Skip to main content

The latest research from Google

VideoPrism: A foundational visual encoder for video understanding

An astounding number of videos are available on the Web, covering a variety of content from everyday moments people share to historical moments to scientific observations, each of which contains a unique record of the world. The right tools could help researchers analyze these videos, transforming how we understand the world around us.

Advances in private training for production on-device language models

Learning the importance of training data under concept drift

DP-Auditorium: A flexible library for auditing differential privacy

Graph neural networks in TensorFlow

A decoder-only foundation model for time-series forecasting

Intervening on early readouts for mitigating spurious features and simplicity bias

MobileDiffusion: Rapid text-to-image generation on-device

Mixed-input matrix multiplication performance optimizations

Exphormer: Scaling transformers for graph-structured data

Introducing ASPIRE for selective prediction in LLMs