Category
3,366 papers
Point-in-time (PIT) agents can recall post-cutoff facts even when their external evidence respects a historical cutoff. We examine whether this access predicts evidence gathering in 48 historical company-comparison tasks. Independent closed-book revenue probes identify the better-remembered company for each model on ta...
Large language model (LLM) routers reduce serving cost by choosing which model to call and how many output tokens to grant it for each query. Existing routers rank model-budget actions using a single quality metric. This does not work for mixed workloads. For ordinary queries, a good answer is correct and useful (utili...
Large language models (LLMs) are increasingly used to discover scientific equations from experimental data. Such a discovery system has two parts that must work together: a library of executable computational tools and the model's tool-use policy. The tools supply the solving capability, from diagnosing structure in th...
As frontier LLMs gain more capabilities, the cost to run them also goes up. At the same time, small language models (SLMs) also gain more capabilities but have largely been able to keep their cost stable, offering 5-40 times cheaper inference for the narrow, repetitive subtasks that agents decompose work into. However,...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Large language model (LLM) alignment often assumes that the user interacting with a model is also the primary beneficiary of its behavior. Yet in many consequential settings, one person directs the system while another bears the consequences. We study this problem in caregiver-mediated healthcare, where parents, pet ow...
The rapid advancement of Large Language Models (LLMs) has driven their deployment toward general-purpose harness environments, where LLM-based agents operate in sandbox workspaces and interact directly with file systems and shells. While numerous post-training pipelines exist for tool-use agents, their counterparts for...
A small language model running on local hardware can serve as the reasoning layer for case-level and trio-based variant interpretation when it is surrounded by deterministic safeguards.
Background: Vision-language models (VLMs) are being considered for estimating energy intake from meal photographs. Prompt descriptions such as a Japanese-dietitian persona shift the estimates, suggesting their use for calibration; what the estimates rest on was unknown. Objective: We examined whether prompt description...
An offline VLM on a tablet reproduced server-side energy accuracy and is a candidate tool for dietary counselling where photographs cannot leave the institution; given the wide limits of agreement, its usefulness in practice remains to be examined.
English-language proficiency requirements became more than three times as common between 2010 and 2023 and were associated with lower enrolled proportions of Asian and Hispanic/Latinx participants, which may be a tractable target for improving enrollment equity.
Clinical trials of LLM interventions show modest adherence to established reporting guidelines, with persistent underreporting of LLM specific methodological details, reproducibility artefacts, and harms reporting required to support reproducibility and confident appraisal of safety risks before their clinical translat...
Praxis configures large language models to do data-driven natural science as a small lab of specialist agents running an explicit, falsifiable scientific method over real data. A domain-agnostic core (method loop, scientist roles, integrity rules, and a provenance-stamped, mechanically validated cache engine) is extend...
Genie 4: our new world model unlocking unprecedented realism in real-time simulation.
Generative AI
Assistant Professor Benjamin Lindquist studies how engineers deliberately injected randomness into early AI, giving rise to deep-learning models that sometimes hallucinate.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations 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.
