Category
3,822 papers
This work introduces REFINE (Refactoring with Evidence-aware Flow for Integrated ageNtic Execution), a tool-agnostic, evidence-aware multi-agent approach for generating Java file-level refactoring candidates that achieves a higher median code-smell reduction with smaller edits and fewer public-method removals.
Local distillation is proposed, in which a black-box teacher guides a regularized linear"student" model at each query point, and it is proved that this randomization yields feature-selection probabilities that are stable under small perturbations of the training responses.
QUASAR is introduced, a QAT method that continuously performs lightweight, loss-aware reconstruction in the training loop to lower the loss floor and improve the resulting low-bit model, establishing QUASAR's objective as a principled optimization target.
Extensive experiments across scientific evaluation, mathematical reasoning, and coding generation tasks with multiple large language models show that SR-OPSD achieves the state-of-the-art or competitive performance across various settings.
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work shows that early stopping can overcome suboptimality: in a Gaussian mixture model with label-flipping noise, GD stopped at an appropriate oracle time achieves minimax-optimal excess zero-one risk for covariance spectra with fast and continuous decay, including polynomial and exponential spectral decays.
A generalized data processing inequality is formulated, requiring the constrained Bayes risk of a joint distribution to lower bound the constrained Bayes risk on the stochastically modified distribution, regardless of the choice of distribution, to be equivalent to a set containment condition on a specific function set...
Evidence that influential samples tend to lie close to the decision boundary, thereby making contact with a standard data selection heuristic in active learning is provided.
A structured variational approximation is offered that retains graph dependencies, preserves compositional uncertainty, and captures the explaining-away behaviour of colliders, attaining state-of-the-art performance while recovering low-fidelity contributions and yielding interpretability of the simulator hierarchy.
It is proved that the Wasserstein distance between a standard normal distribution and linear projections of the data is maximized when the projection recovers an independent component, and the OT-ICA algorithm which finds this projection by gradient-based optimization is proposed.
We study expected improvement (EI) for minimizing a deterministic function $f$ in the RKHS $\mathcal H_k$ of a continuous positive-semidefinite kernel $k$ on a nonempty compact set $\mathcal X\subset\mathbb R^d$. Function values are observed exactly, and EI is computed from a fixed zero-mean Gaussian-process model with...
An online multiclass L2D algorithm that combines queried-action bandit feedback with a dynamically varying pool of experts is introduced that achieves expected true-deferral regret under a concentrated-score condition.
This work uncover and identify the notion of ``robust item-wise coverage''as the minimal data requirement to enable sample-efficient robust assortment learning and bridges the gap between robustness and statistical efficiency in assortment learning.
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.
A Blog post by NVIDIA on Hugging Face
A machine-learning approach called CheMeleon provides a practical way to develop new drugs or other molecules with much less detailed, expensive experimentation.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Health & Bioscience
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
