Agent skills have become an important mechanism for equipping language-model agents with reusable procedural knowledge. However, providing skills alone does not guarantee that current models can…
Controllable video generation models are increasingly being developed as world models. Accordingly, evaluating them in this role extends beyond the apparent appearance of generated videos to…
25 Image-to-Video AI Conversion Statistics That Show How Creative Teams Are Finishing Campaigns Faster in 2026
Real-world software development requires coding agents to operate in shared workspaces where users may inspect and modify code during an ongoing task, yet existing repository-level benchmarks…
arXiv:2608.00247v1 Announce Type: cross Abstract: Variable importance may describe either intrinsic predictive information in a population or extrinsic importance for a fitted prediction rule. Quantifying the…
arXiv:2606.27564v1 Announce Type: cross Abstract: Most approaches for accelerating Markov chain mixing either rely on incorporating expensive geometric information in the proposals, or reduce the per-step…
arXiv:2410.01669v3 Announce Type: replace-cross Abstract: Covariance Neural Networks (VNNs) perform graph convolutions on the covariance matrix of input data to leverage correlation information as pairwise connections.…
arXiv:2608.02538v1 Announce Type: new Abstract: This paper is concerned with one-bit mean estimation, where each independent sample is represented by a single binary message. We consider…
arXiv:2605.09454v3 Announce Type: replace Abstract: We study the $textit{single-index bandit}$ problem, where rewards depend on an unknown one-dimensional projection of high-dimensional contexts through an unknown reward…
arXiv:2608.02487v1 Announce Type: new Abstract: Recently, rectified flow has emerged as a fundamental framework for large-scale image generation, powering state-of-the-art systems such as FLUX.1 and Stable…
arXiv:2608.02480v1 Announce Type: new Abstract: With AI systems gaining more access to individuals' information, it is important to protect privacy when reporting statistical answers. Equally important…
arXiv:2507.21449v2 Announce Type: replace Abstract: Degeneracy is an inherent feature of the loss landscape of neural networks, but it is not well understood how stochastic gradient…
arXiv:2608.01976v1 Announce Type: new Abstract: Given an algebraic statistical model, a challenging problem is classifying the data according to the number of positive critical points of…
arXiv:2407.12288v5 Announce Type: replace Abstract: The progress of machine learning over the past decade is undeniable. In retrospect, it is both remarkable and unsettling that this…
arXiv:2608.00675v1 Announce Type: new Abstract: Autoregressive models accumulate error over long rollouts, yet at deployment there is no ground truth to measure it against. We train…
arXiv:2608.00989v1 Announce Type: new Abstract: Most FDR-controlled feature selection methods are designed for coordinate-wise hypotheses, where each feature has a single weight or importance score. This…
arXiv:2608.01268v1 Announce Type: new Abstract: Detecting that a stream of high-dimensional embeddings has changed is usually framed as a choice of statistic. We give a scale…
arXiv:2608.01547v1 Announce Type: new Abstract: Drifting objectives compare a target and model distribution through a vector field observed noisily at finitely many locations. We ask what…
arXiv:2608.01545v1 Announce Type: new Abstract: We study the problem of identifying the dominant arm in multi-armed bandits, where the objective is to find the action with…
arXiv:2511.12840v2 Announce Type: replace Abstract: Overparameterized models often generalize well even when they interpolate noisy training data. This is known as benign overfitting. For linear classification,…
arXiv:2608.01587v1 Announce Type: new Abstract: Machine-learning benchmarks often pair a label that aggregates a long temporal horizon with input observed through one or a few short…
arXiv:2604.10727v2 Announce Type: replace Abstract: Classical information-theoretic learning bounds typically rely on KL mutual information and moment-generating-function (MGF) arguments, which are well matched to bounded or…
arXiv:2601.10763v2 Announce Type: replace-cross Abstract: A probabilistic framework for irreversible kinetics is proposed in which a constrained path functional $mathcal J$ encodes constitutive physics and observations…
arXiv:2503.14549v4 Announce Type: replace-cross Abstract: Scientific generative models must turn tractable local decisions into globally correlated samples that respect physical constraints. We introduce Sampling Decisions, a…