mlsanityData to 14 Oct 2026

RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins

arXiv 2504.13059 ↗First posted 17 Apr 2025cs.RO cs.AI cs.CLcited by 121

Not on the map. Why?

Cited by 39 in Vision-language-action models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

In the rapidly advancing field of robotics, dual-arm coordination and complex object manipulation are essential capabilities for developing advanced autonomous systems. However, the scarcity of diverse, high-quality demonstration data and real-world-aligned evaluation benchmarks severely limits such development. To address this, we introduce RoboTwin, a generative digital twin framework that uses 3D generative foundation models and large language models to produce diverse expert datasets and provide a real-world-aligned evaluation platform for dual-arm robotic tasks. Specifically, RoboTwin creates varied digital twins of objects from single 2D images, generating realistic and interactive scenarios. It also introduces a spatial relation-aware code generation framework that combines object annotations with large language models to break down tasks, determine spatial constraints, and generate precise robotic movement code. Our framework offers a comprehensive benchmark with both simulated and real-world data, enabling standardized evaluation and better alignment between simulated training and real-world performance. We validated our approach using the open-source COBOT Magic Robot platform. Policies pre-trained on RoboTwin-generated data and fine-tuned with limited real-world samples demonstrate significant potential for enhancing dual-arm robotic manipulation systems by improving success rates by over 70% for single-arm tasks and over 40% for dual-arm tasks compared to models trained solely on real-world data.

Key facts. Cited by 121 papers in the map (data through 14 Oct 2026). Builds on 65 of its 74 references that are in the map. First posted on arXiv 17 Apr 2025.

Builds on

65 of 74 references.

References · 65

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  4. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,348
  5. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,071
  6. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,061
  7. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,920
  8. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,568
  9. 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,210
  10. 2022Planning with Diffusion for Flexible Behavior Synthesiscited by 1,061
  11. 2023Adversarial Diffusion Distillationcited by 759
  12. 2023VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Modelscited by 750
38 more
  1. 2019RLBench: The Robot Learning Benchmark & Learning Environmentcited by 689
  2. 2020SAPIEN: A SimulAted Part-based Interactive ENvironmentcited by 595
  3. 2021CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Taskscited by 584
  4. 2022BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learningcited by 523
  5. 2022Is Conditional Generative Modeling all you need for Decision-Making?cited by 516
  6. 2023Emergent Correspondence from Image Diffusioncited by 446
  7. 2022VIMA: General Robot Manipulation with Multimodal Promptscited by 407
  8. 2024RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robotscited by 407
  9. 2024Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperationcited by 391
  10. 2020Transporter Networks: Rearranging the Visual World for Robotic Manipulationcited by 344
  11. 2023ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skillscited by 327
  12. 2023MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrationscited by 327
  13. 2024ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulationcited by 315
  14. 2017Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperationcited by 289
  15. 2023EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thoughtcited by 279
  16. 2021Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasetscited by 250
  17. 2021MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scalecited by 229
  18. 2024ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AIcited by 229
  19. 2023Affordances from Human Videos as a Versatile Representation for Roboticscited by 226
  20. 2022Interactive Language: Talking to Robots in Real Timecited by 218
  21. 2018RoboTurk: A Crowdsourcing Platform for Robotic Skill Learning through Imitationcited by 204
  22. 2023LanguageMPC: Large Language Models as Decision Makers for Autonomous Drivingcited by 190
  23. 2023Look Before You Leap: Unveiling the Power of GPT-4V in Robotic Vision-Language Planningcited by 161
  24. 2023AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Plannerscited by 149
  25. 2024Open-TeleVision: Teleoperation with Immersive Active Visual Feedbackcited by 145
  26. 2023Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functionscited by 131
  27. 20243D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representationscited by 116
  28. 2020Learning to Generalize Across Long-Horizon Tasks from Human Demonstrationscited by 115
  29. 2020Human-in-the-Loop Imitation Learning using Remote Teleoperationcited by 112
  30. 2024HumanoidBench: Simulated Humanoid Benchmark for Whole-Body Locomotion and Manipulationcited by 112
  31. 2024CoPa: General Robotic Manipulation through Spatial Constraints of Parts with Foundation Modelscited by 99
  32. 2022Pre-Training for Robots: Offline RL Enables Learning New Tasks from a Handful of Trialscited by 78
  33. 2024Bunny-VisionPro: Real-Time Bimanual Dexterous Teleoperation for Imitation Learningcited by 77
  34. 2018Multiple Interactions Made Easy (MIME): Large Scale Demonstrations Data for Imitationcited by 76
  35. 2024Robo-ABC: Affordance Generalization Beyond Categories via Semantic Correspondence for Robot Manipulationcited by 71
  36. 2023SkillDiffuser: Interpretable Hierarchical Planning via Skill Abstractions in Diffusion-Based Task Executioncited by 70
  37. 2021A Workflow for Offline Model-Free Robotic Reinforcement Learningcited by 69
  38. 2024RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins (early version)cited by 69

50 most cited of 65 All 65 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 37; 2026: 84.

121 papers.

