awesome-edgeai
github.com/wangxb96/awesome-edgeai ↗Resources of our survey paper "Optimizing Edge AI: A Comprehensive Survey on Data, Model, and System Strategies"
113
GitHub Stars
272
Curated Resources
8
Categories
4 hours ago
Last Refreshed
New: Federated Learning on EdgeNew: TinyML & Microcontroller AINew: Edge AI Security & PrivacyNew: On-Device Training & PersonalizationNew: Multimodal & Embodied Edge AINew: Real-World Applications & Case Studies1. Background Knowledge3. The Data-Model-System Optimization Triad
Use this list with your AI agent
Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:
"Show me 3.2.2. model compression resources from awesome-edgeai"
Installation instructions →What's inside
3. The Data-Model-System Optimization Triad
- 3D CNN acceleration on FPGA using hardware-aware pruning[C] DAC, 2020.3.2.2. Model Compression
Northeastern University, MA
- Accessible melanoma detection using smartphones and mobile image analysis[J]. IEEE Trans. on Multimedia, 2018.3.1. Data Optimization
Singapore University of Technology and Design
- ACG-engine: An inference accelerator for content generative neural networks[C] ICCAD, 2019.3.3. System Optimization
University of Chinese Academy of Sciences
- Achieving full parallelism in LSTM via a unified accelerator design[C] ICCD, 2020.3.3. System Optimization
University of Pittsburgh
- A covid-19 detection algorithm using deep features and discrete social learning particle swarm optimization for edge computing devices[J]. ACM Trans. on Internet Technology (TOIT), 2021.3.1. Data Optimization
Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System
- ActID: An efficient framework for activity sensor based user identification[J]. Computers & Security, 2021.3.1. Data Optimization
University of Houston-Clear Lake
New: Real-World Applications & Case Studies
- 6G Needs Agents: Toward Agentic AI-Native Networks for Autonomous IntelligenceEdge AI in 6G Networks
--
- AIoT Smart Home via Autonomous LLM AgentsSmart Home & IoT
--
- A Memory-Efficient Retrieval Architecture for RAG-Enabled Wearable Medical LLMs-AgentsHealthcare & Wellness
HKUST
- A Reconfigurable Method for Intelligent Manufacturing Based on Industrial Cloud and Edge IntelligenceIndustrial IoT & Manufacturing
--
- Artificial Intelligence-Driven Mechanism for Edge Computing-Based Industrial ApplicationsIndustrial IoT & Manufacturing
--
- A Survey on Cloud-Edge-Terminal Collaborative Intelligence in AIoT NetworksEdge AI in 6G Networks
--
New: Federated Learning on Edge
- Adaptive Federated OptimizationFederated Learning Foundations & Systems
Google Research
- Communication-Efficient Learning of Deep Networks from Decentralized Data (FedAvg)Federated Learning Foundations & Systems
Google
- DeepFusion: Accelerating MoE Training via Federated Knowledge Distillation from Heterogeneous Edge DevicesFederated Learning for LLMs & Edge Models
--
- Federated Black-box Prompt Tuning System for Large Language Models on the EdgeFederated Learning for LLMs & Edge Models
--
- Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 KilobytesFederated Learning for LLMs & Edge Models
--
- Federated Learning of Large Language Models via Parameter-Efficient TuningFederated Learning for LLMs & Edge Models
Zhejiang University
New: Multimodal & Embodied Edge AI
- AdaVFM: Adaptive Vision Foundation Models for Edge Intelligence via LLM-Guided ExecutionMultimodal Models on Edge
Intel Labs / CMU
- An Agentic AI Framework with LLMs and CoT for UAV-Assisted Logistics Scheduling with MECEmbodied AI & Robotics on Edge
NTU
- FastReasonSeg: Fast Reasoning Segmentation for Images and Videos on EdgeMultimodal Models on Edge
--
New: Edge AI Security & Privacy
- Adversarial Examples for Semantic Segmentation and Object DetectionSecurity & Adversarial Robustness
Johns Hopkins
- Competition for Attention Predicts Good-to-Bad Tipping in Edge AISecurity & Adversarial Robustness
--
- Deep Learning with Differential PrivacyPrivacy-Preserving Edge AI
Google
- Differential Privacy: A Survey of ResultsSecurity & Adversarial Robustness
Microsoft Research
- DPFinLLM: Privacy-Enhanced Lightweight LLM for On-Device Financial ApplicationsPrivacy-Preserving Edge AI
--
- Federated Learning with Differential Privacy: Algorithms and Performance AnalysisPrivacy-Preserving Edge AI
--
New: TinyML & Microcontroller AI
- Arduino Edge / TinyML KitTinyML Frameworks & Tools
- CMSIS-NNTinyML Frameworks & Tools
- Edge ImpulseTinyML Frameworks & Tools
Resources
New: On-Device Training & Personalization
- DoRA: Weight-Decomposed Low-Rank AdaptationOn-Device Training & Fine-tuning
--
Showing a sample of 272 resources. View the full list on GitHub →