1714 matching published research entries
Artificial Intelligence · 2026-10-28
arXiv:2610.36239v1 Announce Type: new Abstract: Sequential recommendation models typically predict a user's next action from recent session interactions, which limits personalization when short-term signals are weak or ambiguous. Rather than assuming that incorporating longer-term history and community signals is universally beneficial, we study when it actually helps.
arXiv AIRead article →Artificial Intelligence · 2026-10-28
arXiv:2610.36234v1 Announce Type: new Abstract: Requirements engineering (RE) is foundational to systems engineering (SE), as requirement defects can propagate downstream and adversely affect development outcomes. Although large language models (LLMs) are promising for requirement quality assessment, prior work shows that off-the-shelf models miss a large share of expert-identified defects, perform unevenly across…
arXiv AIRead article →Artificial Intelligence · 2026-10-28
arXiv:2610.36188v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly rely on reusable skills for complex software engineering tasks, making skill libraries essential for repository development and maintenance. However, repository-specific skills must evolve with changing code structures, implementation conventions, and maintenance requirements.
arXiv AIRead article →Artificial Intelligence · 2026-10-28
arXiv:2610.36183v1 Announce Type: new Abstract: We study time-to-arrival (TTA) in sports: the shortest plausible time a player needs to reach an arbitrary location on the pitch given their current kinematic state, estimated as the lower envelope of observed locomotion times.
arXiv AIRead article →Artificial Intelligence · 2026-10-28
arXiv:2610.36169v1 Announce Type: new Abstract: A retrieval-augmented language model answers from two sources, the retrieved context and its own knowledge, and the two disagree whenever the context is incomplete or wrong. Existing methods settle the disagreement with a rule fixed at design time: follow the context, amplify it in proportion to how far it moves the model, or trust the model's memory.
arXiv AIRead article →Artificial Intelligence · 2026-10-28
arXiv:2610.36146v1 Announce Type: new Abstract: Prompt optimization should improve the image a user receives without changing the scene the user requested. Yet stylistic rewriting can weaken object attributes and relations even when global text--image similarity remains high.
arXiv AIRead article →Artificial Intelligence · 2026-10-28
arXiv:2610.36116v1 Announce Type: new Abstract: As AI begins to match or exceed human researchers at core scientific tasks, two questions become pressing: \emph{why} should humans keep doing science, and \emph{how} should they use AI when they do? This paper argues that the second can be answered only by answering the first.
arXiv AIRead article →Artificial Intelligence · 2026-10-28
arXiv:2610.36100v1 Announce Type: new Abstract: Language model agents for clinical cohort curation should accommodate evolving eligibility criteria without repeatedly processing unchanged requirements. We introduce CohortFlow, a steerable agent that represents natural language corrections as localized updates to a structured cohort specification and reconciles them with a persistent execution graph.
arXiv AIRead article →Artificial Intelligence · 2026-10-28
arXiv:2610.36077v1 Announce Type: new Abstract: Multimodal intelligence can be viewed as human-guided co-evolution between worlds and agents through interaction. However, scaling this process faces two bottlenecks: constructing heterogeneous, verifiable environments is costly, and manual Harness iteration cannot keep pace with growing task diversity and complexity.
arXiv AIRead article →Artificial Intelligence · 2026-10-28
arXiv:2610.35984v1 Announce Type: new Abstract: Deep learning models are highly effective in a wide range of domains, particu larly in plant disease diagnosis. However, their performance is often limited by challenges such as insufficient data and class imbalance. In our work, we propose a comprehensive data generation strategy to overcome these limitations.
arXiv AIRead article →Artificial Intelligence · 2026-10-28
arXiv:2610.35942v1 Announce Type: new Abstract: I consider what it means for AI assistance to save time. I contrast a stopwatch view, on which time saved is whatever the clock records, with a ledger view, on which it is a counterfactual that has to be read next to the errors the work lets through, and I argue for the latter. The argument has four parts.
arXiv AIRead article →Space & Discovery · 2026-10-28
A national monument since the 1920s, Chiricahua is America’s newest national park.
