The Synergistic Policy network for Edge Resource Control (SPERC) is presented, a novel deep reinforcement learning framework designed to solve this joint problem of ensuring performance through appropriate computational resource allocation and minimizing storage costs through image layer sharing.
Seyed Hossein Ahmadpanah, A. Sahafi, S. Erfani· Journal of Supercomputing· 0 citations
CK Vision's 13MP MIPI CSI camera modules represent the pinnacle of high-resolution embedded imaging, combining optoelectronic precision with flexible hardware interfaces. Engineered to meet the technical excellence demanded by the ever-evolving field of machine vision, our 13.2 mp mipi camera module portfolio delivers...
chenkun· Zenodo (CERN European Organi...· 0 citations
Kolmogorov-Arnold Networks (KANs) replace the fixed activation functions and linear weights of Multi-Layer Perceptrons (MLPs) with learnable univariate functions on network edges, offering improved interpretability and, in some settings, competitive parameter efficiency. While the approximation properties of KANs have...
Guang-Neng Chen, David García Selfa, Pablo Quesada Barriuso· 0 citations
This paper shows that the proposed method ensures a bounded Byzantine influence on both distillation gradients and individual client private gradients after cross-modality fusion, thereby enabling stable local optimization for honest clients under Byzantine distillation.
Xiao Ma, Hong Shen, Hui Tian et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
An AI-for-science approach to linking neural connectivity to computation is suggested and a conditional generative latent framework is proposed that encodes connectome graphs into a compact structural space while using available node-level conditions to guide reconstruction and generation.
Zhuo-Lin Yu, Xing-Yu Liu, Yuan-Hao Jia et al.· 0 citations
A controlled measurement study of self-hosted LLM inference across edge and near-edge deployment nodes: an NVIDIA Jetson AGX Orin and a near-edge server with CPU-only and GPU-enabled inference modes, highlighting that compute-side inference metrics alone can lead to suboptimal placement for latency-sensitive interactiv...
Maysam Khatib, Moysis Symeonides, Demetris Trihinas et al.· 0 citations
Deployment of Large Language Models (LLMs) on memory-constrained edge devices relies heavily on aggressive post-training quantization. However, evaluating these models is largely based on zero-shot task accuracy, which depends solely on argmax predictions and is insensitive to changes in the underlying predictive distr...
Shahzeb Qamar, L. Sparrenberg, Christian Bauckhage et al.· 1 citation
Mobile edge computing (MEC) accelerates Internet of Things (IoT) applications by caching content near end users. However, cached data remains vulnerable to corruption, misleading applications, and eroding user trust. Traditional centralized edge data integrity verification (EDIV) methods adopt challenge-response protoc...
Adil Sarwar, Yanlong Zhai, Jun Shen et al.· IEEE Internet of Things Jour...· 0 citations
This paper proposes SEELE, a Lyapunov-guided online control algorithm that represents accumulated budget pressure with two virtual queues and converts the long-term constrained problem into lightweight per-slot decisions, and provides steady-state QoE statistically comparable to a pretrained PPO policy while significan...
Yuxuan Xiao, Han Xiao, Chuxing Fang et al.· Italian National Conference...· 0 citations
In this review, recent studies on TRNGs based on emerging material-based semiconductor devices are examined from the perspectives of entropy sources, device structures, randomness validation, and wearable/flexible extensions to provide a useful framework for future research on hardware security devices.
Y. Jo, D. Joe, Joonyoung Kwak· Journal of Electrical and El...· 0 citations
Le contrôle qualité en temps réel des pièces composites dans l'industrie aéronautique représente un enjeu majeur pour garantir l'intégrité structurale des composants tout en maintenant des cadences de production élevées. Cet article présente un système modulaire open-source combinant vision industrielle et Line Scan Th...
Alexis Griffon, Nicolas Leymarie, Vincent Dorval et al.· e-Journal of Nondestructive...· 0 citations
A rating-aware graded security offloading framework for UAV-assisted MEC networks that maintains a higher offloading ratio and lower system cost than the fixed-security and no-rating baselines in the considered hover-based UAV-MEC scenario.
Han Zhang, Jian-Bin Xue· Journal of King Saud Univers...· 0 citations
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.
MIT News · Artificial Intelligence· news.mit.eduOct 2, 2026
