TensorFlow code and pre-trained models for BERT

Google's BERT model reads text in both directions at once to understand word meaning in context, then fine-tunes on specific language tasks like question answering or sentiment analysis.

Google Research

This is a large collection of Jupyter notebooks and Python code released by Google Research, covering AI and machine learning experiments, each subdirectory is an independent research project you download individually rather than cloning the whole repo.

A playbook for systematically maximizing the performance of deep learning models.

A structured guide from Google researchers on how to systematically tune hyperparameters and improve deep learning model performance through principled experimentation.

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.

Pre-trained AI model from Google for forecasting time-series data without retraining. Feed it historical numbers, get future predictions with confidence ranges.

No description.

Google Research's code and pre-trained models for Vision Transformer (ViT) and MLP-Mixer, image recognition models that treat image patches like words in a sentence, achieving top results on large datasets and available for fine-tuning on custom images.

arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"

SimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learners

Scenic: A Jax Library for Computer Vision Research and Beyond

A Code Release for Mip-NeRF 360, Ref-NeRF, and RawNeRF

Check out the new game server:

Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.

ALBERT: A Lite BERT for Self-supervised Learning of Language Representations

FILM: Frame Interpolation for Large Motion, In ECCV 2022.

No description.

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.

ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators

Unsupervised Data Augmentation (UDA)

Shared repository for open-sourced projects from the Google AI Language team.

No description.

Differentiable SDE solvers with GPU support and efficient sensitivity analysis.

Research language for array processing in the Haskell/ML family

No description.

No description.

No description.

No description.

Official repository for the "Big Transfer (BiT): General Visual Representation Learning" paper.

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

No description.

No description.

Learning Latent Dynamics for Planning from Pixels

A simple method to perform semi-supervised learning with limited data.

No description.

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

Fast & Simple Resource-Constrained Learning of Deep Network Structure

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.

Official JAX implementation of MAGVIT: Masked Generative Video Transformer

AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty

No description.

Efficient Batched Reinforcement Learning in TensorFlow

Pix2Seq codebase: multi-tasks with generative modeling (autoregressive and diffusion)

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

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

A dataset of datasets for learning to learn from few examples

AndroidWorld is an environment and benchmark for autonomous agents

BLEURT is a metric for Natural Language Generation based on transfer learning.

A Configurable Recommender Systems Simulation Platform

No description.

A collection of Google research projects related to Federated Learning and Federated Analytics.

[CoRL '23] Dexterous piano playing with deep reinforcement learning.

Dream to Control: Learning Behaviors by Latent Imagination

No description.

NASBench: A Neural Architecture Search Dataset and Benchmark

No description.

Code release for CVPR'24 submission 'OmniGlue'

Original Implementation of Prompt Tuning from Lester, et al, 2021

No description.

No description.

Transformers for Longer Sequences

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

Fast Differentiable Sorting and Ranking

A benchmark for the next generation of data-driven global weather models.

No description.

No description.

Distributed machine learning infrastructure for large-scale robotics research

Official Jax Implementation of MaskGIT

Multi-modal Content Creation Model Training Infrastructure including the FACT model (AI Choreographer) implementation.

Offline Reinforcement Learning (aka Batch Reinforcement Learning) on Atari 2600 games

No description.

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.

No description.

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

Recipes for reproducing Analysis-Ready & Cloud Optimized (ARCO) ERA5 datasets.

No description.

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

Compute receptive fields of your favorite convnets

No description.

No description.

No description.

PDFM Embeddings: location-based vectors for geo-spatial analysis.

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

No description.

No description.

Real-World RL Benchmark Suite

Suite of human-collected datasets and a multi-task continuous control benchmark for open vocabulary visuolinguomotor learning.

Splat-SLAM: Globally Optimized RGB-only SLAM with 3D Gaussians

No description.

Code for the paper "Defeating Prompt Injections by Design"

End-to-end training of sparse deep neural networks with little-to-no performance loss.

No description.

Learning from synthetic data - code and models

Machine learning models and utilities for exoplanet science.

No description.

This is the official code release for SPARF: Neural Radiance Fields from Sparse and Noisy Poses [CVPR 2023-Highlight]

RETVec is an efficient, multilingual, and adversarially-robust text vectorizer.

