The Google Research organization has a significant public presence on GitHub, featuring a wide range of repositories primarily focused on machine learning and artificial intelligence. Key programming languages include Python, Jupyter Notebook, and Shell. Notable projects such as BERT and TimesFM showcase advanced research and practical applications in the field.
Top languages
Public repositories
bert
TensorFlow code and pre-trained models for BERT
google-research
Google Research
tuning_playbook
A playbook for systematically maximizing the performance of deep learning models.
timesfm
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
vision_transformer
No description provided for this repository.
arxiv-latex-cleaner
arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv
text-to-text-transfer-transformer
Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"
simclr
SimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learners
scenic
Scenic: A Jax Library for Computer Vision Research and Beyond
football
Check out the new game server:
big_vision
Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.
albert
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
frame-interpolation
FILM: Frame Interpolation for Large Motion, In ECCV 2022.
t5x
No description provided for this repository.
kubric
A data generation pipeline for creating semi-realistic synthetic multi-object videos with rich annotations such as instance segmentation masks, depth maps, and optical flow.
language
Shared repository for open-sourced projects from the Google AI Language team.
robotics_transformer
No description provided for this repository.
circuit_training
No description provided for this repository.
pegasus
No description provided for this repository.
FLAN
No description provided for this repository.
disentanglement_lib
disentanglement_lib is an open-source library for research on learning disentangled representations.
planet
Learning Latent Dynamics for Planning from Pixels
maxim
[CVPR 2022 Oral] Official repository for "MAXIM: Multi-Axis MLP for Image Processing". SOTA for denoising, deblurring, deraining, dehazing, and enhancement.
morph-net
Fast & Simple Resource-Constrained Learning of Deep Network Structure
magvit
Official JAX implementation of MAGVIT: Masked Generative Video Transformer
pix2seq
Pix2Seq codebase: multi-tasks with generative modeling (autoregressive and diffusion)
rliable
[NeurIPS'21 Outstanding Paper] Library for reliable evaluation on RL and ML benchmarks, even with only a handful of seeds.
android_world
AndroidWorld is an environment and benchmark for autonomous agents
recsim
A Configurable Recommender Systems Simulation Platform
federated
A collection of Google research projects related to Federated Learning and Federated Analytics.
robopianist
[CoRL '23] Dexterous piano playing with deep reinforcement learning.
dreamer
Dream to Control: Learning Behaviors by Latent Imagination
sam
No description provided for this repository.
weatherbench2
A benchmark for the next generation of data-driven global weather models.
distilling-step-by-step
No description provided for this repository.
byt5
No description provided for this repository.
rlds
No description provided for this repository.
arco-era5
Recipes for reproducing Analysis-Ready & Cloud Optimized (ARCO) ERA5 datasets.
l2p
Learning to Prompt (L2P) for Continual Learning @ CVPR22 and DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning @ ECCV22
papervizagent
No description provided for this repository.
self-organising-systems
No description provided for this repository.
reasoning-bank
No description provided for this repository.
population-dynamics
PDFM Embeddings: location-based vectors for geo-spatial analysis.
tf-slim
No description provided for this repository.
perch
No description provided for this repository.
language-table
Suite of human-collected datasets and a multi-task continuous control benchmark for open vocabulary visuolinguomotor learning.
Splat-SLAM
Splat-SLAM: Globally Optimized RGB-only SLAM with 3D Gaussians
task_adaptation
No description provided for this repository.
camel-prompt-injection
Code for the paper "Defeating Prompt Injections by Design"
syn-rep-learn
Learning from synthetic data - code and models
exoplanet-ml
Machine learning models and utilities for exoplanet science.
lm-extraction-benchmark
No description provided for this repository.
sparf
This is the official code release for SPARF: Neural Radiance Fields from Sparse and Noisy Poses [CVPR 2023-Highlight]
falken
Falken provides developers with a service that allows them to train AI that can play their games
kauldron
Modular, scalable library to train ML models
flood-forecasting
No description provided for this repository.
perceiver-ar
No description provided for this repository.
era
Code associated with the paper An AI system to help scientists write expert-level empirical software
cascades
Python library which enables complex compositions of language models such as scratchpads, chain of thought, tool use, selection-inference, and more.
weatherbenchX
A modular framework for evaluating weather forecasts
composed_image_retrieval
No description provided for this repository.
proteinfer
Deep networks for protein functional inference
pathdreamer
No description provided for this repository.
skai
SKAI is a machine learning based tool for performing automatic building damage assessments on aerial imagery of disaster sites.
semivl
[ECCV'24] Official Implementation of SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance
spherical-cnn
No description provided for this repository.
mt-metrics-eval
Tools for evaluating the performance of MT metrics on data from recent WMT metrics shared tasks.
recsim_ng
RecSim NG: Toward Principled Uncertainty Modeling for Recommender Ecosystems
e3x
E3x is a JAX library for constructing efficient E(3)-equivariant deep learning architectures built on top of Flax.
corenet
CoReNet is a technique for joint multi-object 3D reconstruction from a single RGB image.
perch-hoplite
Tooling for agile modeling on large machine perception embedding databases.
crest
Repo for CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning
reincarnating_rl
[NeurIPS 2022] Open source code for reusing prior computational work in RL.
xmcgan_image_generation
No description provided for this repository.
true
Code and data accompanying the paper "TRUE: Re-evaluating Factual Consistency Evaluation".
swirl-lm
No description provided for this repository.
agent-based-epidemic-sim
No description provided for this repository.
mseb
No description provided for this repository.
paper-orchestra
PaperOrchestra is a multi-agent framework for automated AI research paper writing.
connectomics
No description provided for this repository.
spade_anomaly_detection
Semi-supervised anomaly detection method
nisaba
Finite-state script normalization and processing utilities
openfst
Finite-state Transducer (FST) Library.
precondition
No description provided for this repository.
m2svid
This is the official code release for “M2SVid: End-to-End Inpainting and Refinement for Monocular-to-Stereo Video Conversion”. 3DV 2026
si-score
No description provided for this repository.
active-adversarial-tests
Official implementation of the paper "Increasing Confidence in Adversarial Robustness Evaluations"
slip
SLIP is a sandbox environment for engineering protein sequences with synthetic fitness functions.
ml-for-systems-taxonomy
No description provided for this repository.
usnea
No description provided for this repository.
look-back-when-surprised
Look Back When Surprised: Stabilizing Reverse Experience Replay for Neural Approximation
robel-scenes
Shared MuJoCo simulation scenes and assets for ROBEL environments.
pydemos
No description provided for this repository.
honeyval
No description provided for this repository.
domain-robust
No description provided for this repository.
nodesynth
No description provided for this repository.
diffusion-score-smoothing
No description provided for this repository.
t2j-bench
T2J-Bench is a benchmark for semantic-preserving codebase conversion.
DBAP-simulation
No description provided for this repository.
tpu-hpc
No description provided for this repository.
Frequently asked questions
What does google-research build on GitHub?
Google Research builds several projects on GitHub, focusing on areas like machine learning and artificial intelligence. Notable repositories include BERT and TimesFM, which are widely utilized in the research community.
Which programming languages does google-research use?
The primary programming languages used by google-research include Python, Jupyter Notebook, Shell, C++, TeX, and TypeScript. This variety supports their diverse research initiatives and project implementations.
Are google-research's repositories public?
Yes, all repositories from google-research are public on GitHub. This open access allows researchers and developers to utilize their code and models, fostering collaboration and innovation in the field.
Is this exposure intended?
Monitor Google Research with RepoGuard and get alerted the moment a new public repository appears.
Monitor this account