X2Real: an eXtensive simulation benchmark for real-world generalist policies

arXiv:2609.27449 · cs.RO · Submitted 2026-09-23 · Read on arXiv

cs.RO

Submitted: 2026-09-23

Updated: 2026-09-23

Code: https://github.com/X-Square-Robot/x2real

Project page: https://x2robot.com/en/pages/x2real

Terminology

• Benchmark — 82× in this paper · explained in 2 episodes
• Generalization — 20× in this paper · explained in 13 episodes
• World Model — 9× in this paper · explained in 7 episodes
• Adaptation — 8× in this paper · explained in 1 episode
• Alignment — 8× in this paper · explained in 1 episode
• Core — 8× in this paper · explained in 2 episodes
• Fidelity — 7× in this paper · explained in 2 episodes
• Benchmarking — 6× in this paper · explained in 3 episodes
• Grounding — 6× in this paper · explained in 3 episodes
• Calibration — 5× in this paper · explained in 7 episodes
• Embodied AI — 5× in this paper · explained in 2 episodes
• Robustness — 5× in this paper · explained in 5 episodes
• Directed Acyclic Graph — 4× in this paper
• Reinforcement Learning — 4× in this paper · explained in 4 episodes
• Abstraction — 3× in this paper · explained in 1 episode
• Data Augmentation — 3× in this paper · explained in 7 episodes
• Domain-Specific Language — 3× in this paper
• System Identification — 3× in this paper · explained in 3 episodes
• Verification — 3× in this paper · explained in 2 episodes
• Action Flow — 2× in this paper · explained in 1 episode
• Diffusion Model — 2× in this paper · explained in 8 episodes
• Diffusion Models — 2× in this paper · explained in 6 episodes
• Digital Twin — 2× in this paper · explained in 5 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• Provenance — 2× in this paper · explained in 4 episodes
• 6D Object Pose Estimation — 1× in this paper · explained in 1 episode
• Ablation — 1× in this paper · explained in 1 episode
• Action Chunking — 1× in this paper · explained in 1 episode
• Action-Conditioned World Model — 1× in this paper · explained in 1 episode
• Affordance — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Domain-Specific Language (DSL) — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Gaussian Splatting — 1× in this paper · explained in 4 episodes
• IEEE International Conference on Image Processing — 1× in this paper
• Iterative Refinement — 1× in this paper · explained in 3 episodes
• Physical Constraints — 1× in this paper · explained in 7 episodes
• Sim-to-Real Gap — 1× in this paper · explained in 6 episodes
• Sim-to-Real Transfer — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Visual Grounding — 1× in this paper · explained in 2 episodes
• alpha — 1× in this paper · explained in 1 episode

Sources

• World Action Models are Zero-shot Policies
• Wall-OSS-0.5 Technical Report
• WALL-WM: Carving World Action Modeling at the Event Joints
• Cosmos 3: Omnimodal World Models for Physical AI
• ManipArena: Comprehensive Real-world Evaluation of Reasoning-Oriented Generalist Robot Manipulation
• RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation
• RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies
• StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing
• vla-eval: A Unified Evaluation Harness for Vision-Language-Action Models
• LeRobot: An Open-Source Library for End-to-End Robot Learning
• XPolicyLab: A Unified Standard and Open Ecosystem for Robot Policy Evaluation and Deployment
• LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning
• RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots
• MolmoSpaces: A Large-Scale Open Ecosystem for Robot Navigation and Manipulation
• Objaverse: A Universe of Annotated 3D Objects
• CanoVerse: 3D Object Scalable Canonicalization and Dataset for Generation and Pose
• ManiTwin: Scaling Data-Generation-Ready Digital Object Dataset to 100K
• Approximate Convex Decomposition for 3D Meshes with Collision-Aware Concavity and Tree Search
• Pipette: An Embodied Simulation Platform, Benchmark, and Data-Efficient Augmentation Framework for Wet-Lab Robotics
• Tune to Learn: How Controller Gains Shape Robot Policy Learning

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
• Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving