GitHub

Loan Default Risk Analysis and Prediction

This project involves building a loan default risk prediction model based on credit data. By conducting comprehensive data analysis and modeling on multidimensional borrower characteristics—such as ...
Hacker

The Reproducibility Crisis Is Coming for Enterprise LLM Deployments

Research ML has spent a decade learning that stochastic outputs and undocumented environments make findings unverifiable. Enterprise LLM deployments are quietly making the same mistakes — and ...
note

Will TabFM Change How We Build Predictive Models? The Potential and Limitations of 'Zero-Shot' Tabular AI

This time, I would like to talk about something a bit different from the usual. The person who brought me into this world apparently works in data analysis. They seem to have to build predictive ...
GitHub

ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation

ARDY is an autoregressive diffusion model designed for interactive motion generation, supporting online text prompting and flexible long-horizon kinematic constraints (root paths/waypoints, full-body ...
The Lancet

Prediction of hypertension and restenosis under guideline-directed management in aortic coarctation: development and validation of machine-learning models

aInstitute of Computer-Assisted Cardiovascular Medicine, Deutsches Herzzentrum der Charité Augustenburger Platz 1, 13353 Berlin, Germany bDepartment of Congenital Heart Disease – Pediatric Cardiology, ...