Overview

Edge computing studies how to process data on or near devices such as phones, sensors, vehicles, robots, and nearby servers instead of sending everything to a distant cloud. Work spans task offloading and resource scheduling, federated and split learning, collaborative edge-cloud inference, and hardware-aware compression and acceleration. Evaluations use workloads from IoT, mobile networks, robotics, and vision, on both simulation benchmarks and real devices such as Raspberry Pis, Jetson boards, and embedded accelerators. The central tension is balancing latency, energy, bandwidth, privacy, and reliability across heterogeneous devices and changing networks; measured deployment costs do not always match gains predicted by models or simulations.

Latest papers

CardsList

199 papers28 papers in the last four weeks, up 33% on the four weeks before. 0.2% of all new papers.

  1. CSI-Assisted Edge SLAM Testbed Platform for 5G Connected Unmanned Autonomous Vehicles

    Jul 11, 2026Boris Radovanovic, Sasa Talosi, Srdjan Sobot +1Simultaneous Localization and MappingIntegrated Sensing and Communication

  2. EvoLP: Self-Evolving Latency Predictor for Model Compression in Real-Time Edge Systems

    Jul 10, 2026Shuo Huai, Hao Kong, Shiqing Li +5Efficient Neural Network InferenceEdge Computing

  3. Entropy-Guided Tensor Compression for Multimodal Federated Learning on Edge Devices

    Jul 7, 2026Quoc Bao Phan, Tuy Tan NguyenTensor NetworksMultimodal Federated Learning

  4. EcoVideo: Entropy-Orchestrated Video Generation Paradigm in Cloud-Edge Dynamics

    Jun 29, 2026Jiayu Chen, Hengyi Zhang, Maoliang Li +5Video Diffusion ModelsEdge Computing

  5. CSAR: Containerized System Architecture for Robotics

    Jun 29, 2026Ambrosio-Cestero, Gregorio, Galindo Andrades +5Edge ComputingRobotics

  6. Harvesting AI Computation at the Edge via Generic Approximation

    Jun 28, 2026Yihan Wang, Huiru Yan, Luxin Zhang +6Edge ComputingApproximate Computing

  7. Adaptive Joint Compression and Synchronisation in Federated Split Learning for IoT Rainfall Prediction

    Jun 23, 2026Wenjie Ding, Yi Sin Lin, Jiale Liu +8Edge ComputingSplit Federated Learning

  8. CABLE: Cloud-Assisted Bandwidth-efficient LMM-based Encoding for V2X Systems

    Jun 17, 2026Haohua Que, Zhipeng Bao, Qianyi Wu +1Efficient VLM InferenceEdge Computing

  9. KATANA: A Fast, Low-Power Mapping of Kalman Filters onto Edge NPUs for Real-Time Tracking

    Jun 12, 2026Bodhisatwa Kundu, Anish Rooj, Sumit Saha +4Kalman FilteringEdge Computing

  10. SemanticXR: Low Power and Real-time Queryable Semantic Mapping with an Object-Level Device-Cloud Architecture

    Jun 11, 2026Rahul Singh, Devdeep Ray, Connor Smith +1Edge ComputingSemantic Mapping

  11. A Lightweight Dual-Factor Acoustic Authentication System via Cascaded GMM-DTW Architecture for Edge Computing

    Jun 9, 2026Yutong ZhangSpeaker VerificationEdge Computing

  12. MemoVAD: Resource-Efficient Video Anomaly Detection via Dynamic Semantic Memory in Edge Computing Scenarios

    Jun 4, 2026Guo Li, Jiandian Zeng, Yang Li +3Streaming Video UnderstandingEfficient VLM Inference

  13. Multi-SPIN: Multi-Access Speculative Inference for Cooperative Token Generation at the Edge

    Jun 3, 2026Haotian Zheng, Zhanwei Wang, Mingyao Cui +3On-Device Language Model InferenceEdge Computing

  14. E2LLM: Towards Efficient LLM Serving in Heterogeneous Edge/Fog Environments

    Jun 2, 2026Truong-Thanh Le, Amir Taherkordi, Hoang-Loc La +3LLM ServingPrefill-Decode Disaggregation

  15. Geometric Fairness-Aware Routing for Federated Edge Networks

    May 31, 2026Ratun RahmanEdge ComputingFederated Graph Learning

  16. CoMIC: Collaborative Memory and Insights Circulation for Long-Horizon LLM Agents in Web Cloud-Edge Systems

    May 30, 2026Yannan Wang, Longli Yang, Zhen Liu +2LLM Agent MemoryEdge Computing

  17. Edge-Based QoS-Aware Adaptive Task Placement: A Closed-Loop Control in Multi-Robot Systems

    May 30, 2026Thien Tran, Jonathan Kua, Thuong Hoang +3Multi-Agent OrchestrationMulti-Robot Systems

  18. Dot-Flik: A Scalable Edge AI Architecture for Distributed Insect Monitoring

    May 27, 2026Mattia Consani, Denisa-Andreea Constantinescu, Åse Håtveit +4Edge ComputingInternet of Things

  19. DRL-Driven Edge-Aware Utility Optimization for Multi-Slice 6G Networks

    May 21, 2026Khaled M. Naguib, Soumaya Cherkaoui, Mahmoud M. Elmessalawy +26G NetworksEdge Computing

  20. E3E^3-Agent: An Executable and Evolving Agent for Resource Management of Edge Generative Inference

    May 21, 2026Rui Bao, Yaping Sun, Zhiyong Chen +4LLM Inference EfficiencyEdge Inference

  21. AIGaitor: Privacy-preserving and cloud-free motion analysis for everyone, using edge computing

    May 20, 2026Lauhitya Reddy, Trisha M. Kesar, Hyeokhyen KwonMarkerless Motion CaptureEdge Computing

  22. Memory-Efficient Partitioned DNN Inference on Resource-Constrained Android Crowds

    May 20, 2026Lakshani Manamperi, Disumi Pathirana, Thiwanka Pathirana +2Efficient Neural Network InferenceEdge Computing

  23. FusionSense: Tri-Stage Near-Sensor Learning for Runtime-Adaptive Multimodal Edge Intelligence

    May 19, 2026Sanggeon Yun, Ryozo Masukawa, Minhyoung Na +5Efficient Multimodal InferenceEdge Computing

  24. Deep Tech to Space: Space Data Centers and AI Revolution at the Edge

    May 19, 2026Jonas Weiss, Patricia Sagmeister, Gabriel Maiolini Capez +16Edge ComputingLEO Satellite Networks

  25. DAG-Based QoS-Aware Dynamic Task Placement for Networked Multi-Stage Control Pipelines

    May 19, 2026Thien Tran, Jonathan Kua, Thuong Hoang +3Robotic ControlEdge Computing

  26. Beyond Scaling: Agents Are Heading to the Edge

    May 18, 2026Chunlin Tian, Dongqi Cai, Wanru Zhao +1Edge ComputingAI Agent Architecture

  27. Heterogeneous Tasks Offloading in Vehicular Edge Computing: A Federated Meta Deep Reinforcement Learning Approach

    May 18, 2026Yaorong Huang, Jingtao Luo, Xuechao WangFederated RLEdge Computing

  28. TSFLora: Token-Compressed Split Fine-Tuning for Wireless Edge Networks

    May 17, 2026Xianke Qiang, Zheng Chang, Li Wang +1Communication-Efficient Distributed TrainingEdge Computing