AI News

Enhancing Layer Attention Efficiency through Pruning Redundant Retrievals (arxiv.org)

Skill-Based Mixture-of-Experts: Adaptive Routing for Heterogeneous Reasoning via Inferred Skills (arxiv.org)

EuroBERT: Scaling Multilingual Encoders for European Languages (arxiv.org)

ShapeLib: Designing a library of programmatic 3D shape abstractions with Large Language Models (arxiv.org)

Self-supervised Monocular Depth and Pose Estimation for Endoscopy with Latent Priors (arxiv.org)

Online Learning in MDPs with Partially Adversarial Transitions and Losses (arxiv.org)

Learning to Remember, Learn, and Forget in Attention-Based Models (arxiv.org)

AnomSeer: Reinforcing Multimodal LLMs to Reason for Time-Series Anomaly Detection (arxiv.org)

Learning To Sample From Diffusion Models Via Inverse Reinforcement Learning (arxiv.org)

Generalization of Gibbs and Langevin Monte Carlo Algorithms in the Interpolation Regime (arxiv.org)

How to Correctly Report LLM-as-a-Judge Evaluations (arxiv.org)

It does what it says on the tin: safe synthetic data from coarsened margins (arxiv.org)

Inverse Depth Scaling From Most Layers Being Similar (arxiv.org)

Error Bounds for a Diffusion Model-Based Drift Estimator (arxiv.org)

ProbRes: Volatility Learning for Probabilistic Time-Series Forecasting (arxiv.org)

When Softmax Fails at the Top: Extreme Value Corrections for InfoNCE (arxiv.org)

ERICA: Quantifying Replicability of Cluster Analysis (arxiv.org)

Riemannian Stochastic Optimization for Sufficient Dimension Reduction (arxiv.org)

Interpreting FCDNNs via RG on Exponential Family (arxiv.org)

Out-of-Distribution generalization of quantile regression with heavy tailed inputs: an SVM approach (arxiv.org)

Is Zero-Shot Super-Resolution Possible in Operator Learning? (arxiv.org)

Parameter-Free and Group Conditional Online Conformal Prediction (arxiv.org)

Spectra-Guided Neural Tucker Factorization (arxiv.org)

Taming the Loss Landscape of PINNs with Noisy Feynman-Kac Supervision: Operator Preconditioning and Non-Asymptotic Error Bounds (arxiv.org)

On Median of Incomplete U-Statistics (arxiv.org)

Statistical Testing on Directed Graphs by Surrogate Data Generation (arxiv.org)

Statistical Analysis of using the Shapley Value for Sensor Anomaly Localization with Accurate Classifiers (arxiv.org)

Bandit Simulation for Average Reward Inference (arxiv.org)

Efficient Synthetic Network Generation via Latent Embedding Reconstruction (arxiv.org)

Practical and Optimal Algorithm for Linear Contextual Bandits with Rare Parameter Updates (arxiv.org)

Reinforcement Learning for Optimal Experiment Design in Parameter Identification of Mechatronic Systems (arxiv.org)

Efficient Approximation for Encoder--Decoder Neural Operators via Variation Spaces (arxiv.org)

Distribution-free changepoint localization after sequential change detection (arxiv.org)

On the Uncertainty Quantification Ability of Tabular Foundation Models (arxiv.org)

Computation-Aware Kalman Filtering with Model Selection for Neural Dynamics (arxiv.org)

Self-Regulating Annealing in Heavy-Tailed Diffusion Models (arxiv.org)

Knowledge-Intensive Video Generation (arxiv.org)

Provable Data Scaling Law for Meta Learning via Complexity Minimization (arxiv.org)

Convex Distance Operator Transport: A Convex and Geometry-Preserving Formulation (arxiv.org)

Bayesian meta-learning for modeling Alzheimer's disease progression (arxiv.org)

Identifiable Markov Switching Models with Instantaneous Effects and Exponential Families (arxiv.org)

ShaplEIG: Bayesian Experimental Design for Shapley Value Estimation (arxiv.org)

Doing well with less! On Sampling Techniques for Empirical Pairwise Loss Estimation/Minimization (arxiv.org)

Sharpness-Aware Hybrid Model Learning for Architecture-Agnostic Parameter Estimation (arxiv.org)

Hoeffding Concept Bottleneck Models with Applications to Overhead Images (arxiv.org)

Physics from Video: Identifiability of Time-Invariant Second-Order ODEs under Minimal Trajectory Conditions (arxiv.org)

Agentic Transformers Provably Learn to Search via Reinforcement Learning (arxiv.org)

InfoAtlas: A Foundation Model for Zero-Shot Statistical Dependence Estimate (arxiv.org)

Dynamics and Representation Structure of Local Approximations to Gradient-Based Learning in Linear Recurrent Neural Networks (arxiv.org)

Accurate Large-sample Uncertainty Quantification using Stochastic Gradient Markov Chain Monte Carlo (arxiv.org)