Back to home

Tag

Google Research

Google Research covers the core engineering behind modern AI: inference efficiency, memory compression, prompt behavior, and benchmark reliability. Its work often shapes how models are deployed, measured, and optimized in production.

2 articles

TurboQuant cuts memory use 6x without accuracy loss
Research/Apr 3

TurboQuant cuts memory use 6x without accuracy loss

Google Research’s TurboQuant claims 6x less memory and 8x faster inference with no accuracy loss, jolting AI inference economics.

Duplicate Prompts Can Lift Accuracy Fast
Research/Apr 2

Duplicate Prompts Can Lift Accuracy Fast

A Google study found repeating prompts once improved 47 of 70 model-benchmark pairs, with one task jumping from 21% to 97%.