No description.

Modular, scalable library to train ML models

No description.

Falken provides developers with a service that allows them to train AI that can play their games

No description.

Code associated with the paper An AI system to help scientists write expert-level empirical software

No description.

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

A modular framework for evaluating weather forecasts

No description.

Tensorflow/Keras code and trained models for Episodic Curiosity Through Reachability

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

No description.

SNAP: Self-supervised Neural Maps for Visual Positioning and Semantic Understanding (NeurIPS 2023)

Deep networks for protein functional inference

No description.

No description.

No description.

No description.

:camera: :camera: :camera: :camera: :camera: Wireless software synchronization of multiple distributed smartphone cameras.

A collection of tools for reverse engineering neural networks.

3d without friction (Torch, TF, Jax, Numpy)

SKAI is a machine learning based tool for performing automatic building damage assessments on aerial imagery of disaster sites.

No description.

No description.

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.

Official PyTorch Implementation for Readout Guidance, CVPR 2024

[ECCV'24] Official Implementation of SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance

No description.

No description.

CLEVR-Robot: a reinforcement learning environment combining vision, language and control.

No description.

An implementation of soft-DTW divergences.

No description.

Tools for evaluating the performance of MT metrics on data from recent WMT metrics shared tasks.

No description.

No description.

Neural reparameterization improves structural optimization

No description.

RecSim NG: Toward Principled Uncertainty Modeling for Recommender Ecosystems

E3x is a JAX library for constructing efficient E(3)-equivariant deep learning architectures built on top of Flax.

CoReNet is a technique for joint multi-object 3D reconstruction from a single RGB image.

Tooling for agile modeling on large machine perception embedding databases.

No description.

Repo for CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning

Project Guideline is a research project that leverages on-device ML to enable people who are blind and low-vision to walk or run for exercise independently.

[NeurIPS 2022] Open source code for reusing prior computational work in RL.

No description.

Scalable Optical Flow-based Image Montaging and Alignment

Code for paper Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding

Code and data accompanying the paper "TRUE: Re-evaluating Factual Consistency Evaluation".

Codebase for Evaluating Attribution for Graph Neural Networks.

The Zebrafish Activity Prediction Benchmark measures progress on the problem of predicting cellular-resolution neural activity throughout an entire vertebrate brain.

No description.

No description.

PaperOrchestra is a multi-agent framework for automated AI research paper writing.

No description.

No description.

No description.

No description.

No description.

No description.

Dataclasses manipulated as numpy arrays (with batching, reshape, slicing,...)

Semi-supervised anomaly detection method

MozoLM: A language model (LM) serving library

No description.

No description.

Finite-state script normalization and processing utilities

No description.

No description.

Finite-state Transducer (FST) Library.

No description.

No description.

No description.

Game code and data for Fool Me Twice: Entailment from Wikipedia Gamification https://arxiv.org/abs/2104.04725

TNCO is a heuristic tool that optimizes tensor network contraction paths.

No description.

This is the official code release for “M2SVid: End-to-End Inpainting and Refinement for Monocular-to-Stereo Video Conversion”. 3DV 2026

CoDA is a multi-agent framework that turns natural language queries into publication-quality visualizations.

No description.

No description.

Official implementation of the paper "Increasing Confidence in Adversarial Robustness Evaluations"

Code accompanying the paper "R-U-SURE? Uncertainty-Aware Code Suggestions By Maximizing Utility Across Random User Intents"

SLIP is a sandbox environment for engineering protein sequences with synthetic fitness functions.

No description.

No description.

No description.

No description.

Heavyweight Python dynamic analysis framework

No description.

Look Back When Surprised: Stabilizing Reverse Experience Replay for Neural Approximation

Shared MuJoCo simulation scenes and assets for ROBEL environments.

No description.

No description.

No description.

No description.

The Google Cloud AI Research team tackles AI research challenges motivated by Google Cloud’s mission of bringing AI to tech, healthcare, finance, retail and many other industries. As part of these efforts, we develop new models, algorithms and tools. This repository is a collection of OSS Colabs that we want to share with the broader community.

No description.

No description.

No description.

T2J-Bench is a benchmark for semantic-preserving codebase conversion.

No description.

No description.

No description.

No description.