Python scripts for performing stereo depth estimation using the HITNET Tensorflow model.

Pytorch implementation of Paper by Google Research - Representation Learning for Information Extraction from Form-like Documents.

Python implementation of the video stabilizing algorithm used in YouTube

This is a working demo of the pegasus summarization model trained on cnn_dailymail

Generate fixed dimensional embeddings for multi-dimensional vectors in python based on Muvera from Google.

Multi-encoder segmentation for contrail detection in satellite imagery | Google Researc

Pytorch Lightning implementation of Vision Transformer with support for loading checkpoints saved in official Flax implementation.

A Pytorch implementation of the MixMatch algorithm developed by google-research.

A TensorFlow implementation of NVIDIA's PilotNet Neural Network

Visual animated walkthroughs of the DeepMind "Titans: Learning to Memorize at Test Time" paper using Manim, aimed at making complex ML concepts accessible.

Derived from Medical Literature Development: Injecting domain expertise into T5 via precision vocabulary-guided masking. 源自医学文献开发：通过精准词库引导遮蔽，为 T5 注入领域专业知识。医学文献開発に基づく実装：高精度な語彙ガイド付きマスキングにより、T5モデルにドメイン専門知識を注入。(機械翻訳)

Application of imitation learning to football (soccer) video game.

This project provides code for fine-tuning T5/mT5 models on data preprocessed by T5-Refiner-DomainFocus, enabling improved performance on domain-specific text. 本项目提供针对经过 T5-Refiner-DomainFocus 预处理后的数据进行微调训练的代码，便于在专业领域文本上优化 T5/mT5 模型性能。本プロジェクトは、T5-Refiner-DomainFocus によって前処理されたデータを用いた T5/mT5 モデルのファインチューニング用コードを提供し、専門分野のテキストにおける性能向上を可能にします。（機械翻訳）

First open-source LoRA fine-tuning of BanglaSenti on XLM-RoBERTa-base for Bengali sentiment analysis, trained with Google Cloud TPUs. Includes code, configs, and reproducible results.

Machine learning models and utilities for exoplanet science.

Official Website of Prince Mireku

Demonstrate how to fine-tune a pre-trained LLM

Repo to build the docker image for Google ChAII

R code for Intersectionality in Conversational AI Safety: How Bayesian Multilevel Models Help Understand Diverse Perceptions of Safety

Google Research