Google Research: Language
Shared repository for open-sourced projects from the Google Research Language team.
This is not an official Google product.
There are no reviews yet. Be the first to send feedback to the community and the maintainers!
Shared repository for open-sourced projects from the Google Research Language team.
This is not an official Google product.
bert
TensorFlow code and pre-trained models for BERTgoogle-research
Google Researchtuning_playbook
A playbook for systematically maximizing the performance of deep learning models.vision_transformer
text-to-text-transfer-transformer
Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"arxiv-latex-cleaner
arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXivsimclr
SimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learnersmultinerf
A Code Release for Mip-NeRF 360, Ref-NeRF, and RawNeRFtimesfm
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.scenic
Scenic: A Jax Library for Computer Vision Research and Beyondfootball
Check out the new game server:albert
ALBERT: A Lite BERT for Self-supervised Learning of Language Representationsframe-interpolation
FILM: Frame Interpolation for Large Motion, In ECCV 2022.t5x
electra
ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generatorskubric
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.big_vision
Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.uda
Unsupervised Data Augmentation (UDA)pegasus
dex-lang
Research language for array processing in the Haskell/ML familytorchsde
Differentiable SDE solvers with GPU support and efficient sensitivity analysis.parti
big_transfer
Official repository for the "Big Transfer (BiT): General Visual Representation Learning" paper.FLAN
robotics_transformer
disentanglement_lib
disentanglement_lib is an open-source library for research on learning disentangled representations.multilingual-t5
circuit_training
tapas
End-to-end neural table-text understanding models.planet
Learning Latent Dynamics for Planning from Pixelsmixmatch
deduplicate-text-datasets
fixmatch
A simple method to perform semi-supervised learning with limited data.morph-net
Fast & Simple Resource-Constrained Learning of Deep Network Structuremaxim
[CVPR 2022 Oral] Official repository for "MAXIM: Multi-Axis MLP for Image Processing". SOTA for denoising, deblurring, deraining, dehazing, and enhancement.deeplab2
DeepLab2 is a TensorFlow library for deep labeling, aiming to provide a unified and state-of-the-art TensorFlow codebase for dense pixel labeling tasks.batch-ppo
Efficient Batched Reinforcement Learning in TensorFlowaugmix
AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintymagvit
Official JAX implementation of MAGVIT: Masked Generative Video Transformerpix2seq
Pix2Seq codebase: multi-tasks with generative modeling (autoregressive and diffusion)seed_rl
SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference. Implements IMPALA and R2D2 algorithms in TF2 with SEED's architecture.meta-dataset
A dataset of datasets for learning to learn from few examplesnoisystudent
Code for Noisy Student Training. https://arxiv.org/abs/1911.04252rliable
[NeurIPS'21 Outstanding Paper] Library for reliable evaluation on RL and ML benchmarks, even with only a handful of seeds.recsim
A Configurable Recommender Systems Simulation Platformjax3d
long-range-arena
Long Range Arena for Benchmarking Efficient Transformerslottery-ticket-hypothesis
A reimplementation of "The Lottery Ticket Hypothesis" (Frankle and Carbin) on MNIST.federated
A collection of Google research projects related to Federated Learning and Federated Analytics.bleurt
BLEURT is a metric for Natural Language Generation based on transfer learning.prompt-tuning
Original Implementation of Prompt Tuning from Lester, et al, 2021nasbench
NASBench: A Neural Architecture Search Dataset and Benchmarkneuralgcm
Hybrid ML + physics model of the Earth's atmospherextreme
XTREME is a benchmark for the evaluation of the cross-lingual generalization ability of pre-trained multilingual models that covers 40 typologically diverse languages and includes nine tasks.lasertagger
sound-separation
pix2struct
vmoe
dreamer
Dream to Control: Learning Behaviors by Latent Imaginationrobopianist
[CoRL '23] Dexterous piano playing with deep reinforcement learning.omniglue
Code release for CVPR'24 submission 'OmniGlue'fast-soft-sort
Fast Differentiable Sorting and Rankingravens
Train robotic agents to learn pick and place with deep learning for vision-based manipulation in PyBullet. Transporter Nets, CoRL 2020.sam
batch_rl
Offline Reinforcement Learning (aka Batch Reinforcement Learning) on Atari 2600 gamesbigbird
Transformers for Longer Sequencestensor2robot
Distributed machine learning infrastructure for large-scale robotics researchbyt5
adapter-bert
mint
Multi-modal Content Creation Model Training Infrastructure including the FACT model (AI Choreographer) implementation.leaf-audio
LEAF is a learnable alternative to audio features such as mel-filterbanks, that can be initialized as an approximation of mel-filterbanks, and then be trained for the task at hand, while using a very small number of parameters.robustness_metrics
maxvit
[ECCV 2022] Official repository for "MaxViT: Multi-Axis Vision Transformer". SOTA foundation models for classification, detection, segmentation, image quality, and generative modeling...receptive_field
Compute receptive fields of your favorite convnetsmaskgit
Official Jax Implementation of MaskGITweatherbench2
A benchmark for the next generation of data-driven global weather models.l2p
Learning to Prompt (L2P) for Continual Learning @ CVPR22 and DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning @ ECCV22distilling-step-by-step
ssl_detection
Semi-supervised learning for object detectionnerf-from-image
Shape, Pose, and Appearance from a Single Image via Bootstrapped Radiance Field Inversioncomputation-thru-dynamics
Understanding computation in artificial and biological recurrent networks through the lens of dynamical systems.tf-slim
realworldrl_suite
Real-World RL Benchmark Suitepython-graphs
A static analysis library for computing graph representations of Python programs suitable for use with graph neural networks.rigl
End-to-end training of sparse deep neural networks with little-to-no performance loss.task_adaptation
self-organising-systems
ibc
Official implementation of Implicit Behavioral Cloning, as described in our CoRL 2021 paper, see more at https://implicitbc.github.io/tensorflow_constrained_optimization
syn-rep-learn
Learning from synthetic data - code and modelsarco-era5
Recipes for reproducing Analysis-Ready & Cloud Optimized (ARCO) ERA5 datasets.vdm
rlds
exoplanet-ml
Machine learning models and utilities for exoplanet science.retvec
RETVec is an efficient, multilingual, and adversarially-robust text vectorizer.sparf
This is the official code release for SPARF: Neural Radiance Fields from Sparse and Noisy Poses [CVPR 2023-Highlight]tensorflow-coder
lm-extraction-benchmark
language-table
Suite of human-collected datasets and a multi-task continuous control benchmark for open vocabulary visuolinguomotor learning.falken
Falken provides developers with a service that allows them to train AI that can play their gamesLove Open Source and this site? Check out how you can help us