Category
2,370 papers
A logical measurement reads out protected information, and the noise it survives sets how much a quantum computation can absorb. Gauging builds one from a graph on the measured qubits, one extra qubit on each edge, turning a global operator into local parity checks. Its tolerance splits in two: the distance of the code...
We study bootstrap percolation with independent vertex thresholds taking values one and two, with threshold-one probability $(1-c/d)/d$ for fixed $c>0$. The seed set is chosen uniformly among sets of a prescribed deterministic size, independently of the graph and thresholds. We prove threshold statements at fixed relat...
A recurring design principle in modern optimizers is to decouple update magnitude from the raw gradient norm, yet its consequences for learning-curve and resource scaling remain unclear. We isolate this mechanism by studying normalized SGD in a random-feature model with power-law teacher and data covariance. Fixed-norm...
Traffic classification (TC) is crucial to secure Internet of Things (IoT) networks, whose edge nodes often operate under privacy, bandwidth, and energy constraints. Yet, encrypted payloads and limited computing power make accurate, real-time TC a challenging task. Existing learning-based TC approaches often fix the inp...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Split Computing (SC) enables efficient deployment of Deep Neural Networks (DNNs) by partitioning inference between edge devices and cloud servers. However, intermediate feature representations are simultaneously exposed to hardware faults and adversarial attacks, which are traditionally evaluated independently. This pa...
Graph Convolutional Networks (GCNs) have emerged as a powerful framework for learning from graph-structured data, yet their deployment on resource-constrained edge platforms remains challenging due to the computational and memory demands of sparse graph aggregation. This work presents an FPGA-based GCN accelerator that...
IoT encompasses diverse physical entities, from smart home devices to autonomous vehicles, creating a complex environment with heterogeneous security models. This heterogeneity makes IoT sub-systems vulnerable to various network attacks. Modern security systems must therefore be more robust to ensure security and priva...
Large language models (LLMs) have achieved substantial performance gains through increases in model size, training data, and computational resources. However, traditional scaling approaches produce diminishing returns, rising financial and environmental costs, and barriers to participation for researchers operating out...
Language-model agents are evolving into long-running services that interact with models, tools, computers, mobile devices, and distributed environments. Existing agent frameworks simplify reasoning and tool invocation. However, cloud-centric designs face three limitations: centralized execution increases failure impact...
A lightweight spatial enhancement detection model, namely GLA-YOLO, based on YOLOv5s, GhostConv and C3Ghost are introduced to reduce computational complexity and parameter scale and to handle the small size, complex morphology and background interference of photovoltaic defects.
The current work introduces a model for edge weight calculation with multi-source feature fusion named EW-GAT, a semantic similarity graph constructed via cosine similarity and Top-K sparsification, with similarity values directly embedded as edge weights to quantitatively encode behavioral closeness between flows.
The results show that the suggested ABB-DVS architecture increases robustness, lowers leakage power, boosts energy efficiency, and offers a scalable solution for next-generation low-power CMOS VLSI systems.
By rethinking how large cloud computing systems operate, Associate Professor Christina Delimitrou seeks to make data centers more energy efficient.
An ongoing survey tracks the latest AI accelerator systems to keep hardware relevant for Lincoln Laboratory staff and sponsors.
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.
Associate Professor Cathy Wu uses reinforcement learning to help map out improvements to transportation and other multifaceted systems.
Announcing Gemini 4 Argon, our frontier model for real-world coding, enterprise knowledge work and cyber defense, rolling out soon.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
