google-research/google-research: Google Research

google-research/deduplicate-text-datasets:

google-research/remixmatch:

google-research/deadunits:

google-research/vision_transformer:

google-research/pyreach:

google-research/byt5:

google-research/task_adaptation:

google-research/football: Check out the new game server:

google-research/arxiv-latex-cleaner: arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

google-research/citrus-nlp:

google-research/proteinfer:

google-research/tensor2robot: Distributed machine learning infrastructure for large-scale robotics research

google-research/pddm:

google-research/meta-dataset: A dataset of datasets for learning to learn from few examples

google-research/nisaba: Finite-state script normalization and processing utilities

google-research/rlds:

google-research/sam:

google-research/cryptanalytic-model-extraction:

google-research/agent-based-epidemic-sim:

google-research/localmot:

google-research/DBAP-simulation:

google-research/DBAP-algorithm:

google-research/robustness_metrics:

google-research/mixmatch:

google-research/adamatch:

google-research/tapas: End-to-end neural table-text understanding models.

google-research/lag:

google-research/structured-additive-IR:

google-research/robel: ROBEL: Robotics Benchmarks for Learning with low-cost robots

google-research/cross-replication-reliability:

google-research/multilingual-t5:

google-research/social_cascades:

google-research/tf-slim:

google-research/heldout-influence-estimation:

google-research/albert: ALBERT: A Lite BERT for Self-supervised Learning of Language Representations

google-research/adapter-bert:

google-research/raksha:

google-research/xmcgan_image_generation:

google-research/understanding-transfer-learning:

google-research/world_models:

google-research/DP-FTRL: DP-FTRL from "Practical and Private (Deep) Learning without Sampling or Shuffling" for centralized training.

google-research/OOD-failures:

google-research/rlds-creator: A web-based tool to collect human data from simulated environments.

google-research/augmix: AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty

google-research/pathdreamer:

google-research/reassessed-imagenet: Labels and other data for the paper "Are we done with ImageNet?"

google-research/automemcpy:

google-research/si-score:

google-research/mint: Multi-modal Content Creation Model Training Infrastructure including the FACT model (AI Choreographer) implementation.

google-research/autoconj: Recognizing and exploiting conjugacy without a domain-specific language

google-research/libsoftwaresync: :camera: :camera: :camera: :camera: :camera: Wireless software synchronization of multiple distributed smartphone cameras.

google-research/understanding-curricula:

google-research/batch_rl: Offline Reinforcement Learning (aka Batch Reinforcement Learning) on Atari 2600 games

google-research/noisystudent: Code for Noisy Student Training. https://arxiv.org/abs/1911.04252

google-research/exoplanet-ml: Machine learning models and utilities for exoplanet science.

google-research/xtreme: 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.

google-research/motion_imitation: Code accompanying the paper "Learning Agile Robotic Locomotion Skills by Imitating Animals"

google-research/seanet:

google-research/deep_ope:

google-research/jumping-task:

google-research/fitvid:

google-research/scenic: Scenic: A Jax Library for Computer Vision Research and Beyond

google-research/recsim: A Configurable Recommender Systems Simulation Platform

google-research/vaccination-search-insights: A dashboard that visualizes publicly released Google Vaccination Search data.

google-research/trecs_image_generation:

google-research/robodesk:

google-research/tensorflow_constrained_optimization:

google-research/realworldrl_suite: Real-World RL Benchmark Suite

google-research/pangea: Panoramic Graph Environment Annotation toolkit, for collecting audio and text annotations in panoramic graph environments such as Matterport3D and StreetLearn.

google-research/sunds:

google-research/mozolm: MozoLM: A language model (LM) serving library

google-research/lasertagger:

google-research/tiny-differentiable-simulator: Tiny Differentiable Simulator is a header-only C++ and CUDA physics library for reinforcement learning and robotics with zero dependencies.

google-research/noisy-fewshot-learning:

google-research/swift-tfp: Find shape errors before you run your code!

google-research/torchsde: Differentiable SDE solvers with GPU support and efficient sensitivity analysis.

google-research/batch-ppo: Efficient Batched Reinforcement Learning in TensorFlow

google-research/dreamer: Dream to Control: Learning Behaviors by Latent Imagination

google-research/graph-attribution: Codebase for Evaluating Attribution for Graph Neural Networks.

google-research/keyboard_oracle: A dynamic 'keyboard' made using Flutter. The keyboard uses what the user has already typed to predict what is most likely to come next and displays these predictions as buttons.

google-research/bleurt: BLEURT is a metric for Natural Language Generation based on transfer learning.