Sort:

By area:

  1. 2025RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulationcited by 518
  2. 2025Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Modelcited by 134
  3. 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applicationscited by 84
  4. 2025WorldEval: World Model as Real-World Robot Policies Evaluatorcited by 68
  5. 2026World Action Models: The Next Frontier in Embodied AIcited by 50
  6. 2026Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Modelscited by 50
  7. 2026Harness VLA: Steering Frozen VLAs into Reliable Manipulation Primitives via Memory-Guided Agentscited by 47
  8. 2026RMBench: Memory-Dependent Robotic Manipulation Benchmark with Insights into Policy Designcited by 45
  9. 2026RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policiescited by 40
  10. 2025GWM: Towards Scalable Gaussian World Models for Robotic Manipulationcited by 39
  11. 2025EmbodiedGen: Towards a Generative 3D World Engine for Embodied Intelligencecited by 36
  12. 2026DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulationcited by 34
38 more
  1. 2025RoboEval: Where Robotic Manipulation Meets Structured and Scalable Evaluationcited by 32
  2. 2025EmbodieDreamer: Advancing Real2Sim2Real Transfer for Policy Training via Embodied World Modelingcited by 29
  3. 2025Do What You Say: Steering Vision-Language-Action Models via Runtime Reasoning-Action Alignment Verificationcited by 26
  4. 2026JEPA-VLA: Video Predictive Embedding is Needed for VLA Modelscited by 24
  5. 20253D FlowMatch Actor: Unified 3D Policy for Single- and Dual-Arm Manipulationcited by 20
  6. 2025Align-Then-stEer: Adapting the Vision-Language Action Models through Unified Latent Guidancecited by 20
  7. 2025GSWorld: Closed-Loop Photo-Realistic Simulation Suite for Robotic Manipulationcited by 19
  8. 2025AutoBio: A Simulation and Benchmark for Robotic Automation in Digital Biology Laboratorycited by 16
  9. 2025TwinVLA: Data-Efficient Bimanual Manipulation with Twin Single-Arm Vision-Language-Action Modelscited by 13
  10. 2025Video2Act: A Dual-System Video Diffusion Policy with Robotic Spatio-Motional Modelingcited by 13
  11. 2025GP3: A 3D Geometry-Aware Policy with Multi-View Images for Robotic Manipulationcited by 12
  12. 2025EMMA: Generalizing Real-World Robot Manipulation via Generative Visual Transfercited by 12
  13. 2026chi0: Resource-Aware Robust Manipulation via Taming Distributional Inconsistenciescited by 12
  14. 2026SimRecon: SimReady Compositional Scene Reconstruction from Real Videoscited by 12
  15. 2026Kinema4D: Kinematic 4D World Modeling for Spatiotemporal Embodied Simulationcited by 12
  16. 2026World Action Models: A Surveycited by 12
  17. 2025AnchorDream: Repurposing Video Diffusion for Embodiment-Aware Robot Data Synthesiscited by 11
  18. 2026AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discoverycited by 10
  19. 2026LIBERO-Safety: A Comprehensive Benchmark for Physical and Semantic Safety in Vision-Language-Action Modelscited by 10
  20. 2025FreqPolicy: Frequency Autoregressive Visuomotor Policy with Continuous Tokenscited by 9
  21. 2025End-to-End Dexterous Arm-Hand VLA Policies via Shared Autonomy: VR Teleoperation Augmented by Autonomous Hand VLA Policy for Efficient Data Collectioncited by 9
  22. 2026PhysForge: Generating Physics-Grounded 3D Assets for Interactive Virtual Worldcited by 9
  23. 2026Towards Long-horizon Embodied Agents with Tool-Aligned Vision-Language-Action Modelscited by 9
  24. 2025Benchmarking Generalizable Bimanual Manipulation: RoboTwin Dual-Arm Collaboration Challenge at CVPR 2025 MEIS Workshopcited by 8
  25. 2025AnyTask: an Automated Task and Data Generation Framework for Advancing Sim-to-Real Policy Learningcited by 8
  26. 2026VLA Knows Its Limits: Adaptive Execution Horizons for Robot Policiescited by 8
  27. 2026World Engine: Towards the Era of Post-Training for Autonomous Drivingcited by 8
  28. 2025Genie Centurion: Accelerating Scalable Real-World Robot Training with Human Rewind-and-Refine Guidancecited by 7
  29. 2025RoboTransfer: Controllable Geometry-Consistent Video Diffusion for Manipulation Policy Transfercited by 7
  30. 2026Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understandingcited by 7
  31. 2026RynnValue: Scaling Robotic Value Foundation Models with Temporal Distancecited by 7
  32. 2025Towards High-Consistency Embodied World Model with Multi-View Trajectory Videoscited by 6
  33. 2026PEAfowl: Perception-Enhanced Multi-View Vision-Language-Action for Bimanual Manipulationcited by 6
  34. 2026World-Action Models for Robot Learning and Control: A Surveycited by 6
  35. 2025ManiVID-3D: Generalizable View-Invariant Reinforcement Learning for Robotic Manipulation via Disentangled 3D Representationscited by 5
  36. 2026Action-Geometry Prediction with 3D Geometric Prior for Bimanual Manipulationcited by 5
  37. 2026ManiTwin: Scaling Data-Generation-Ready Digital Object Dataset to 100Kcited by 5
  38. 2026FineVLA: Fine-Grained Instruction Alignment for Steerable Vision-Language-Action Policiescited by 5

50 most cited of 121 All 121 (JSON)