Publiczne ślady GitHub Google Research

TensorFlow code and pre-trained models for BERT

Google Research

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

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

Brak opisu dla tego repozytorium.

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

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.

Brak opisu dla tego repozytorium.

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.

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

Brak opisu dla tego repozytorium.

Brak opisu dla tego repozytorium.

Brak opisu dla tego repozytorium.

Brak opisu dla tego repozytorium.

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

Learning Latent Dynamics for Planning from Pixels

[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

Official JAX implementation of MAGVIT: Masked Generative Video Transformer

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.

AndroidWorld is an environment and benchmark for autonomous agents

A Configurable Recommender Systems Simulation Platform

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

Brak opisu dla tego repozytorium.

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

Brak opisu dla tego repozytorium.

Brak opisu dla tego repozytorium.

Brak opisu dla tego repozytorium.

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

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

Brak opisu dla tego repozytorium.

Brak opisu dla tego repozytorium.

Brak opisu dla tego repozytorium.

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

Brak opisu dla tego repozytorium.

Brak opisu dla tego repozytorium.

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

Brak opisu dla tego repozytorium.

Code for the paper "Defeating Prompt Injections by Design"

Learning from synthetic data - code and models

Machine learning models and utilities for exoplanet science.

Brak opisu dla tego repozytorium.

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

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

Modular, scalable library to train ML models

Brak opisu dla tego repozytorium.

Brak opisu dla tego repozytorium.

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

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

Brak opisu dla tego repozytorium.

Deep networks for protein functional inference

Brak opisu dla tego repozytorium.

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

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

Brak opisu dla tego repozytorium.

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

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.

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

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

Brak opisu dla tego repozytorium.

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

Brak opisu dla tego repozytorium.

Brak opisu dla tego repozytorium.

Brak opisu dla tego repozytorium.

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

Brak opisu dla tego repozytorium.

Semi-supervised anomaly detection method

Finite-state script normalization and processing utilities

Finite-state Transducer (FST) Library.

Brak opisu dla tego repozytorium.

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

Brak opisu dla tego repozytorium.

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

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

Brak opisu dla tego repozytorium.

Brak opisu dla tego repozytorium.

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

Shared MuJoCo simulation scenes and assets for ROBEL environments.

Brak opisu dla tego repozytorium.

Brak opisu dla tego repozytorium.

Brak opisu dla tego repozytorium.

Brak opisu dla tego repozytorium.

Brak opisu dla tego repozytorium.

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

Brak opisu dla tego repozytorium.

Brak opisu dla tego repozytorium.