Data Science

Google quietly launched an AI dictation app that works offline

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

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

[2508.01067] Expressive Power of Graph Transformers via Logic

This paper explores the expressive power of graph transformers, comparing their capabilities under different logical frameworks, particul...

[2512.18454] Out-of-Distribution Detection in Molecular Complexes via Diffusion Models for Irregular Graphs

This paper presents a novel framework for out-of-distribution (OOD) detection in molecular complexes using diffusion models tailored for ...

[2512.22623] Communication Compression for Distributed Learning with Aggregate and Server-Guided Feedback

This paper presents novel frameworks for communication compression in distributed learning, addressing bandwidth constraints in federated...

[2511.12158] Data-Efficient Self-Supervised Algorithms for Fine-Grained Birdsong Analysis

This article presents a novel approach to birdsong analysis using data-efficient self-supervised algorithms, focusing on a lightweight ne...

[2511.10831] A Versatile Variational Quantum Kernel Framework for Non-Trivial Classification

This article presents a novel variational quantum kernel framework aimed at enhancing classification tasks in machine learning, demonstra...

[2505.03795] Modeling Human Behavior in a Strategic Network Game with Complex Group Dynamics

This article explores modeling human behavior in strategic network games, focusing on the Junior High Game (JHG) and comparing various be...

[2504.19223] CARL: Camera-Agnostic Representation Learning for Spectral Image Analysis

The paper presents CARL, a camera-agnostic model for spectral image analysis that enhances AI methodologies across various imaging modali...

[2510.24318] Transformers can do Bayesian Clustering

The paper presents Cluster-PFN, a Transformer-based model for unsupervised Bayesian clustering, demonstrating improved accuracy and speed...

[2510.16161] Still Competitive: Revisiting Recurrent Models for Irregular Time Series Prediction

The paper presents GRUwE, a novel Gated Recurrent Unit model designed for predicting irregularly sampled multivariate time series, demons...

[2509.25380] Predicting Training Re-evaluation Curves Enables Effective Data Curriculums for LLMs

The paper introduces the Training Re-evaluation Curve (TREC), a diagnostic tool for optimizing data placement in LLM training, revealing ...

[2509.22007] Stage-wise Dynamics of Classifier-Free Guidance in Diffusion Models

This paper explores the dynamics of Classifier-Free Guidance (CFG) in diffusion models, revealing its effects on sampling processes and d...

[2502.14894] FOCUS on Contamination: Hydrology-Informed Noise-Aware Learning for Geospatial PFAS Mapping

The paper introduces FOCUS, a deep learning framework for mapping PFAS contamination by integrating sparse data with environmental contex...

[2508.11810] FairTabGen: High-Fidelity and Fair Synthetic Health Data Generation from Limited Samples

FairTabGen introduces a novel framework for generating high-fidelity synthetic healthcare data from limited samples, enhancing fairness a...

[2508.10836] SoK: Data Minimization in Machine Learning

The paper presents a systematization of knowledge on data minimization in machine learning, addressing its importance in regulatory compl...

[2508.02566] Model-Agnostic Dynamic Feature Selection with Uncertainty Quantification

This paper presents a model-agnostic framework for dynamic feature selection (DFS) that incorporates uncertainty quantification, addressi...

[2507.12257] Robust Causal Discovery in Real-World Time Series with Power-Laws

This paper presents a novel method for causal discovery in time series data, leveraging power-law distributions to enhance robustness aga...

[2411.16537] RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for Robotics

The paper presents RoboSpatial, a dataset aimed at enhancing spatial understanding in robotics by providing 2D and 3D vision-language mod...

[2507.06009] KnowIt: Deep Time Series Modeling and Interpretation

KnowIt is a Python toolkit designed for deep time series modeling and interpretation, allowing users to build models and explain their be...

[2507.04033] Benchmarking Stochastic Approximation Algorithms for Fairness-Constrained Training of Deep Neural Networks

This paper benchmarks stochastic approximation algorithms for fairness-constrained training of deep neural networks, addressing theoretic...

[2409.17091] Ctrl-GenAug: Controllable Generative Augmentation for Medical Sequence Classification

The paper presents Ctrl-GenAug, a novel framework for controllable generative augmentation in medical sequence classification, addressing...