Data Science

Data analysis, statistics, and data engineering

Top This Week

Top 10 AI certifications and courses for 2026
Ai Startups

Top 10 AI certifications and courses for 2026

This article reviews the top 10 AI certifications and courses for 2026, highlighting their significance in a rapidly evolving field and t...

AI Events · 15 min ·
[2603.18109] Discovery of Bimodal Drift Rate Structure in FRB 20240114A: Evidence for Dual Emission Regions
Machine Learning

[2603.18109] Discovery of Bimodal Drift Rate Structure in FRB 20240114A: Evidence for Dual Emission Regions

Abstract page for arXiv paper 2603.18109: Discovery of Bimodal Drift Rate Structure in FRB 20240114A: Evidence for Dual Emission Regions

arXiv - AI · 4 min ·
[2509.22367] What Is The Political Content in LLMs' Pre- and Post-Training Data?
Llms

[2509.22367] What Is The Political Content in LLMs' Pre- and Post-Training Data?

Abstract page for arXiv paper 2509.22367: What Is The Political Content in LLMs' Pre- and Post-Training Data?

arXiv - AI · 4 min ·

All Content

[2602.18089] DohaScript: A Large-Scale Multi-Writer Dataset for Continuous Handwritten Hindi Text
Data Science

[2602.18089] DohaScript: A Large-Scale Multi-Writer Dataset for Continuous Handwritten Hindi Text

DohaScript introduces a large-scale dataset for continuous handwritten Hindi text, addressing the lack of diverse and high-quality resour...

arXiv - Machine Learning · 4 min ·
[2602.18045] Conformal Tradeoffs: Guarantees Beyond Coverage
Nlp

[2602.18045] Conformal Tradeoffs: Guarantees Beyond Coverage

This article presents a framework for operational certification in conformal predictors, focusing on trade-offs beyond mere coverage, and...

arXiv - AI · 4 min ·
[2602.17779] Topological Exploration of High-Dimensional Empirical Risk Landscapes: general approach, and applications to phase retrieval
Machine Learning

[2602.17779] Topological Exploration of High-Dimensional Empirical Risk Landscapes: general approach, and applications to phase retrieval

This paper explores the topological properties of high-dimensional empirical risk landscapes, focusing on phase retrieval applications an...

arXiv - Machine Learning · 4 min ·
[2602.17776] Solving and learning advective multiscale Darcian dynamics with the Neural Basis Method
Machine Learning

[2602.17776] Solving and learning advective multiscale Darcian dynamics with the Neural Basis Method

The paper presents the Neural Basis Method, a new approach for solving and learning advective multiscale Darcian dynamics, enhancing stab...

arXiv - Machine Learning · 3 min ·
[2602.17773] Learning Flow Distributions via Projection-Constrained Diffusion on Manifolds
Machine Learning

[2602.17773] Learning Flow Distributions via Projection-Constrained Diffusion on Manifolds

The paper presents a novel generative modeling framework for synthesizing physically feasible two-dimensional incompressible flows, addre...

arXiv - Machine Learning · 3 min ·
[2602.17772] Sparse Bayesian Modeling of EEG Channel Interactions Improves P300 Brain-Computer Interface Performance
Machine Learning

[2602.17772] Sparse Bayesian Modeling of EEG Channel Interactions Improves P300 Brain-Computer Interface Performance

This article presents a novel sparse Bayesian modeling approach to enhance the performance of P300 brain-computer interfaces (BCIs) by ef...

arXiv - Machine Learning · 4 min ·
[2602.18019] DeepSVU: Towards In-depth Security-oriented Video Understanding via Unified Physical-world Regularized MoE
Computer Vision

[2602.18019] DeepSVU: Towards In-depth Security-oriented Video Understanding via Unified Physical-world Regularized MoE

The paper introduces DeepSVU, a novel approach for Security-oriented Video Understanding that identifies threats and evaluates their caus...

arXiv - AI · 4 min ·
[2602.17770] CLUTCH: Contextualized Language model for Unlocking Text-Conditioned Hand motion modelling in the wild
Llms

[2602.17770] CLUTCH: Contextualized Language model for Unlocking Text-Conditioned Hand motion modelling in the wild

The paper introduces CLUTCH, a novel model for generating hand motions from text, leveraging a new dataset and advanced techniques to imp...

arXiv - Machine Learning · 4 min ·
[2602.17747] AgriVariant: Variant Effect Prediction using DeepChem-Variant for Precision Breeding in Rice
Machine Learning

[2602.17747] AgriVariant: Variant Effect Prediction using DeepChem-Variant for Precision Breeding in Rice

