Shuai Wang

Latest

• Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots
• FaaSLearner: Resource-Efficient Edge Video Analytics via Correlation-aware Multi-model Continual Learning
• InfSquad: SLO-aware Serverless Machine Learning Inference with Wasm-assisted Hybrid Functions
• LLM-Flex: Adaptive Heterogeneous Federated Learning Based on LLM in Uncertain Scenarios
• AI-Native Computing for Distributed Cloud-Edge-Device Collaboration
• DigimonGPT: An Evolvable Agent with Hierarchical Human-like Memory for Video Question Answering
• Real-Batch: Real-time Adaptive Batch Processing for Accurate Object Detection in Autonomous Driving
• Jarvis: Zero-code Prototyping of IoT Applications with Composable Hardware-Software Abstractions
• FluidEdge: Expediting Serverless Machine Learning Inference via Bottleneck-aware Auto-scaling on Edge SoCs
• nnWeb: Towards Efficient WebGPU-based DNN Inference via Automatic Collaborative Offloading
• MobiLoRA: Accelerating LoRA-based LLM Inference on Mobile Devices via Context-aware KV Cache Optimization
• Collaborative Model Inference for Edge AI: A Deviceless Approach
• InfScaler: Enabling Efficient ML Inference Serving on Multi-Accelerator Edge Devices via Asymmetric Auto-Scaling
• From Perception to Computation: Revisiting Delay Optimization for Connected Autonomous Vehicles
• Agent-as-a-Service: an AI-native Edge Computing Framework for 6G Networks
• WebInf: Accelerating WebGPU-based In-browser DNN Inference via Adaptive Model Partitioning
• The First Measurement Study of Target Wake Time Mechanism in 802.11ax on COTS Devices