Category
19,710 papers
LLM-SR-UQ is introduced, a framework that retains competing equation structures and uses their disagreement to characterize uncertainty about the underlying functional form and substantially improves coverage attainment by incorporating structural disagreement while preserving in-distribution coverage.
Automated, self-updating meta-analysis of when humans and AI work better together, and when they work better alone is introduced, finding that, on average, human-AI combinations performed significantly better than humans alone, but they performed significantly worse than the better of humans or AI alone.
An idealized reference model---an injection-invariant, utility-preserving oracle---can nevertheless be approximated, as its output distribution in training is interestingly accessible, which motivates a theoretically principled SecPO loss.
Chronos-2 is introduced, a foundation model for zero-shot forecasting that models the interactions between multivariate time series and heterogeneous covariates, which commonly arise in scientific applications and shows that a single pretrained model can capture structure shared across temporal systems.
Reach audiences
Advertise in front of researchers, engineers, and readers.
A novel framework to align MLLMs with the multidimensional mental representations underlying human similarity judgements, which builds on a previously established behavior-derived semantic embedding space and points to a data-driven route for incorporating human cognitive structure into MLLMs alignment.
An approximation can reproduce an energy while missing its response, or satisfy an error tolerance without being certified by a given bound. We formulate observable-specific validity records for scientific artificial intelligence (AI) that link a reduction to its reference model, error measure, tolerance, parameter dom...
Foundation models (FMs) learn reusable representations from large collections of unlabeled data. In chemistry the corresponding data mainly consists of molecular structures, which are abundant, whereas experimental measurements are scarce. Chemical FMs such as ChemBERTa and MoLFormer were therefore trained on diverse m...
Job applicants increasingly use large language models (LLMs) to write cover letters, while employers deploy LLMs to screen them. In this all-AI setting, we ask whether the \emph{choice of model} affects hiring outcomes independently of candidate qualifications. We introduce a multi-model auditing framework pairing elev...
Conversational explainable AI (ConvXAI) agents often use GUS-style architectures with separate modules for intent recognition, dialogue management, and template-based response generation. While faithful to the underlying XAI methods, these pipelines are hard to adapt and often struggle with context-dependent follow-up...
An analysis framework is proposed that relates the per-dataset gap to InceptionTime to dataset properties and tests convolutional feature learning by replacing the flatten readout with global average pooling, measured as a difference-in-differences (DD) against a backpropagation control on the identical architecture.
LYNX-ECG is introduced, a graph neural network that represents each heartbeat as a sparse visibility graph of timestamped turning points that pair accurate ECG classification with clinically grounded, testable explanations.
Continual learning is the study of how a model accumulates knowledge from data received over time, rather than all at once. In practice, this is typically achieved by dividing a dataset into tasks and presenting them sequentially. Explanations of the resulting measurements take into account factors such as the similari...
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
