Overview

Edge inference studies how to run AI models close to where data is collected, often on devices with limited memory, power, and computing capacity. Common approaches include quantization, pruning and distillation, hardware-aware model and accelerator design, and adaptive methods such as early exits, model routing, and device-edge splitting. Work spans tasks from object detection and segmentation to language and multimodal models, with evaluation on benchmarks such as COCO and MVTec as well as phones, Raspberry Pi, Jetson, microcontrollers, and FPGAs. A central challenge is balancing accuracy, latency, energy, and robustness: proxy measures such as FLOPs may not predict real-device performance, which also varies with hardware, workload contention, and sustained operation.

Latest papers

CardsList

248 papers26 papers in the last four weeks, up 13% on the four weeks before. 0.2% of all new papers.

  1. Metasurfaces-Integrated Wireless Neural Networks for Lightweight Over-The-Air Edge Inference

    Feb 22, 2026Kyriakos Stylianopoulos, Mario Edoardo Pandolfo, Paolo Di Lorenzo +1Wireless CommunicationsEdge Inference

  2. DART: Input-Difficulty-AwaRe Adaptive Threshold for Early-Exit DNNs

    Feb 17, 2026Parth Patne, Mahdi Taheri, Christian Herglotz +3Efficient Neural Network InferenceEarly-Exit Neural Networks

  3. MoE-SpAc: Efficient MoE Inference Based on Speculative Activation Utility in Heterogeneous Edge Scenarios

    Feb 12, 2026Shuhuai Li, Jianghao Lin, Dongdong Ge +1Mixture-of-Experts InferenceEdge Inference

  4. Hardware-Algorithm Co-Optimization of Early-Exit Neural Networks for Multi-Core Edge Accelerators

    Dec 4, 2025Alaa Zniber, Arne Symons, Ouassim Karrakchou +2Efficient Neural Network InferenceDynamic Neural Networks

  5. Vision Transformers on the Edge: A Comprehensive Survey of Model Compression and Acceleration Strategies

    Feb 26, 2025Shaibal Saha, Lanyu XuEfficient ViTsNeural Network Compression

  6. A Comprehensive Evaluation of Deep Learning Object Detection Models on Heterogeneous Edge Devices

    Sep 25, 2024Daghash K. Alqahtani, Muhammad Aamir Cheema, Maria A. Rodriguez +1Energy-Efficient MLEdge Inference