Category
3,051 papers
SimpleCount is proposed, a reference with no parameter fitting that selects one scalar feature per dataset from a fixed pool of counts, recencies, first-occurrence indicators, and count-derived transforms that matches or exceeds SLADE on three of six datasets and exceeds IsoForest on all six.
An ADC/DAC-free neural accelerator based on the Walsh-Hadamard Transform and bit-plane processing that offers a multiplier-free, converter-free, regular, and scalable solution for low-power edge intelligence.
With the transformation of unconventional oil and gas resource development towards digitalization and intelligence, massive, multi-source, and dynamic well-entry fluid and material detection data have become core assets driving engineering decision-making. Traditional digital platforms aimed at process onlineization ha...
A Green AI–driven framework is presented for optimizing machine learning models with the goal of supporting sustainable computing and offers a practical and reproducible solution for deploying energy-efficient machine learning models across both cloud and edge environments.
Reach audiences
Advertise in front of researchers, engineers, and readers.
Cameroon is made up of an extensive tectonic system that includes a geologically significant structure in Central Africa called the Cameroon Volcanic Line (CVL). In this study, a multi-phase approach was applied to identify new tectonic structures across the CVL using gravity data from the XGM2019e_2159 model, magnetic...
This paper proposes a simple current-controlled second-order LAM mathematical model, which exhibits both negative differential resistance edge of chaos (EOC) domains and positive differential resistance (PDR) EOC domains, and constructs a minimalist third-order neuronal circuit by simply paralleling the LAM with a capa...
It is shown that edge symmetries can be exploited to design syndrome-extraction circuits from the underlying components, rather than from the full quantum code, to produce depth-optimal circuits from the underlying components.
FedMARL-LTI is presented, a federated multi-agent reinforcement learning framework whose architecture answers both pressures with a single decision: each organization’s threat intelligence is shared only as a differentially private 768-dimensional semantic embedding, never as raw data.
A novel video-based stress detection system with speaking awareness that dynamically processes facial features according to online detection of speech activities to demonstrate the system's applicability to real-world applications in stress tracking across healthcare, educational, and workplace well-being contexts.
The methods through which smart farming and human-wildlife conflicts can be reduced are discussed, based on increasing scalability and sustainability through use of satellite data, multimodal sensing and community-based warning systems.
The results demonstrate the potential of adaptive reward weighting to provide a systematic mechanism for controlling the exploration–imitation trade-off and enhancing the stability and robustness of GAIL-based policy learning while retaining the exploration advantages of the TD3-SAC hybrid framework.
We study weighted periodic-orbit zeta functions for an infinitely cusped tree lattice $Y_q$, where $q\ge2$ is even and the quotient is a one-sided comb. The global Euler product fails coefficientwise because infinitely many primitive cycles have length four. A first-return determinant at a finite directed-edge set neve...
Host Sowbhagya Suresh shares some of the latest news and cutting-edge research from across Microsoft—from understanding the challenges facing coding agents to uncovering how people use AI at work and improving extended-range weather forecasting. The post Microsoft Research Focus – Edition #97 appeared first on Microsoft Research.
Professor Paris Smaragdis develops computers with superhuman hearing for applications like speech recognition, music understanding, and environmental monitoring.
Education Innovation
For decades, a fundamental question about the difficulty of computing in high-dimensional spaces has resisted proof. New research resolves this question, removing a major theoretical obstacle to understanding the efficiency of randomized algorithms used across science and computing. The Kannan–Lovász–Simonovits (KLS) conjecture was proposed in 1995. It asks whether, for a broad class of high-dimensional […] The post Solving a 31-year-old grand challenge in mathematics – the KLS conjecture appear…
A new computational approach reveals how cells communicate to assemble into tissues. This could accelerate stem cell engineering, improve disease models, and inform therapies.
Zero-knowledge proofs can verify computing results without rerunning workloads or exposing sensitive data. Magnetar helps bring them into the mainstream with support for standard programming languages, major speed gains, and quantum-resistant security. The post Proof-based general-purpose computing with Magnetar 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.
