Code implementation of the paper "World-in-World: World Models in a Closed-Loop World" (ICLR'26 Oral)

The official repository for paper: BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization

NVIDIA Isaac GR00T N1.6 - A Foundation Model for Generalist Robots.

SAPIEN Manipulation Skill Framework, an open source GPU parallelized robotics simulator and benchmark, led by Hillbot, Inc.

Collections of robotics environments geared towards benchmarking multi-task and meta reinforcement learning

This repository contains the official implementation for the paper "REMAC: Self-Reflective and Self-Evolving Multi-Agent Collaboration for Long-Horizon Robot Manipulation" submitted to ICRA 2026 fo…

RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI

Code for "Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation"

[ICLR 2026] Unified Vision-Language-Action Model

AI agents running research on single-GPU nanochat training automatically

Code for Phys2Real -- https://phys2real.github.io/ (ICRA 2026).

[ICLR 2026] Official code for "Ref-Adv: Exploring MLLM Visual Reasoning in Referring Expression Tasks"

An end-to-end open ecosystem for robot learning

Paper list of Video LLM hallucination. Welcome to Star and Contribute!

Universal Notation for Tensor Operations in Python

Cosmos Policy

Rethinking Video Generation Model for the Embodied World

Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations https://video-prediction-policy.github.io

Tiny AutoEncoder for Hunyuan Video (and other video models)

[NeurIPS 2025] Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance

[ICLR 2026] [NeurIPS 2025] ViPRA: Video Prediction for Robot Actions

WoW (World-Omniscient World Model) is a generative world model trained on 2 million robotic interaction trajectories, designed to imagine, reason, and act in the physical world. Unlike passive vide…

RoboTwin 2.0 Offical Repo

Official code of Motus: A Unified Latent Action World Model

A comprehensive list of papers for the definition of World Models and using World Models for General Video Generation, Embodied AI, and Autonomous Driving, including papers, codes, and related webs…