Category
2,285 papers
Companion data archive for the paper "Strangers to Themselves: What Language Models Say About Themselves Is Generic". The code, the slimmed scoring record and the generated paper tables live in the GitHub repository. That repository alone reproduces every number in the paper. This archive holds the parts that were too...
The area of a polygon whose vertices sit on lattice points comes out exactly from counting points. This paper asks why a count can produce a continuous quantity──the answer is that the three terms on the right count three different things. No new mathematical theorem and no new law is claimed. Scope of this paper (scop...
The Juggler map sends an even positive integer to the integer part of its square root and an odd positive integer to the integer part of its three-halves power. We prove that every nonempty set A closed under taking preimages satisfies ∑_(n ∈ A, n ≤ x)1/n ≥ c(log x)^(λ), for all sufficiently large x and every 0 < λ < λ...
The water of a reactor glows blue. A charged particle, it is said, has travelled “faster than light”. This paper asks which speed is the one exceeded──the answer is the phase velocity c/n, and not the vacuum speed of light c. No new mathematical theorem and no new law is claimed. Scope of this paper (scope note): No ne...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Résumé Les outils d’intelligence artificielle générative, notamment les grands modèles de langage, transforment les pratiques marketing en intervenant à plusieurs étapes du parcours d’achat, de la recherche d’information au service après-vente. Contrairement à l’IA prédictive, qui exploite principalement des données ex...
With the emergence of Large Language Models (LLMs), significant advancements have occurred in artificial intelligence technologies. Models such as ChatGPT, developed by OpenAI, stand out for their high performance in areas like accessing information, writing code, assisting in data analysis, translation and multilingua...
This repository contains the raw experimental outputs produced during evaluation of locally deployed large language model (LLM) and retrieval-augmented generation (RAG) systems. The records capture the outputs of the experimental generation pipeline before downstream evaluation metrics were computed. They include stand...
Abstract—Programming activities, such as automatic debugging and program repair, are increasingly being supported by Generative Artificial Intelligence (GenAI). However, a rigorous empirical evaluation of the efficacy of various large language models (LLMs) across several debugging phases is necessary. Using a benchmar...
Record-level screening data of a systematic mapping of the 2026 literature on artificial intelligence in Chinese education, companion to the paper "Digital transformation and systemic architecture of Chinese education: trajectory and the AI + Education plan toward 2030" (SAMYRAD 2026, Seville, 5–6 October 2026, IEEE Xp...
Ingredient overlap between 26 world cuisines, measured over 1,956 well-known dishes described in 7 languages. Provenance — read this first: the dishes are real, well-known dishes, but their ingredient lists were written by a large language model and verified by a second model pass, not transcribed from cookbooks. This...
Underground coal-mine equipment operates under broadband noise, high dust, humidity, and methane. Acoustic sensing is uniquely suited to this environment: it captures vibration, friction, and airflow signatures without physical contact, incurs low sensor-deployment cost, responds at millisecond speed, and remains effec...
AntEngage Empathy Conversation Dataset (Version 1.0.0) is an open-access dataset containing 4,008 AI-synthesized multi-turn empathy-focused conversations designed for research and development in natural language processing, conversational AI, and affective computing. The dataset was created by AntEngage Technology Priv...
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.
Learn how Google DeepMind and GovTech Singapore uses lightweight on-device Gemma models to intercept conversational scams in private chats with zero cloud data egress.
StudentSim is a research system for evaluating and improving AI tutoring tools before they are tested with learners. It models how individuals may engage with tutors, giving feedback to improve tutor performance across subjects like chess, writing, and mathematics. The post Simulating student learning for better AI tutoring appeared first on Microsoft Research.
By rethinking how large cloud computing systems operate, Associate Professor Christina Delimitrou seeks to make data centers more energy efficient.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
