Skip to content

Category

edge computing

2,370 papers

#edge computing Open access Oct 2026

A lightweight pose-guided fusion approach for accurate safety helmet compliance monitoring on edge devices

This paper presents an AI framework employing automated visual analysis to verify personal protective equipment (PPE) compliance in complex construction and industrial settings. Within the framework of engineering automation, robust semantic modeling of worker safety configurations is essential for enabling real-time h...

Azimjon Akhtamov, Jeong Hwan Ryu, Young-ho Park et al. · 0 citations
#edge computing Dataset Open access Oct 2026

High-resolution multi-modal accessibility metrics for Switzerland

Per-cell accessibility metrics for Switzerland at approx. 100m resolution (H3 grid, resolution 10), computed in a time-based domain (gross travel time in seconds, including origin- and destination-side overheads), a utility-based domain (disutility from a fitted mode-choice discrete-choice model), and using straight-li...

Marco Miotti, Arnór B. Elvarsson, Yves M. Räth et al. · 0 citations
#edge computing Dataset Open access Oct 2026

Calibrated multi-modal transport networks for Switzerland

Cleaned OpenStreetMap-derived walk, bike, and car networks for Switzerland (plus a cross-border buffer for realistic frontier-cell routing), with per-edge calibrated travel durations. These are the networks used to compute the companion accessibility metrics dataset: https://doi.org/10.5281/zenodo.21410968. Contents 1)...

Marco Miotti, Arnór B. Elvarsson, Yves M. Räth et al. · 0 citations
#edge computing Dataset Open access Oct 2026

Multiband SMR, ICC and ICLD Dataset of Grammy-Nominated Tracks (1995–2026)

Description This repository contains the derived audio features, statistical results, robustness analyses, and Python source code accompanying: Long-Term Changes in Multiband Stereo Characteristics of Grammy-Nominated Popular Music Recordings (1995–2026) The study analyzes 536 Grammy-nominated recordings from 1995–2026...

Jooyoung Kim · 0 citations
#edge computing Open access Oct 2026

The Pentachoric Tower and the Riemann Hypothesis: Unconditional Results and a Conditional Reduction

From the prime sequence, a free scale constant, and a selection predicate, we prove three things. The selected polytope is the 4-simplex Σ4Σ4​. The Hessian of its squared volume at the regular point is (l6/2304)(−5I+2A)(l6/2304)(−5I+2A), with spectrum +7,−3,−9+7,−3,−9 and signature (+1,−9)(+1,−9). Every S5S5​-invariant...

Timothy Poschel · 0 citations
#edge computing Open access Oct 2026

Void Network Geometry and Bell Non-Locality: Withdrawal of the c√(3/2) Propagation Speed

Version 1.0 of this record claimed that the octahedral-void network of the BCC Planck foam has nearest-neighbour spacing shorter than the bubble spacing, and that voids therefore propagate at c_V = c√(3/2) ≈ 1.22c, supplying a finite-speed mechanism for Bell non-locality. That result is withdrawn. Two errors are identi...

Luke Martin · 0 citations
#edge computing Open access Oct 2026

A Stable Dyon of Unit Electric Charge at the LHC: The Acceptance Gap of the Existing Searches and a Tracker Based Search to Close It

A stable spin one half particle with unit electric charge and one Dirac unit of magnetic charge is examined at 1.86 TeV, with a 3 TeV monopole as a second benchmark. In the ATLAS barrel it reaches the electromagnetic calorimeter only if its initial velocity exceeds 0.45c at central rapidity and 0.62c at the edge of the...

Robert Bruce Ware · 0 citations
#edge computing Open access Oct 2026

A Stable Dyon of Unit Electric Charge at the LHC: The Acceptance Gap of the Existing Searches and a Tracker Based Search to Close It

A stable spin one half particle with unit electric charge and one Dirac unit of magnetic charge is examined at 1.86 TeV, with a 3 TeV monopole as a second benchmark. In the ATLAS barrel it reaches the electromagnetic calorimeter only if its initial velocity exceeds 0.45c at central rapidity and 0.62c at the edge of the...

Robert Bruce Ware · 0 citations
#edge computing Open access Oct 2026

Deploying LLM Inference on a Repurposed UMA APU: Transferable Lessons from a Vulkan-Only, 16 GB Edge Platform

Cost-driven interest in running large language models (LLMs) on non-mainstream silicon outpaces the maturity of the surrounding software stacks. This paper uses one such platform, the AMD BC-250 (a repurposed cryptocurrency-mining board with a GFX1013 "Cyan Skillfish" accelerated processing unit (APU), 16 GB of unified...

Artur Andrzejczak · 0 citations
#edge computing Review Open access Oct 2026

On-Device Multimodal Small Language Models for Privacy- Preserving Edge Intelligence Through Quantization Pruning Distillation and Energy-Efficient Inference

On-device multimodal small language models are emerging as a practical foundation for privacypreserving edge intelligence, enabling devices to interpret and generate language while processing images, audio, video, sensor streams, and contextual signals without continuous cloud dependence. Their deployment can reduce da...

Stanley Nwakamma · 1 citation
#large language models Open access Oct 2026

Deploying LLM Inference on a Repurposed UMA APU: Transferable Lessons from a Vulkan-Only, 16 GB Edge Platform

Cost-driven interest in running large language models (LLMs) on non-mainstream silicon outpaces the maturity of the surrounding software stacks. This paper uses one such platform, the AMD BC-250 (a repurposed cryptocurrency-mining board with a GFX1013 "Cyan Skillfish" accelerated processing unit (APU), 16 GB of unified...

Artur Andrzejczak · 0 citations
#edge computing Preprint Oct 2026

The Zero Forcing Number of Graph Powers

The $k$-th power of a simple graph $G$, denoted $G^k$, is the graph with vertex set $V(G)$ where two vertices are adjacent if they are within distance $k$ in $G$. We investigate the zero forcing number of graph powers. Powers of graphs are much denser and generally not encompassed by existing results on zero forcing of...

A. Abiad, Mary Flagg, Sina Ghasemi Nezhad et al. · 0 citations

From tech blogs

See all →
Microsoft Research Blog Oct 6, 2026

What AI gets wrong and what failure teaches us

Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and stops that led to her professional sweet spot and her work identifying “surprising failures” making it hard for AI to handle complexity.  The post What AI gets wrong and what failure teaches us appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.