Category
3,195 papers
Large language models (LLMs) may generate unreliable code on corner cases missed by testing, while formal verification can provide machine-checkable guarantees. Recently, researchers have proposed several benchmarks to evaluate the capabilities of LLMs in generating formally verifiable code, where LLMs need to formulat...
Autonomous agents powered by large language models (LLMs) are rapidly evolving into an open agentic ecosystem. To support trustworthy collaboration, industry initiatives increasingly assess agent reputation from past behavior and provide performance leaderboards. However, reputation derived from past performance may no...
This work proposes RefCon, which combines sequential self-refinement with parallel self-contrast to extract higher-quality memories without gold labels, and generalizes across model scales and to software engineering tasks, where it surpasses even ground-truth baselines.
Background: Polycystic Ovary Syndrome affects about 6–13 percent of women of reproductive age. It is a leading cause of infertility and is associated with insulin resistance, obesity, and high cardiovascular risk. Diet quality plays an important role in managing the condition. Diets high in refined carbohydrates and su...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Climate Diversity Calculation — Code and Data This repository accompanies the manuscript "Stability and changes of global climate diversity by 2100". It provides a reproducible example of the climate diversity (CD) calculation on a focal study region, using the actual 15 standardised bioclimatic variables and seven mov...
Climate Diversity Calculation — Code and Data This repository accompanies the manuscript "Stability and changes of global climate diversity by 2100". It provides a reproducible example of the climate diversity (CD) calculation on a focal study region, using the actual 15 standardised bioclimatic variables and seven mov...
Background: Polycystic Ovary Syndrome affects about 6–13 percent of women of reproductive age. It is a leading cause of infertility and is associated with insulin resistance, obesity, and high cardiovascular risk. Diet quality plays an important role in managing the condition. Diets high in refined carbohydrates and su...
The purpose of this research was to validate the online game addiction scale among students in Alborz city. The method of the current research was survey-descriptive. The research population included second-grade high school students in Alborz city. The research sample consisted of 374 high school students who were ran...
ObjectiveTo address the limited expressiveness of traditional leather decorative techniques and the insufficient application of the cyanotype process on leather, this study investigates the feasibility of applying the cyanotype process to sheep leather and expands its application methods in the design of women’s sheep...
Modern software systems evolve rapidly under CI/CD practices, where tests are critical for quality. However, substantial code changes often render existing test cases obsolete, causing pipeline disruptions, reduced productivity, and compromised quality. Recent automatic test update approaches leverage LLMs to refine te...
Purpose To compare the scan trueness and marginal gaps of monolithic zirconia implant-supported fixed complete prostheses (iFCPs) fabricated using direct and indirect digital workflows. In addition, to compare average marginal gap values of digital analysis and stereomicroscopic image analysis, performing 1-screw test,...
AI coding agents operate without persistent memory; useful outputs produced in one session are unavailable in the next, and information from one project never transfers to another. We present DevMemory, a structured memory management architecture that brings trust-scored, cross-scope knowledge retrieval to AI coding ag...
A Blog post by IBM Granite on Hugging Face
“X-Hinges” helps design and 3D print items like lamps and gloves with an interactive twist: automatically embedded sensors that perceive and adaptively respond to human contact.
We’re giving developers, enterprises, scientists, and consumers access to Gemini 4 Argon, our latest frontier model.
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.
An ongoing survey tracks the latest AI accelerator systems to keep hardware relevant for Lincoln Laboratory staff and sponsors.
Writing as a participant and researcher, PhD student JS Tan SM ’22 has co-authored a new book about the rise of tech worker protests and the employer backlash that followed.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
