Fully open source, End to End Encrypted alternative to Google Photos and Apple Photos

Documentation that simply works

ML Collections is a library of Python Collections designed for ML use cases.

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

High performance self-hosted photo and video management solution.

AI-Powered Photos App for the Decentralized Web 🌈💎✨

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

Kolmogorov Arnold Networks

STUdio - Story Teller Unleashed

Image processing in Python

a state-of-the-art-level open visual language model | 多模态预训练模型

A modular, open and non-proprietary toolkit for core robotic functionalities by harnessing deep learning

SkyPilot: Run AI and batch jobs on any infra (Kubernetes or 12+ clouds). Get unified execution, cost savings, and high GPU availability via a simple interface.

A fully-modern text-based browser, rendering to TTY and browsers

[ICLR'23] DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models

Course Info for VIP-GEAI

👋 Xplique is a Neural Networks Explainability Toolbox

[COLM 2024] OpenAgents: An Open Platform for Language Agents in the Wild

A simple template jit compiler for a subset of Python

Master programming by recreating your favorite technologies from scratch.

An RTSP bridge to Reolink IP cameras

docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.

DeepImageSearch is a Python library for fast and accurate image search. It offers seamless integration with Python, GPU support, and advanced capabilities for identifying complex image patterns usi…

A public release of TimelineBuilder for building personal digital data timelines.

Transformers are Sample-Efficient World Models. ICLR 2023, notable top 5%.

Python compiler

Official PyTorch implementation of SegFormer

🔊 Text-Prompted Generative Audio Model

Automated dense category annotation engine that serves as the initial semantic labeling for the Segment Anything dataset (SA-1B).

Official implementation of the paper: Behind the Scenes: Density Fields for Single View Reconstruction (CVPR 2023)