Efficient few-shot learning with Sentence Transformers

TORAX: Tokamak transport simulation in JAX

Numerical integration in arbitrary dimensions on the GPU using PyTorch / TF / JAX

ROBOTIS Dynamixel SDK (Protocol1.0/2.0)

Fast and memory-efficient exact attention

LongLive: Real-time Interactive Long Video Generation

Zero Teleop, Infinite Data: The Automated Synthetic Data Framework for Robotics. / 零遥操，一键生成：您的自动化机器人数据集引擎。

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

Standard Open Arm 100

NVIDIA Isaac GR00T N1.5 - A Foundation Model for Generalist Robots.

OpenVLA: An open-source vision-language-action model for robotic manipulation.

Action Chunking Transformer implementation for low cost robot

Code for the ICLR 2024 spotlight paper: "Learning to Act without Actions" (introducing Latent Action Policies)

A pipeline parallel training script for diffusion models.

Official PyTorch Implementation of Unified Video Action Model (RSS 2025)

multi-engine batch transformation framework

Dion optimizer algorithm

Perceptual video metrics toolkit

PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838

[ICLR 2025] When Attention Sink Emerges in Language Models: An Empirical View (Spotlight)

A Quirky Assortment of CuTe Kernels

PyTorch Single Controller

[ICCV 2025] SpatialTrackerV2: 3D Point Tracking Made Easy

Machine Learning Engineering Open Book

Machine Learning with Symbolic Tensors

This is the code repository for IntPhys 2, a video benchmark designed to evaluate the intuitive physics understanding of deep learning models.

PyTorch code and models for VJEPA2 self-supervised learning from video.