#
Starred repositories
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
Recipes to train reward model for RLHF.
A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.
[Lumina Embodied AI Community] 具身智能技术指南 Embodied-AI-Guide
FlashMLA: Efficient MLA decoding kernels
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
Integrate the DeepSeek API into popular softwares
The Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems
A generative world for general-purpose robotics & embodied AI learning.
Apache Arrow is the universal columnar format and multi-language toolbox for fast data interchange and in-memory analytics
Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/
Official s3cmd repo -- Command line tool for managing S3 compatible storage services (including Amazon S3 and CloudFront).
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation
CoTracker is a model for tracking any point (pixel) on a video.
An example RLDS dataset builder for X-embodiment dataset conversion.
[ICML 2024] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model
A high-performance runtime framework for modern robotics.
[NeurIPS 2024] CLOVER: Closed-Loop Visuomotor Control with Generative Expectation for Robotic Manipulation
[ECCV 2024] 💐Official implementation of the paper "Diffusion Reward: Learning Rewards via Conditional Video Diffusion"
"rsync for cloud storage" - Google Drive, S3, Dropbox, Backblaze B2, One Drive, Swift, Hubic, Wasabi, Google Cloud Storage, Azure Blob, Azure Files, Yandex Files
world modeling challenge for humanoid robots
[NeurIPS 2024] A Generalizable World Model for Autonomous Driving
[RSS 2024] Learning Manipulation by Predicting Interaction