mlsanityData to 7 Oct 2026

Galaxea Open-World Dataset and G0 Dual-System VLA Model

arXiv 2509.00576 ↗First posted 30 Aug 2025cs.RO cs.CVcited by 90

On the map: Vision-language-action models → Generalist VLA models and benchmarks

Abstract (arXiv)

We present Galaxea Open-World Dataset, a large-scale, diverse collection of robot behaviors recorded in authentic human living and working environments. All demonstrations are gathered using a consistent robotic embodiment, paired with precise subtask-level language annotations to facilitate both training and evaluation. Building on this dataset, we introduce G0, a dual-system framework that couples a Vision-Language Model (VLM) for multimodal planning with a Vision-Language-Action (VLA) model for fine-grained execution. G0 is trained using a three-stage curriculum: cross-embodiment pre-training, single-embodiment pre-training, and task-specific post-training. A comprehensive benchmark spanning tabletop manipulation, few-shot learning, and long-horizon mobile manipulation, demonstrates the effectiveness of our approach. In particular, we find that the single-embodiment pre-training stage, together with the Galaxea Open-World Dataset, plays a critical role in achieving strong performance.

Key facts. Cited by 90 papers in the map (data through 7 Oct 2026). Placed in Generalist VLA models and benchmarks, one of 13 directions in Vision-language-action models. Builds on 27 of its 31 references that are in the map. First posted on arXiv 30 Aug 2025.

Builds on

27 of 31 references.

Closest ancestors · 7

Same direction, newest first

  1. 2025VLA-OS: Structuring and Dissecting Planning Representations and Paradigms in Vision-Language-Action Models21 Jun
  2. 2025π0.5: a Vision-Language-Action Model with Open-World Generalization22 Apr
  3. 2024CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation29 Nov
  4. 2024π0: A Vision-Language-Action Flow Model for General Robot Control31 Oct
  5. 2024TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation19 Sep
  6. 2024OpenVLA: An Open-Source Vision-Language-Action Model13 Jun
  7. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control28 Jul

Other references · 20

  1. 2025Qwen2.5-VL Technical Reportcited by 5,418
  2. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  3. 2023Open X-Embodiment: Robotic Learning Datasets and RT-X Modelscited by 849
  4. 2024DROID: A Large-Scale In-The-Wild Robot Manipulation Datasetcited by 801
  5. 2023CogVLM: Visual Expert for Pretrained Language Modelscited by 704
  6. 2024PaliGemma: A versatile 3B VLM for transfercited by 679
  7. 2024RDT-1B: a Diffusion Foundation Model for Bimanual Manipulationcited by 670
  8. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Modelscited by 643
  9. 2023BridgeData V2: A Dataset for Robot Learning at Scalecited by 634
  10. 2025AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systemscited by 390
  11. 2020Integrated Task and Motion Planningcited by 281
  12. 2021Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasetscited by 248
8 more
  1. 2025Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Modelscited by 216
  2. 2021VisualGPT: Data-efficient Adaptation of Pretrained Language Models for Image Captioningcited by 190
  3. 2025HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Modelcited by 176
  4. 2024VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Taskscited by 171
  5. 2024RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulationcited by 166
  6. 2024LMFusion: Adapting Pretrained Language Models for Multimodal Generationcited by 120
  7. 2024From Multimodal LLMs to Generalist Embodied Agents: Methods and Lessonscited by 42
  8. 2025Is Diversity All You Need for Scalable Robotic Manipulation?cited by 19

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 13; 2026: 77.

90 papers.

Sort:

By area:

