Edge devices and associated networks utilising microservices
PulseAugur coverage of Edge devices and associated networks utilising microservices — every cluster mentioning Edge devices and associated networks utilising microservices across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
MLOps evolves with AI automation and edge device management
The MLOps field is evolving to encompass AI-driven automation and the management of AI models on edge devices. Autonomous MLOps aims to streamline the AI lifecycle by enabling AI systems to manage other AI systems, whil…
-
Flox Intelligence uses AI edge devices to deter wildlife from infrastructure · 7 sources tracked
Flox Intelligence is developing AI-powered edge devices designed to deter wildlife from critical infrastructure like transportation routes and airfields. These devices use on-device models to identify animals and emit s…
-
New methods optimize 3D Gaussian head avatars for quality and edge deployment
Two new research papers propose advancements in 3D Gaussian head avatar modeling. The first introduces a counterfactual route optimization framework to dynamically adjust training objectives for better geometry, appeara…
-
Robots learn advanced manipulation and tracking with new AI frameworks · 10 sources tracked
Researchers are developing advanced methods for robots to perform complex manipulation tasks, focusing on improving robustness and efficiency in real-world scenarios. Several papers introduce new frameworks and techniqu…
-
New S2-MoE framework boosts MoE model efficiency on edge devices
Researchers have developed S2-MoE, a novel framework designed to make Mixture-of-Experts (MoE) models more efficient for inference on edge devices. This approach addresses the challenges of memory and bandwidth constrai…
-
Study questions token necessity in vision transformers for place recognition
A new study published on arXiv explores the necessity of all tokens in visual place recognition (VPR) using vision transformers. Researchers developed a benchmark to evaluate token reduction methods, finding that signif…
-
Differentiable Logic Gate Networks enable low-latency EEG classification on edge devices
Researchers have developed Differentiable Logic Gate Networks (Diff-Logic), a novel approach for low-latency electroencephalography (EEG) classification on edge devices. This method compiles neural network models into p…
-
Adaptive Model Compression boosts transformer efficiency for edge devices
Researchers have developed Adaptive Model Compression (AMC), a new framework designed to make transformer models more efficient for use on resource-constrained edge devices. AMC dynamically allocates hardware resources …
-
New Paper Outlines Embedded ML Workflow for Microcontrollers
A new paper details a comprehensive workflow for implementing machine learning on microcontrollers, focusing on the engineering challenges of resource-constrained devices. It covers data acquisition, signal preprocessin…
-
Federated autoencoder enhances ECG anomaly detection with privacy on edge devices
Researchers have developed a privacy-preserving federated autoencoder system for detecting anomalies in electrocardiogram (ECG) data on edge devices. The system combines federated learning with differential privacy and …
-
NuWa method creates specialized, lightweight Vision Transformers for edge devices
Researchers have developed NuWa, a novel method for creating lightweight, class-specific Vision Transformers (ViTs) optimized for edge devices. Existing compression techniques often retain redundant information, leading…
-
Model multiplicity defends small language models against edge device attacks
Researchers have developed a novel defense system called "model multiplicity" to detect adversarial attacks during the training of small language models on edge devices. This approach involves training multiple language…
-
New BitTP method enables LLMs for edge-device trajectory prediction
Researchers have developed BitTP, a novel method for making large language models (LLMs) suitable for trajectory prediction on edge devices. BitTP converts LLM-based predictors into a lightweight bitlinear architecture,…
-
ZipMoE system enables efficient on-device serving of large language models
Researchers have developed ZipMoE, a system designed to make Mixture-of-Experts (MoE) large language models more efficient for on-device deployment. ZipMoE utilizes lossless compression and a cache-affinity scheduling a…
-
New BMO method defends on-device AI models against cross-node attacks
A new method called BMO has been developed to enhance the security of on-device machine learning models against cross-node attacks. This technique obfuscates model parameters by diversifying the decision boundary, makin…