From the 3 of 5 linked papers with an AI index.
5 papers
Cross-Core Inference Offload as an Operating-System Service on Dual-Core Microcontrollers
Dimitrios Kafetzis
The paper presents SynapticOS, an open‑source Zephyr‑based runtime that offloads AI inference from a low‑power core to a more capable core on asymmetric dual‑core microcontrollers…
Inference Pipelines as Operating-System Objects: Priority Scheduling and Constant-Footprint Streaming for Microcontroller Neural Inference
Dimitrios Kafetzis
The paper presents SynapticOS, a Zephyr‑based runtime that treats neural inference pipelines on microcontrollers as first‑class operating‑system objects, using priority scheduling…
SynapticOS: An Inference-First Runtime Architecture for Neural Processing Units on Resource-Constrained Microcontrollers
Dimitrios Kafetzis
The paper introduces SynapticOS, an open‑source runtime for microcontrollers with on‑die neural processing units that treats AI inference as a first‑class workload, providing deter…
Video Quality Monitoring for Remote Autonomous Vehicle Control
Dimitrios Kafetzis, Nikos Fotiou, Savvas Argyropoulos +2
The delivery of high-quality, low-latency video streams is critical for remote autonomous vehicle control, where operators must intervene in real time. However, reliable video deli…
Large Language Model Partitioning for Low-Latency Inference at the Edge
Dimitrios Kafetzis, Ramin Khalili, Iordanis Koutsopoulos
Large Language Models (LLMs) based on autoregressive, decoder-only Transformers generate text one token at a time, where a token represents a discrete unit of text. As each newly p…