The article presents AgriVariant, a deep learning-based pipeline for predicting the effects of genetic variants in rice, enhancing precis...

arXiv - Machine Learning · 3 min ·
[2602.17730] Clever Materials: When Models Identify Good Materials for the Wrong Reasons
Machine Learning

[2602.17730] Clever Materials: When Models Identify Good Materials for the Wrong Reasons

This article examines the limitations of machine learning in materials discovery, highlighting that high performance on benchmarks may st...

arXiv - Machine Learning · 3 min ·
[2602.17708] Spectral Homogenization of the Radiative Transfer Equation via Low-Rank Tensor Train Decomposition
Machine Learning

[2602.17708] Spectral Homogenization of the Radiative Transfer Equation via Low-Rank Tensor Train Decomposition

This paper presents a novel approach to solving the radiative transfer equation using low-rank tensor train decomposition, enhancing comp...

arXiv - Machine Learning · 4 min ·
[2602.17701] Deep Neural Network Architectures for Electrocardiogram Classification: A Comprehensive Evaluation
Machine Learning

[2602.17701] Deep Neural Network Architectures for Electrocardiogram Classification: A Comprehensive Evaluation

This article evaluates various deep neural network architectures for ECG classification, highlighting the effectiveness of CNN-LSTM model...

arXiv - Machine Learning · 4 min ·
[2602.17973] PenTiDef: Enhancing Privacy and Robustness in Decentralized Federated Intrusion Detection Systems against Poisoning Attacks
Ai Infrastructure

[2602.17973] PenTiDef: Enhancing Privacy and Robustness in Decentralized Federated Intrusion Detection Systems against Poisoning Attacks

The paper presents PenTiDef, a novel framework designed to enhance privacy and robustness in decentralized federated intrusion detection ...

arXiv - AI · 4 min ·
[2602.17949] CUICurate: A GraphRAG-based Framework for Automated Clinical Concept Curation for NLP applications
Machine Learning

[2602.17949] CUICurate: A GraphRAG-based Framework for Automated Clinical Concept Curation for NLP applications

CUICurate introduces a GraphRAG framework for automated curation of clinical concepts in NLP, enhancing efficiency and accuracy in clinic...

arXiv - AI · 4 min ·
[2602.18435] Assigning Confidence: K-partition Ensembles
Machine Learning

[2602.18435] Assigning Confidence: K-partition Ensembles

The paper introduces CAKE, a framework for assessing confidence in clustering assignments using K-partition ensembles, enhancing the reli...

arXiv - Machine Learning · 3 min ·
[2602.17907] Improving Neural Topic Modeling with Semantically-Grounded Soft Label Distributions
Llms

[2602.17907] Improving Neural Topic Modeling with Semantically-Grounded Soft Label Distributions

This paper presents a novel approach to neural topic modeling by using semantically-grounded soft label distributions, enhancing topic co...

arXiv - AI · 3 min ·
[2602.18403] Scientific Knowledge-Guided Machine Learning for Vessel Power Prediction: A Comparative Study
Machine Learning

[2602.18403] Scientific Knowledge-Guided Machine Learning for Vessel Power Prediction: A Comparative Study

This study presents a hybrid modeling framework that combines scientific knowledge with machine learning to improve vessel power predicti...

arXiv - Machine Learning · 4 min ·
[2602.18396] PRISM-FCP: Byzantine-Resilient Federated Conformal Prediction via Partial Sharing
Machine Learning

[2602.18396] PRISM-FCP: Byzantine-Resilient Federated Conformal Prediction via Partial Sharing

The paper presents PRISM-FCP, a Byzantine-resilient framework for federated conformal prediction that enhances robustness against attacks...

arXiv - Machine Learning · 4 min ·
[2602.18348] Explaining AutoClustering: Uncovering Meta-Feature Contribution in AutoML for Clustering
Machine Learning

[2602.18348] Explaining AutoClustering: Uncovering Meta-Feature Contribution in AutoML for Clustering

This article explores the explainability of AutoClustering methods in AutoML, focusing on the contribution of dataset meta-features to al...

arXiv - Machine Learning · 4 min ·
[2602.18308] JPmHC Dynamical Isometry via Orthogonal Hyper-Connections
Machine Learning

[2602.18308] JPmHC Dynamical Isometry via Orthogonal Hyper-Connections

The paper presents JPmHC, a framework enhancing deep learning stability by replacing identity skips in residual connections with a traina...

arXiv - AI · 4 min ·
Previous Page 88 Next

Related Topics

Stay updated with AI News

Get the latest news, tools, and insights delivered to your inbox.

Daily or weekly digest • Unsubscribe anytime