bertTensorFlow code and pre-trained models for BERT
tuning_playbookA playbook for systematically maximizing the performance of deep learning models.
text-to-text-transfer-transformerCode for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"
arxiv-latex-cleanerarXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv
simclrSimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learners
multinerfA Code Release for Mip-NeRF 360, Ref-NeRF, and RawNeRF
footballCheck out the new game server:
albertALBERT: A Lite BERT for Self-supervised Learning of Language Representations
scenicScenic: A Jax Library for Computer Vision Research and Beyond
electraELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators
frame-interpolationFILM: Frame Interpolation for Large Motion, In ECCV 2022.
udaUnsupervised Data Augmentation (UDA)
kubricA data generation pipeline for creating semi-realistic synthetic multi-object videos with rich annotations such as instance segmentation masks, depth maps, and optical flow.
dex-langResearch language for array processing in the Haskell/ML family
languageShared repository for open-sourced projects from the Google AI Language team.
big_transferOfficial repository for the "Big Transfer (BiT): General Visual Representation Learning" paper.
torchsdeDifferentiable SDE solvers with GPU support and efficient sensitivity analysis.
disentanglement_libdisentanglement_lib is an open-source library for research on learning disentangled representations.
planetLearning Latent Dynamics for Planning from Pixels
tapasEnd-to-end neural table-text understanding models.
fixmatchA simple method to perform semi-supervised learning with limited data.
morph-netFast & Simple Resource-Constrained Learning of Deep Network Structure
big_visionOfficial codebase used to develop Vision Transformer, MLP-Mixer, LiT and more.
batch-ppoEfficient Batched Reinforcement Learning in TensorFlow
deeplab2DeepLab2 is a TensorFlow library for deep labeling, aiming to provide a unified and state-of-the-art TensorFlow codebase for dense pixel labeling tasks.
augmixAugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
maxim[CVPR 2022 Oral] Official repository for "MAXIM: Multi-Axis MLP for Image Processing". SOTA for denoising, deblurring, deraining, dehazing, and enhancement.
seed_rlSEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference. Implements IMPALA and R2D2 algorithms in TF2 with SEED's architecture.
pix2seqPix2Seq codebase: multi-tasks with generative modeling (autoregressive and diffusion)
noisystudentCode for Noisy Student Training. https://arxiv.org/abs/1911.04252
meta-datasetA dataset of datasets for learning to learn from few examples
lottery-ticket-hypothesisA reimplementation of "The Lottery Ticket Hypothesis" (Frankle and Carbin) on MNIST.
recsimA Configurable Recommender Systems Simulation Platform
nasbenchNASBench: A Neural Architecture Search Dataset and Benchmark
rliable[NeurIPS'21 Outstanding Paper] Library for reliable evaluation on RL and ML benchmarks, even with only a handful of seeds.
long-range-arenaLong Range Arena for Benchmarking Efficient Transformers
magvitOfficial JAX implementation of MAGVIT: Masked Generative Video Transformer
xtremeXTREME 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.
bleurtBLEURT is a metric for Natural Language Generation based on transfer learning.
dreamerDream to Control: Learning Behaviors by Latent Imagination
federatedA collection of Google research projects related to Federated Learning and Federated Analytics.
prompt-tuningOriginal Implementation of Prompt Tuning from Lester, et al, 2021
bigbirdTransformers for Longer Sequences
fast-soft-sortFast Differentiable Sorting and Ranking
robopianist[CoRL '23] Dexterous piano playing with deep reinforcement learning.
tensor2robotDistributed machine learning infrastructure for large-scale robotics research
batch_rlOffline Reinforcement Learning (aka Batch Reinforcement Learning) on Atari 2600 games
ravensTrain robotic agents to learn pick and place with deep learning for vision-based manipulation in PyBullet. Transporter Nets, CoRL 2020.
leaf-audioLEAF 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.
mintMulti-modal Content Creation Model Training Infrastructure including the FACT model (AI Choreographer) implementation.
receptive_fieldCompute receptive fields of your favorite convnets
ssl_detectionSemi-supervised learning for object detection
maxvit[ECCV 2022] Official repository for "MaxViT: Multi-Axis Vision Transformer". SOTA foundation models for classification, detection, segmentation, image quality, and generative modeling...
computation-thru-dynamicsUnderstanding computation in artificial and biological recurrent networks through the lens of dynamical systems.
realworldrl_suiteReal-World RL Benchmark Suite
l2pLearning to Prompt (L2P) for Continual Learning @ CVPR22 and DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning @ ECCV22
nerf-from-imageShape, Pose, and Appearance from a Single Image via Bootstrapped Radiance Field Inversion
riglEnd-to-end training of sparse deep neural networks with little-to-no performance loss.
maskgitOfficial Jax Implementation of MaskGIT
python-graphsA static analysis library for computing graph representations of Python programs suitable for use with graph neural networks.
exoplanet-mlMachine learning models and utilities for exoplanet science.
falkenFalken provides developers with a service that allows them to train AI that can play their games
ibcOfficial implementation of Implicit Behavioral Cloning, as described in our CoRL 2021 paper, see more at https://implicitbc.github.io/
3d-momentsCode for CVPR 2022 paper '3D Moments from Near-Duplicate Photos'
episodic-curiosityTensorflow/Keras code and trained models for Episodic Curiosity Through Reachability
nested-transformerNested Hierarchical Transformer https://arxiv.org/pdf/2105.12723.pdf
reassessed-imagenetLabels and other data for the paper "Are we done with ImageNet?"