Data Science

UMKC Announces New Master of Science in Artificial Intelligence

UMKC announces a new Master of Science in Artificial Intelligence program aimed at addressing workforce demand for AI expertise, set to l...

CONESTOGA COLLEGE Robots deepen AI and data analytics training for Conestoga students

Google quietly launched an AI dictation app that works offline | TechCrunch

Google's new offline-first dictation app uses Gemma AI models to take on the apps like Wispr Flow.

[2511.19879] Learning Degenerate Manifolds of Frustrated Magnets with Boltzmann Machines

This paper explores the use of Restricted Boltzmann Machines (RBMs) to model spin configurations in frustrated magnets, demonstrating the...

[2511.14147] Imaging with super-resolution in changing random media

This article presents a novel imaging algorithm that utilizes strong scattering to achieve super-resolution in dynamic random media, enha...

[2511.17772] Weighted Birkhoff Averages Accelerate Data-Driven Methods

The paper discusses Weighted Birkhoff Averages, a method that accelerates convergence in data-driven algorithms for dynamical systems, de...

[2511.04681] Dark Energy Survey Year 3 results: Simulation-based $w$CDM inference from weak lensing and galaxy clustering maps with deep learning: Analysis design

This article presents a novel simulation-based inference pipeline utilizing deep learning to analyze weak lensing and galaxy clustering m...

[2511.03952] High-dimensional limit theorems for SGD: Momentum and Adaptive Step-sizes

This paper presents high-dimensional limit theorems for Stochastic Gradient Descent (SGD) with Polyak Momentum and adaptive step-sizes, c...

[2509.20345] Statistical Inference Leveraging Synthetic Data with Distribution-Free Guarantees

This article presents the GEneral Synthetic-Powered Inference (GESPI) framework, which enhances statistical inference by integrating synt...

[2504.13519] Filter2Noise: A Framework for Interpretable and Zero-Shot Low-Dose CT Image Denoising

The paper presents Filter2Noise, a novel framework for interpretable and zero-shot low-dose CT image denoising, achieving state-of-the-ar...

[2503.20711] Demand Estimation with Text and Image Data

This article presents a novel demand estimation method that utilizes unstructured data from text and images to enhance substitution patte...

[2502.20063] Strategic Hiring under Algorithmic Monoculture

The paper explores strategic hiring in labor markets dominated by algorithmic evaluation, highlighting the inefficiencies of naive hiring...

[2412.00364] LMSeg: Unleashing the Power of Large-Scale Models for Open-Vocabulary Semantic Segmentation

The paper presents LMSeg, a novel approach for open-vocabulary semantic segmentation that enhances visual and linguistic feature alignmen...

[2412.10537] VerifiableFL: Verifiable Claims for Federated Learning using Exclaves

The paper presents VerifiableFL, a system for federated learning that ensures verifiable claims about model training using exclaves, enha...

[2512.00036] Refined Bayesian Optimization for Efficient Beam Alignment in Intelligent Indoor Wireless Environments

This article presents a refined Bayesian optimization framework for efficient beam alignment in intelligent indoor wireless environments,...

[2510.12768] Uncertainty Matters in Dynamic Gaussian Splatting for Monocular 4D Reconstruction

This paper presents USplat4D, a novel framework for monocular 4D reconstruction that incorporates uncertainty in dynamic Gaussian splatti...

[2602.11320] Efficient Analysis of the Distilled Neural Tangent Kernel

The paper presents a novel approach to reduce the computational complexity of Neural Tangent Kernel (NTK) methods through dataset distill...

[2602.10067] Features as Rewards: Scalable Supervision for Open-Ended Tasks via Interpretability

The paper introduces a novel approach to using features as rewards in reinforcement learning for open-ended tasks, focusing on reducing h...

[2510.06200] StarEmbed: Benchmarking Time Series Foundation Models on Astronomical Observations of Variable Stars

The paper introduces StarEmbed, a benchmark for evaluating time series foundation models on astronomical observations of variable stars, ...

[2510.04694] Multilingual Routing in Mixture-of-Experts

This paper explores multilingual routing in Mixture-of-Experts (MoE) architectures, revealing how these models handle multilingual data a...

[2602.08755] Align and Adapt: Multimodal Multiview Human Activity Recognition under Arbitrary View Combinations

The paper presents AliAd, a model for multimodal multiview human activity recognition that enhances performance by integrating diverse vi...

[2601.20568] Reinforcement Unlearning via Group Relative Policy Optimization

This article presents a novel method called PURGE for reinforcement unlearning in large language models, addressing the challenge of safe...

[2601.11616] Mixture-of-Experts as Soft Clustering: A Dual Jacobian-PCA Spectral Geometry Perspective

This paper explores Mixture-of-Experts (MoE) architectures through a geometric lens, analyzing their impact on function representation an...