Official code base for LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

We release Evo-RL, the opensource real-world offline RL on So-101 and AgileX PiPER for easier reproduction.

A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation

Single-stage End-to-End Training for Tokenization and Generation

Distributed, scalable benchmarking of generalist robot policies.

Building Open-Ended Embodied Agents with Internet-Scale Knowledge

One framework to evaluate any VLA model on any robot simulation benchmark.

Train the smallest LM you can that fits in 16MB. Best model wins!

🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade archite…

ICLR 2026: Towards Bridging the Gap between Large-Scale Pretraining and Efficient Finetuning for Humanoid Controls

SCOPE-RL: A python library for offline reinforcement learning, off-policy evaluation, and selection

Official implementation of Kimodo, a kinematic motion diffusion model for high-quality human(oid) motion generation.

Official codebase for the paper "How to build a consistency model: Learning flow maps via self-distillation" (NeurIPS 2025).

Pytorch Implementation (unofficial) of the paper "Mean Flows for One-step Generative Modeling" by Geng et al.

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

A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs dir…

Reimplementation of GR-1, a generalized policy for robotics manipulation.

Welcome to Psi-Zero, a Humanoid VLA towards Universal Humanoid Intelligence.

PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation

PhysClaw*: Physical Continual Learning Agent Workflow

🇨🇳 SWCC — Democratic Centralism Multi-Agent Orchestration for Claude Code (民主集中制多智能体编排)

Reimplementation of LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory

The repo contains the code and dataset for the World Models Track of GigaBrain Challenge 2026 CVPR Workshop.

Code for the paper https://arxiv.org/abs/2402.04997