Data Science

Harvard opens more free online courses in AI, data science, programming: Check full list and direct links

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...

[D] Offering licensed Indian language speech datasets (with explicit contributor consent)

Hi everyone, I run a small data initiative where we collect speech datasets in multiple Indian languages directly from contributors who p...

[2602.19475] Scale-PINN: Learning Efficient Physics-Informed Neural Networks Through Sequential Correction

The paper presents Scale-PINN, a novel approach to enhance Physics-Informed Neural Networks (PINNs) by integrating a Sequential Correctio...

[2602.19467] Can Large Language Models Replace Human Coders? Introducing ContentBench

This article introduces ContentBench, a benchmark suite assessing the ability of low-cost large language models (LLMs) to perform interpr...

[2602.19219] Controlled Face Manipulation and Synthesis for Data Augmentation

The paper presents a novel method for controlled face manipulation to augment data for facial expression analysis, addressing label scarc...

[2602.19196] An Interpretable Data-Driven Model of the Flight Dynamics of Hawks

This paper presents a data-driven model using dynamic mode decomposition to analyze the flight dynamics of hawks, revealing common behavi...

[2602.19412] Redefining the Down-Sampling Scheme of U-Net for Precision Biomedical Image Segmentation

This paper presents a novel down-sampling strategy called Stair Pooling for U-Net architectures, aimed at enhancing precision in biomedic...

[2602.19441] When AI Teammates Meet Code Review: Collaboration Signals Shaping the Integration of Agent-Authored Pull Requests

This paper investigates how AI-generated pull requests integrate into human-led code review processes, emphasizing the importance of coll...

[2602.19140] CaReFlow: Cyclic Adaptive Rectified Flow for Multimodal Fusion

The paper presents CaReFlow, a novel approach for multimodal fusion that addresses modality gaps using cyclic adaptive rectified flow, en...

[2602.19348] MultiDiffSense: Diffusion-Based Multi-Modal Visuo-Tactile Image Generation Conditioned on Object Shape and Contact Pose

The paper presents MultiDiffSense, a diffusion-based model for generating visuo-tactile images conditioned on object shape and contact po...

[2602.19326] City Editing: Hierarchical Agentic Execution for Dependency-Aware Urban Geospatial Modification

The paper presents a hierarchical framework for urban geospatial modification, enabling efficient urban renewal through agentic systems a...

[2602.19005] GUIDE-US: Grade-Informed Unpaired Distillation of Encoder Knowledge from Histopathology to Micro-UltraSound

The paper presents a novel method for non-invasive grading of prostate cancer using micro-ultrasound, leveraging knowledge distillation f...

[2602.19324] RetinaVision: XAI-Driven Augmented Regulation for Precise Retinal Disease Classification using deep learning framework

The article presents RetinaVision, a deep learning framework for accurate classification of retinal diseases using optical coherence tomo...

[2602.18997] Implicit Bias and Convergence of Matrix Stochastic Mirror Descent

This paper explores the convergence properties of Matrix Stochastic Mirror Descent (SMD) in overparameterized settings, proving that it c...

[2602.19319] Health+: Empowering Individuals via Unifying Health Data

The paper presents Health+, a user-centric health data management system designed to empower individuals by unifying their fragmented hea...

[2602.18895] Could Large Language Models work as Post-hoc Explainability Tools in Credit Risk Models?

This paper explores the potential of large language models (LLMs) as post-hoc explainability tools in credit risk models, evaluating thei...

[2602.18870] Federated Measurement of Demographic Disparities from Quantile Sketches

This paper presents a federated learning approach to measure demographic disparities using quantile sketches, addressing privacy concerns...

[2602.18863] TIACam: Text-Anchored Invariant Feature Learning with Auto-Augmentation for Camera-Robust Zero-Watermarking

The paper presents TIACam, a novel framework for camera-robust zero-watermarking that utilizes text-anchored invariant feature learning w...

[2602.19248] No Need For Real Anomaly: MLLM Empowered Zero-Shot Video Anomaly Detection

The paper presents LAVIDA, a novel zero-shot video anomaly detection framework that utilizes a Multimodal Large Language Model to enhance...

[2602.19241] Scaling Laws for Precision in High-Dimensional Linear Regression

This paper explores scaling laws for low-precision training in high-dimensional linear regression, analyzing the effects of quantization ...

[2602.18762] Bounds and Identification of Joint Probabilities of Potential Outcomes and Observed Variables under Monotonicity Assumptions

This paper explores the bounding and identification of joint probabilities of potential outcomes and observed variables under monotonicit...

[2602.18726] WiCompass: Oracle-driven Data Scaling for mmWave Human Pose Estimation

The paper presents WiCompass, a framework for improving mmWave human pose estimation by focusing on data coverage rather than brute-force...