GigaBrain-0: A World Model-Powered Vision-Language-Action Model

The best ChatGPT that $100 can buy.

All Algorithms implemented in Python

InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy

RLinf is a flexible and scalable open-source infrastructure designed for post-training foundation models (LLMs, VLMs, VLAs) via reinforcement learning.

A Gym for Agentic LLMs

Interactive Post-Training for Vision-Language-Action Models

Galaxea's first VLA release

A minimal implementation of DeepMind's Genie world model

Official code of RDT 2

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

[IROS 2025 Award Finalist] The Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems

[NeurIPS 2025] AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning

WorldVLA: Towards Autoregressive Action World Model

SpatialVID: A Large-Scale Video Dataset with Spatial Annotations

Friends of OLMo and their links.

Code and implementations for the paper "AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning" by Zhiheng Xi et al.

SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

Code of WinT3R: Window-Based Streaming Rrconstruction With Camera Token Pool

[ICCV 2025 ⭐highlight⭐] Implementation of VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory

AgentScope: Agent-Oriented Programming for Building LLM Applications

Minimalistic 4D-parallelism distributed training framework for education purpose

A repository consisting of paper/architecture replications of classic/SOTA AI/ML papers in pytorch

Machine Learning Engineering Open Book

NanoGPT (124M) in 3 minutes

A MemAgent framework that can be extrapolated to 3.5M, along with a training framework for RL training of any agent workflow.