  1. 2025VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Modelcited by 140
  2. 2026GigaWorld-Policy: An Efficient Action-Centered World--Action Modelcited by 129
  3. 2026π0.7: a Steerable Generalist Robotic Foundation Model with Emergent Capabilitiescited by 127
  4. 2026A Pragmatic VLA Foundation Modelcited by 97
  5. 2026ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learningcited by 94
  6. 2026Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalizationcited by 61
  7. 2026Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisonscited by 51
  8. 2026Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Modelscited by 47
  9. 2025InternData-A1: Pioneering High-Fidelity Synthetic Data for Pre-training Generalist Policycited by 46
  10. 2025DepthVLA: Enhancing Vision-Language-Action Models with Depth-Aware Spatial Reasoningcited by 44
  11. 2025GigaBrain-0: A World Model-Powered Vision-Language-Action Modelcited by 43
  12. 2026World Model for Robot Learning: A Comprehensive Surveycited by 42
38 more
  1. 2026RISE: Self-Improving Robot Policy with Compositional World Modelcited by 39
  2. 2025Emergence of Human to Robot Transfer in Vision-Language-Action Modelscited by 36
  3. 2026RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policiescited by 35
  4. 2026ACoT-VLA: Action Chain-of-Thought for Vision-Language-Action Modelscited by 30
  5. 2026Rethinking Video Generation Model for the Embodied Worldcited by 30
  6. 2026ABot-M0.5: Unified Mobility-and-Manipulation World Action Modelcited by 28
  7. 2026RLDX-1 Technical Reportcited by 25
  8. 2026From Foundation to Application: Improving VLA Models in Practicecited by 25
  9. 2026Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectoriescited by 24
  10. 2026GigaBrain-0.5M*: a VLA That Learns From World Model-Based Reinforcement Learningcited by 23
  11. 2026ABot-PhysWorld: Interactive World Foundation Model for Robotic Manipulation with Physics Alignmentcited by 23
  12. 2025FASTer: Toward Efficient Autoregressive Vision Language Action Modeling via Neural Action Tokenizationcited by 21
  13. 2026A Systematic Study of Data Modalities and Strategies for Co-training Large Behavior Models for Robot Manipulationcited by 20
  14. 2026Steerable Vision-Language-Action Policies for Embodied Reasoning and Hierarchical Controlcited by 19
  15. 2025Seeing to Act, Prompting to Specify: A Bayesian Factorization of Vision Language Action Policycited by 17
  16. 2026Scaling World Model for Hierarchical Manipulation Policiescited by 15
  17. 2026TwinBrainVLA: Unleashing the Potential of Generalist VLMs for Embodied Tasks via Asymmetric Mixture-of-Transformerscited by 14
  18. 2026Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generationcited by 12
  19. 2026MemoryWAM: Efficient World Action Modeling with Persistent Memorycited by 12
  20. 2026chi0: Resource-Aware Robust Manipulation via Taming Distributional Inconsistenciescited by 11
  21. 2026Wall-OSS-0.5 Technical Reportcited by 11
  22. 2026SimVLA: A Simple VLA Baseline for Robotic Manipulationcited by 10
  23. 2026GigaWorld-1: A Roadmap to Build World Models for Robot Policy Evaluationcited by 10
  24. 2025Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Compositioncited by 8
  25. 2026CORAL: Scalable Multi-Task Robot Learning via LoRA Expertscited by 8
  26. 2026DeMaVLA: A Vision-Language-Action Foundation Model for Generalizable Deformable Manipulationcited by 8
  27. 2026DSWAM: A Dual-System World Action Foundation Model for Fine-Grained Robot Manipulationcited by 8
  28. 2025Pixel Motion Diffusion is What We Need for Robot Controlcited by 7
  29. 2025Mind to Hand: Purposeful Robotic Control via Embodied Reasoningcited by 7
  30. 2026Rethinking Visual-Language-Action Model Scaling: Alignment, Mixture, and Regularizationcited by 7
  31. 2026RC-NF: Robot-Conditioned Normalizing Flow for Real-Time Anomaly Detection in Robotic Manipulationcited by 7
  32. 2026GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention Specializationcited by 7
  33. 2025Asynchronous Fast-Slow Vision-Language-Action Policies for Whole-Body Robotic Manipulationcited by 6
  34. 2026ForeAct: Steering Your VLA with Efficient Visual Foresight Planningcited by 6
  35. 2026X-Tokenizer: A Multimodal Action Tokenizer for Vision-Language-Action Pretrainingcited by 6
  36. 2026RynnValue: Scaling Robotic Value Foundation Models with Temporal Distancecited by 5
  37. 2026Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Modelscited by 5
  38. 2026Towards Exploratory and Focused Manipulation with Bimanual Active Perception: A New Problem, Benchmark and Strategycited by 4

50 most cited of 90 All 90 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Colosseum V2: Benchmarking Generalization for Vision-Language-Action Models
  2. 2024Benchmarking Vision, Language, & Action Models on Robotic Learning Tasks
  3. 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications
  4. 2025Vision Language Action Models in Robotic Manipulation: A Systematic Review
  5. 2025HAMSTER: Hierarchical Action Models For Open-World Robot Manipulation
  6. 2025VLA-0: Building State-of-the-Art VLAs with Zero Modification
  7. 2025REALM: A Real-to-Sim Validated Benchmark for Generalization in Robotic Manipulation
  8. 2026RDT2: Exploring the Scaling Limit of UMI Data Towards Zero-Shot Cross-Embodiment Generalization