[CoRL 2025] ManiFlow: A General Robot Manipulation Policy via Consistency Flow Training

An Easy-to-use, Scalable and High-performance RLHF Framework designed for Multimodal Models.

JittorInfer is a high-performance C++ inference framework designed for large language models on Huawei's Ascend AI processor.

JAX implementation of MeanFlow

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

[CVPR 2025] Magma: A Foundation Model for Multimodal AI Agents

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

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

code for paper "Graph Structure of Neural Networks"

Train transformer language models with reinforcement learning.

Generative Models by Stability AI