Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Models and examples built with TensorFlow

A generative world for general-purpose robotics & embodied AI learning.

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

Github Pages template based upon HTML and Markdown for personal, portfolio-based websites.

PyTorch code and models for the DINOv2 self-supervised learning method.

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

Effortless data labeling with AI support from Segment Anything and other awesome models.

Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.

Count the MACs / FLOPs of PyTorch models

[ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attention

Code to create Stylized-ImageNet, a stylized version of standard ImageNet (ICLR 2019 Oral)

MiniCPM4 & MiniCPM4.1: Ultra-Efficient LLMs on End Devices, achieving 3+ generation speedup on reasoning tasks

Paper list of multi-agent reinforcement learning (MARL)

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

Scaling Vision Pre-Training to 4K Resolution

Tutorials and implementations for "Self-normalizing networks"

Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.

ImageBind One Embedding Space to Bind Them All

The simplest, fastest repository for training/finetuning medium-sized GPTs.

[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". A…

DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder

DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space

Efficient vision foundation models for high-resolution generation and perception.

[ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training

DINO-X: The World's Top-Performing Vision Model for Open-World Object Detection and Understanding