Category
8,685 papers
It is argued that the work of memory divides, as thinking does, into two systems: long-term memory and reasoning model answering, and Mnemon, a memory agent built on this division.
This work studies activations from ensembles of prompts that require inferring relationships between three tokens corresponding to a cyclic concept to correctly predict the next token and finds a consistent layerwise progression in how the joint dependence among the tokens is geometrically organized and causally used.
VoxParity tests whether agents act on how a caller sounds, or how a caller sounds, or what else is audible, can change the right action and whether agents act on it.
CruxBench is introduced, a benchmark that grades LLM-generated questions by their Value of Information (VOI): how much a model-proposed crux updates beliefs about a target forecasting question and finds that VOI correlates highly with independent measures of model capability and captures cruxes'usefulness for answering...
Reach audiences
Advertise in front of researchers, engineers, and readers.
PACT is proposed, which turns this structure into four training terms that need no new annotation: a difference-in-differences margin over each pair that is invariant to any shared logit offset, a permutation-consistency term against answer-code position bias, an evidence-necessity term on certificate-verified ablated...
These findings show that aggregate detection metrics conceal persistent, model dependent heterogeneity in language model failures and motivate regime conditioned evaluation.
Treating intrinsic self-correction as a revision policy rather than as a uniformly beneficial second pass is suggested, and evaluating it through both the corrections it recovers and the errors it introduces.
Across 4,500 full-duplex calls and five voice configurations, Spanish, Portuguese, and Hindi remain within 3.2 task-completion points of English, but Korean and Mandarin fall by 14.7 and 8.4 points, respectively.
Although uniform diffusion language models (UDLMs) represent a promising diffusion paradigm, scaling them remains challenging. We identify the core obstacle as an over-uniform training objective and condition-target confusion during sampling. To address these, we propose Less Uniform Diffusion (LUDI), a novel UDLM fram...
Large language model search agents are often trained with synthetic questions whose difficulty is increased through larger evidence graphs, additional hops, and longer trajectories. These global properties, however, are only indirect proxies for the local retrieval capabilities required during search. To address this m...
To help researchers understand how to run statistics over LLM judges responsibly, guidance and tooling for the statistical analysis of mixed human-AI judge designs are presented, and recommendations for what CI, p-value, and FWER correction methods to use for small-sample AI evaluations are derived, and researchers are...
This paper evaluates six strong browser-use agents, three GUI-only agents that see only screenshots, and humans, evaluating the construction of challenging instances from tasks agents already solve, turning difficulty into a programmable property of the environment.
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’re on a journey to advance and democratize artificial intelligence through open source and open science.
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.
A new language-processing tool could help identify the highest-risk individuals from natural language, enabling swifter interventions.
A Blog post by Liquid AI on Hugging Face
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
