Answering billions of reporting queries each day with low latency
World scale inverse reinforcement learning in Google Maps
How Project Starline improves remote communication
Better Language Models Without Massive Compute
Characterizing Emergent Phenomena in Large Language Models
UL2 20B: An Open Source Unified Language Learner
Language Models Perform Reasoning via Chain of Thought
Using Deep Learning to Annotate the Protein Universe
Google Research: Themes from 2021 and Beyond
Google at ICCV 2021
Introducing FLAN: More generalizable Language Models with Instruction Fine-Tuning