NASARead article →Space & Discovery · 2026-10-28
APOD Science APOD APOD: 2026 October 28 – The… Today’s APOD Archive Submissions Index Search Calendar RSS Education About Discuss APOD Astronomy Picture of the Day Discover the cosmos! Each day a different image or photograph of our fascinating universe is featured, along with a brief explanation written by a professional astronomer. To view […]
NASARead article →Artificial Intelligence · 2026-10-27
Prabha Jha used her experience with MIT Open Learning’s program for senior executives to develop AI solutions for her employer, Verizon, and to write a book.
MIT Artificial IntelligenceRead article →Engineering · 2026-10-27
Science has a spam problem. And the spam filter is getting clogged up. According to all reports, academic publishing is drowning in what has come to be called AI slop: low-quality, mass-produced content generated with AI. By 2025, an estimated 57 percent of all published academic articles exhibited detectable evidence of large language model (LLM) influence, a massive jump from 12 percent in 2023.
IEEE SpectrumRead article →Engineering · 2026-10-27
This article is brought to you by VicOne. A mobile robot slows for someone in a hallway. A collaborative arm eases its movement as a worker approaches. A humanoid pauses to let a person pass. Each response depends on information about the robot or its surroundings: a distance reading, a position estimate, or a stop signal.
IEEE SpectrumRead article →Science · 2026-10-27
New evidence suggests that early humans reached the Jordan Valley at least 1.9 million years ago, hundreds of thousands of years earlier than scientists previously thought. Advanced dating methods revealed that the ‘Ubeidiya site is roughly as old as the famous Dmanisi site in Georgia, placing both among the earliest known human settlements outside Africa.
ScienceDailyRead article →Science · 2026-10-27
Mayo Clinic scientists have uncovered surprising new insights into “zombie cells,” aging cells that linger in the body and contribute to inflammation and disease. Seven studies reveal why these cells are harmful and identify new strategies for targeting them, including a natural compound found in tomatoes. In aging mice, experimental treatments reduced inflammation and improved physical and brain health.
ScienceDailyRead article →Science · 2026-10-27
Why do some people stay mentally sharp even when their brains show signs of Alzheimer’s disease? Scientists in the Netherlands may have uncovered an important clue hidden in a rare group of immature brain cells. Researchers discovered that these cells remain present even in people over 80, but their behavior differs dramatically between those who develop dementia and those who remain cognitively healthy.
ScienceDailyRead article →Science · 2026-10-27
Scientists have discovered that spiders may sleep in ways surprisingly similar to humans, complete with distinct sleep stages and a dream-like REM state. Researchers at the University of Bonn studied the Australian jumping spider Portia fimbriata, a remarkably clever hunter known for its sophisticated strategies.
ScienceDailyRead article →Science · 2026-10-27
Scientists have created one of the largest and most detailed simulations of the early universe ever made, offering an extraordinary new glimpse into the cosmos shortly after the Big Bang. Called Lumina, the groundbreaking simulation recreates the universe’s first 2 billion years, showing how dark matter, gas, and radiation interacted to give rise to the earliest stars, galaxies, and black holes.
ScienceDailyRead article →Science · 2026-10-27
A scorching lava planet 280 light-years away has surprised astronomers by apparently maintaining a thick atmosphere despite conditions that should have stripped it away billions of years ago. James Webb Space Telescope observations suggest that TOI-561 b reflects about 75% of incoming starlight, possibly because of mineral clouds that act like a giant sunscreen.
ScienceDailyRead article →Science · 2026-10-27
A surprising discovery reveals that widely used anti-inflammatory drugs may unintentionally help dangerous viruses spread through the body. Scientists found that JAK inhibitors, prescribed for rheumatoid arthritis and other inflammatory diseases, can weaken a crucial immune defense against influenza, COVID-19, and other infections.
ScienceDailyRead article →Space & Discovery · 2026-10-27
A technician inspects the large sunshade of NASA’s Near-Earth Object (NEO) Surveyor mission in this image released on Oct. 26, 2026. The sunshade structure, which stands 20 feet (6 meters) tall and measures 8 feet (2.4 meters) wide at its base, will keep the infrared space telescope cool as it searches for near-Earth asteroids and […]
NASARead article →