Skip to main content

The latest research from Google

Large sequence models for software development activities

Software isn’t created in one dramatic step. It improves bit by bit, one little step at a time — editing, running unit tests, fixing build errors, addressing code reviews, editing some more, appeasing linters, and fixing more errors — until finally it becomes good enough to merge into a code repository. Software engineering isn’t an isolated process, but a dialogue among human developers, code reviewers, bug reporters, software architects and tools, such as compilers, unit tests, linters and static analyzers.

Foundation models for reasoning on charts

Barkour: Benchmarking animal-level agility with quadruped robots

Differentially private clustering for large-scale datasets

Google Research at I/O 2023

Resolving code review comments with ML

Making ML models differentially private: Best practices and open challenges

Sparse video tubes for joint video and image vision transformers

Responsible AI at Google Research: PAIR

Using reinforcement learning for dynamic planning in open-ended conversations

Larger language models do in-context learning differently