https://deepai.org/publication/task-oriented-communication-for-multi-device-cooperative-edge-inference
Task-Oriented Communication for Multi-Device Cooperative Edge Inference | DeepAI
Sep 1, 2021 - 09/01/21 - This paper investigates task-oriented communication for multi-device cooperative edge inference, where a group of distributed low-...
multi deviceedge inferencetaskorientedcommunication
https://deepai.org/publication/learning-task-oriented-communication-for-edge-inference-an-information-bottleneck-approach
Learning Task-Oriented Communication for Edge Inference: An Information Bottleneck Approach | DeepAI
Feb 8, 2021 - 02/08/21 - This paper investigates task-oriented communication for edge inference, where a low-end edge device transmits the extracted featur...
for edge
https://www.digitimes.com/news/a20260410VL217/gitex-asia-2026-ai-infrastructure-singapore.html
AI spending shifts to edge inference as GITEX Asia spotlights monetization push
GITEX Asia 2026 wrapped up in Singapore with a clear shift in industry priorities, as artificial intelligence (AI) spending moves from infrastructure buildout...
edge inference
https://arxiv.org/abs/2409.04249
[2409.04249] Hermes: Memory-Efficient Pipeline Inference for Large Models on Edge Devices
Abstract page for arXiv paper 2409.04249: Hermes: Memory-Efficient Pipeline Inference for Large Models on Edge Devices
https://ai.google.dev/edge/mediapipe/solutions/genai/llm_inference/ios?authuser=5
LLM Inference guide for iOS | Google AI Edge | Google AI for Developers
llm inferencefor iosgoogle aiguideedge
https://arxiv.org/abs/2604.17373
[2604.17373] Active Inference-Based Adaptive Routing for Heterogeneous Edge AI Services
Abstract page for arXiv paper 2604.17373: Active Inference-Based Adaptive Routing for Heterogeneous Edge AI Services
active inferenceadaptive routing
https://www.infoq.com/news/2025/09/linkedin-edge-recommendations/
LinkedIn Re-Architects Edge-Building System to Support Diverse Inference Workflows - InfoQ
LinkedIn has detailed its re-architected edge-building system, an evolution designed to support diverse inference workflows for delivering fresher and more...
building system
https://www.hpe.com/psnow/doc/a50006385enw
High-performance, energy-efficient AI inference at the Edge solution brief
AI inference workloads with integrated and optimized HPE Edgeline EL8000 Converged Edge Systems and Intel Arctic Sound-M ATS-M75 and ATS-M150 PCIe accelerators.
at the edgehigh performanceenergy efficientai inference
https://ai.google.dev/edge/api/mediapipe/python/mp/calculators/tensor/inference_calculator_pb2/InferenceCalculatorOptions
mp.calculators.tensor.inference_calculator_pb2.InferenceCalculatorOptions | Google AI Edge | Google...
google aimpcalculatorstensorinference
https://openreview.net/forum?id=ewDvdtfzN0&referrer=%5Bthe%20profile%20of%20Jie%20Liu%5D(%2Fprofile%3Fid%3D~Jie_Liu15)
DVFO: Learning-Based DVFS for Energy-Efficient Edge-Cloud Collaborative Inference | OpenReview
Due to limited resources on edge and different characteristics of deep neural network (DNN) models, it is a big challenge to optimize DNN inference performance...
for energy