google-research/ssl_detection: Semi-supervised learning for object detection

google-research/fast-soft-sort: Fast Differentiable Sorting and Ranking

google-research/s4l: Tensorflow implementation of S4L: Self-Supervised Semi-Supervised Learning

google-research/selfstudy-adversarial-robustness:

google-research/perceptual-quality: Perceptual quality metrics for TensorFlow

google-research/unique-randomizer:

google-research/fnc:

google-research/smore:

google-research/neural-structural-optimization: Neural reparameterization improves structural optimization

google-research/nested-transformer: Nested Hierarchical Transformer https://arxiv.org/pdf/2105.12723.pdf

google-research/federated: A collection of Google research projects related to Federated Learning and Federated Analytics.

google-research/rliable: [NeurIPS'21 Outstanding Paper] Library for reliable evaluation on RL and ML benchmarks, even with only a handful of seeds.

google-research/falken: Falken provides developers with a service that allows them to train AI that can play their games

google-research/prompt-tuning: Original Implementation of Prompt Tuning from Lester, et al, 2021

google-research/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.

google-research/text-to-text-transfer-transformer: Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"

google-research/hit-gan: Tensorflow implementation for "Improved Transformer for High-Resolution GANs" (NeurIPS 2021).

google-research/bert: TensorFlow code and pre-trained models for BERT

google-research/morph-net: Fast & Simple Resource-Constrained Learning of Deep Network Structure

google-research/sound-separation:

google-research/tuning_playbook: A playbook for systematically maximizing the performance of deep learning models.

google-research/robotics_transformer:

google-research/nerf-from-image: Shape, Pose, and Appearance from a Single Image via Bootstrapped Radiance Field Inversion

google-research/pix2struct:

google-research/language-table: Suite of human-collected datasets and a multi-task continuous control benchmark for open vocabulary visuolinguomotor learning.

google-research/sofima: Scalable Optical Flow-based Image Montaging and Alignment

google-research/optformer:

google-research/tf-opt:

google-research/meliad:

google-research/dataclass_array: Dataclasses which can be manipulated as numpy arrays (with batching, reshape, slicing,...)

google-research/preprocessor-aware-black-box-attack:

google-research/active-adversarial-tests: Official implementation of the paper "Increasing Confidence in Adversarial Robustness Evaluations"

google-research/FLAN:

google-research/recsim_ng: RecSim NG: Toward Principled Uncertainty Modeling for Recommender Ecosystems

google-research/python-graphs: A static analysis library for computing graph representations of Python programs suitable for use with graph neural networks.

google-research/electra: ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators

google-research/rl-reliability-metrics: The RL Reliability Metrics library provides a set of metrics for measuring the reliability of reinforcement learning (RL) algorithms, as well as statistical tools for comparing algorithms and for computing confidence intervals on these metrics.

google-research/relay-policy-learning:

google-research/self-organising-systems:

google-research/ibc: Official implementation of Implicit Behavioral Cloning, as described in our CoRL 2021 paper, see more at https://implicitbc.github.io/

google-research/computation-thru-dynamics: Understanding computation in artificial and biological recurrent networks through the lens of dynamical systems.

google-research/dp-imagenet:

google-research/math-opt-benchmark:

google-research/frame-interpolation: FILM: Frame Interpolation for Large Motion, In ECCV 2022.

google-research/t5x:

google-research/fool-me-twice: Game code and data for Fool Me Twice: Entailment from Wikipedia Gamification https://arxiv.org/abs/2104.04725

google-research/circuit_training:

google-research/l2p: Learning to Prompt (L2P) for Continual Learning @ CVPR22 and DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning @ ECCV22

google-research/public-data-in-dpfl:

google-research/ml-for-systems-taxonomy:

google-research/turkish-morphology: A two-level morphological analyzer for Turkish.

google-research/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.

google-research/growneuron:

google-research/nasbench: NASBench: A Neural Architecture Search Dataset and Benchmark

google-research/schema-guided-dialogue:

google-research/head2toe:

google-research/longt5:

google-research/seed_rl: SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference. Implements IMPALA and R2D2 algorithms in TF2 with SEED's architecture.

google-research/FirstOrderLp.jl: Experimental first-order solvers for linear and quadratic programming.

google-research/long-range-arena: Long Range Arena for Benchmarking Efficient Transformers

google-research/uda: Unsupervised Data Augmentation (UDA)

google-research/planet: Learning Latent Dynamics for Planning from Pixels

google-research/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.

