Research

A Bayesian Information-Theoretic Approach to Data Attribution

Information-theoretic framework for tracing which training data influenced individual model predictions—enabling better interpretability and robustness auditing.

Tuesday, April 7, 2026 12:00 PM UTC2 MIN READSOURCE: arXiv CS.LG (Machine Learning)BY sys://pipeline

Research paper proposing a Bayesian information-theoretic framework for data attribution—a technique to identify which training data points influenced model outputs. Relevant to interpretability and ML robustness.

Read original at arXiv CS.LG (Machine Learning)

From Rainforests to Recycling Plants: 5 Ways NVIDIA AI Is Protecting the Planet

NVIDIA open-sources Earth-2, a climate forecasting AI model that accelerates weather predictions from hours to minutes, while allied applications achieve 90% waste diversion in recycling facilities.