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 RawNeRFfootball
Check out the new game server:albert
ALBERT: A Lite BERT for Self-supervised Learning of Language Representationsscenic
Scenic: A Jax Library for Computer Vision Research and Beyondelectra
ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generatorst5x
frame-interpolation
FILM: Frame Interpolation for Large Motion, In ECCV 2022.uda
Unsupervised Data Augmentation (UDA)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.pegasus
dex-lang
Research language for array processing in the Haskell/ML familylanguage
Shared repository for open-sourced projects from the Google AI Language team.parti
big_transfer
Official repository for the "Big Transfer (BiT): General Visual Representation Learning" paper.torchsde
Differentiable SDE solvers with GPU support and efficient sensitivity analysis.disentanglement_lib
disentanglement_lib is an open-source library for research on learning disentangled representations.FLAN
multilingual-t5
planet
Learning Latent Dynamics for Planning from Pixelsmixmatch
tapas
End-to-end neural table-text understanding models.fixmatch
A simple method to perform semi-supervised learning with limited data.morph-net
Fast & Simple Resource-Constrained Learning of Deep Network Structurerobotics_transformer
big_vision
Official codebase used to develop Vision Transformer, MLP-Mixer, LiT and more.batch-ppo
Efficient Batched Reinforcement Learning in TensorFlowdeeplab2
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.augmix
AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintymaxim
[CVPR 2022 Oral] Official repository for "MAXIM: Multi-Axis MLP for Image Processing". SOTA for denoising, deblurring, deraining, dehazing, and enhancement.seed_rl
SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference. Implements IMPALA and R2D2 algorithms in TF2 with SEED's architecture.deduplicate-text-datasets
pix2seq
Pix2Seq codebase: multi-tasks with generative modeling (autoregressive and diffusion)noisystudent
Code for Noisy Student Training. https://arxiv.org/abs/1911.04252meta-dataset
A dataset of datasets for learning to learn from few exampleslottery-ticket-hypothesis
A reimplementation of "The Lottery Ticket Hypothesis" (Frankle and Carbin) on MNIST.recsim
A Configurable Recommender Systems Simulation Platformjax3d
nasbench
NASBench: A Neural Architecture Search Dataset and Benchmarkcircuit_training
rliable
[NeurIPS'21 Outstanding Paper] Library for reliable evaluation on RL and ML benchmarks, even with only a handful of seeds.long-range-arena
Long Range Arena for Benchmarking Efficient Transformersmagvit
Official JAX implementation of MAGVIT: Masked Generative Video Transformerxtreme
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
bleurt
BLEURT is a metric for Natural Language Generation based on transfer learning.dreamer
Dream to Control: Learning Behaviors by Latent Imaginationfederated
A collection of Google research projects related to Federated Learning and Federated Analytics.sound-separation
prompt-tuning
Original Implementation of Prompt Tuning from Lester, et al, 2021bigbird
Transformers for Longer Sequencesfast-soft-sort
Fast Differentiable Sorting and Rankingrobopianist
[CoRL '23] Dexterous piano playing with deep reinforcement learning.tensor2robot
Distributed machine learning infrastructure for large-scale robotics researchbatch_rl
Offline Reinforcement Learning (aka Batch Reinforcement Learning) on Atari 2600 gamesravens
Train robotic agents to learn pick and place with deep learning for vision-based manipulation in PyBullet. Transporter Nets, CoRL 2020.sam
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
byt5
mint
Multi-modal Content Creation Model Training Infrastructure including the FACT model (AI Choreographer) implementation.vmoe
adapter-bert
receptive_field
Compute receptive fields of your favorite convnetsssl_detection
Semi-supervised learning for object detectionmaxvit
[ECCV 2022] Official repository for "MaxViT: Multi-Axis Vision Transformer". SOTA foundation models for classification, detection, segmentation, image quality, and generative modeling...pix2struct
tf-slim
computation-thru-dynamics
Understanding computation in artificial and biological recurrent networks through the lens of dynamical systems.realworldrl_suite
Real-World RL Benchmark Suitel2p
Learning to Prompt (L2P) for Continual Learning @ CVPR22 and DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning @ ECCV22nerf-from-image
Shape, Pose, and Appearance from a Single Image via Bootstrapped Radiance Field Inversionrigl
End-to-end training of sparse deep neural networks with little-to-no performance loss.maskgit
Official Jax Implementation of MaskGITtensorflow_constrained_optimization
python-graphs
A static analysis library for computing graph representations of Python programs suitable for use with graph neural networks.exoplanet-ml
Machine learning models and utilities for exoplanet science.task_adaptation
tensorflow-coder
falken
Falken provides developers with a service that allows them to train AI that can play their gamesibc
Official implementation of Implicit Behavioral Cloning, as described in our CoRL 2021 paper, see more at https://implicitbc.github.io/self-organising-systems
vdm
distilling-step-by-step
ott
perceiver-ar
3d-moments
Code for CVPR 2022 paper '3D Moments from Near-Duplicate Photos'lm-extraction-benchmark
lag
episodic-curiosity
Tensorflow/Keras code and trained models for Episodic Curiosity Through Reachabilitynested-transformer
Nested Hierarchical Transformer https://arxiv.org/pdf/2105.12723.pdfdata-driven-advection
jaxpruner
reassessed-imagenet
Labels and other data for the paper "Are we done with ImageNet?"Love Open Source and this site? Check out how you can help us