google-research/bigbird: Transformers for Longer Sequences

google-research/rigl: End-to-end training of sparse deep neural networks with little-to-no performance loss.

google-research/data-driven-advection:

google-research/simclr: SimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learners

google-research/clevr_robot_env: CLEVR-Robot: a reinforcement learning environment combining vision, language and control.

google-research/dads: Code for 'Dynamics-Aware Unsupervised Discovery of Skills' (DADS). Enables skill discovery without supervision, which can be combined with model-based control.

google-research/lottery-ticket-hypothesis: A reimplementation of "The Lottery Ticket Hypothesis" (Frankle and Carbin) on MNIST.

google-research/ott:

google-research/pegasus:

google-research/crest: Repo for CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning

google-research/google-research: Google Research

google-research/parti:

google-research/policy-learning-landscape: Explore the optimization landscape for direct policy learning reinforcement learning.

google-research/sputnik: A library of GPU kernels for sparse matrix operations.

google-research/mnist-c:

google-research/reverse-engineering-neural-networks: A collection of tools for reverse engineering neural networks.

google-research/big_vision: Official codebase used to develop Vision Transformer, MLP-Mixer, LiT and more.

google-research/perceiver-ar:

google-research/maxvit: [ECCV 2022] Official repository for "MaxViT: Multi-Axis Vision Transformer". SOTA foundation models for classification, detection, segmentation, image quality, and generative modeling...

google-research/cascades: Python library which enables complex compositions of language models such as scratchpads, chain of thought, tool use, selection-inference, and more.

google-research/t5x_retrieval:

google-research/3d-moments: Code for CVPR 2022 paper '3D Moments from Near-Duplicate Photos'

google-research/maskgit: Official Jax Implementation of MaskGIT

google-research/maxim: [CVPR 2022 Oral] Official repository for "MAXIM: Multi-Axis MLP for Image Processing". SOTA for denoising, deblurring, deraining, dehazing, and enhancement.

google-research/sparse_dp_histograms:

google-research/connectomics:

google-research/big_transfer: Official repository for the "Big Transfer (BiT): General Visual Representation Learning" paper.

google-research/hyperbo:

google-research/graphworld:

google-research/slot-attention-video:

google-research/mood-board-search:

google-research/jax-influence:

google-research/look-back-when-surprised: Look Back When Surprised: Stabilizing Reverse Experience Replay for Neural Approximation

google-research/opticalflow-autoflow:

google-research/hybrid_rcc: A C++ library for information theory and probability

google-research/fixmatch: A simple method to perform semi-supervised learning with limited data.

google-research/diffstride: TF/Keras code for DiffStride, a pooling layer with learnable strides.

google-research/dialog-inpainting:

google-research/pisac: Tensorflow 2 source code for the PI-SAC agent from "Predictive Information Accelerates Learning in RL" (NeurIPS 2020)

google-research/corenet: CoReNet is a technique for joint multi-object 3D reconstruction from a single RGB image.

google-research/ravens: Train robotic agents to learn pick and place with deep learning for vision-based manipulation in PyBullet. Transporter Nets, CoRL 2020.

google-research/disentanglement_lib: disentanglement_lib is an open-source library for research on learning disentangled representations.

google-research/tensorflow-coder:

google-research/pix2seq: Pix2Seq - A general framework for turning RGB pixels into semantically meaningful sequences

google-research/language: Shared repository for open-sourced projects from the Google AI Language team.

google-research/receptive_field: Compute receptive fields of your favorite convnets

google-research/multinerf: A Code Release for Mip-NeRF 360, Ref-NeRF, and RawNeRF

google-research/jax3d:

google-research/vdm:

google-research/skai: SKAI is a machine learning based tool for performing automatic building damage assessments on aerial imagery of disaster sites.

google-research/plur: PLUR (Programming-Language Understanding and Repair) is a collection of source code datasets suitable for graph-based machine learning. We provide scripts for downloading, processing, and loading the datasets. This is done by offering a unified API and data structures for all datasets.

google-research/crossbeam:

google-research/visu3d: 3d without friction (TF, Jax, Numpy)

google-research/url-nlp:

google-research/compressive-visual-representations: Tensorflow 2 implementations of the C-SimCLR and C-BYOL self-supervised visual representation methods from "Compressive Visual Representations" (NeurIPS 2021)

google-research/chirp:

google-research/dex-lang: Research language for array processing in the Haskell/ML family

google-research/vmoe:

google-research/deep_representation_one_class:

google-research/dice_rl:

google-research/soft-dtw-divergences: An implementation of soft-DTW divergences.