internet of Things. Volume 6, Issue 4, Article No.: 27, Pages 1 - 27. DOI: 10.1145/3762670.
DOI
FluidEdge: Expediting Serverless Machine Learning Inference via Bottleneck-aware Auto-scaling on Edge SoCs
FluidEdge: Expediting Serverless Machine Learning Inference via Bottleneck-aware Auto-scaling on Edge SoCs. Published in IEEE Trans. on Mobile Computing. Volume: 24, Issue: 12, December 2025, pp. 13586 - 13599. DOI: 10.1109/TMC.2025.3592334.
DOI
nnWeb: Towards Efficient WebGPU-based DNN Inference via Automatic Collaborative Offloading
nnWeb: Towards Efficient WebGPU-based DNN Inference via Automatic Collaborative Offloading. Published in Computer Networks. Volume 270, October 2025, 111489. DOI: 10.1016/j.comnet.2025.111489.
DOI
Collaborative Model Inference for Edge AI: A Deviceless Approach
Collaborative Model Inference for Edge AI: A Deviceless Approach. Published in Communications of CCF, Vol. 21, No. 3, March 2025.
Exploiting Multiple Similarity Spaces for Deduplication of Encrypted Container Images
Exploiting Multiple Similarity Spaces for Deduplication of Encrypted Container Images. Published in ACM Trans. on Storage. To appear.
From Perception to Computation: Revisiting Delay Optimization for Connected Autonomous Vehicles
From Perception to Computation: Revisiting Delay Optimization for Connected Autonomous Vehicles. Published in ACM Computing Surveys. Volume 57, Issue 8, Article No.: 200, Pages 1 - 45.