mlsanityData to 14 Oct 2026

π0.5: a Vision-Language-Action Model with Open-World Generalization

arXiv 2504.16054 ↗First posted 22 Apr 2025cs.LG cs.ROcited by 1,761

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

Abstract (arXiv)

In order for robots to be useful, they must perform practically relevant tasks in the real world, outside of the lab. While vision-language-action (VLA) models have demonstrated impressive results for end-to-end robot control, it remains an open question how far such models can generalize in the wild. We describe π0.5, a new model based on π0 that uses co-training on heterogeneous tasks to enable broad generalization. π0.5 uses data from multiple robots, high-level semantic prediction, web data, and other sources to enable broadly generalizable real-world robotic manipulation. Our system uses a combination of co-training and hybrid multi-modal examples that combine image observations, language commands, object detections, semantic subtask prediction, and low-level actions. Our experiments show that this kind of knowledge transfer is essential for effective generalization, and we demonstrate for the first time that an end-to-end learning-enabled robotic system can perform long-horizon and dexterous manipulation skills, such as cleaning a kitchen or bedroom, in entirely new homes.

Key facts. Cited by 1,761 papers in the map (data through 14 Oct 2026). Placed in Generalist VLA models and benchmarks, one of 13 directions in Vision-language-action models. Builds on 76 of its 90 references that are in the map. First posted on arXiv 22 Apr 2025.

Builds on

76 of 90 references.

Closest ancestors · 9

Same direction, newest first

  1. 2025OTTER: A Vision-Language-Action Model with Text-Aware Visual Feature Extraction5 Mar
  2. 2025DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control9 Feb
  3. 2025HAMSTER: Hierarchical Action Models For Open-World Robot Manipulation8 Feb
  4. 2024NaVILA: Legged Robot Vision-Language-Action Model for Navigation5 Dec
  5. 2024CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation29 Nov
  6. 2024π0: A Vision-Language-Action Flow Model for General Robot Control31 Oct
  7. 2024TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation19 Sep
  8. 2024LLaRA: Supercharging Robot Learning Data for Vision-Language Policy28 Jun
  9. 2024OpenVLA: An Open-Source Vision-Language-Action Model13 Jun

Other references · 67

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  4. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  5. 2020Language Models are Few-Shot Learnerscited by 32,419
  6. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  7. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  8. 2023Segment Anythingcited by 8,234
  9. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  10. 2022Flow Matching for Generative Modelingcited by 5,702
  11. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  12. 2016Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answeringcited by 2,516
38 more
  1. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,348
  2. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,071
  3. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,061
  4. 2024Octo: An Open-Source Generalist Robot Policycited by 1,484
  5. 2015Microsoft COCO Captions: Data Collection and Evaluation Servercited by 1,462
  6. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,225
  7. 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,210
  8. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,035
  9. 2024Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMscited by 838
  10. 2024PaliGemma: A versatile 3B VLM for transfercited by 696
  11. 2022R3M: A Universal Visual Representation for Robot Manipulationcited by 694
  12. 2024RDT-1B: a Diffusion Foundation Model for Bimanual Manipulationcited by 691
  13. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Modelscited by 665
  14. 2023BridgeData V2: A Dataset for Robot Learning at Scalecited by 657
  15. 2022ProgPrompt: Generating Situated Robot Task Plans using Large Language Modelscited by 611
  16. 2025CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Modelscited by 451
  17. 2025AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systemscited by 405
  18. 2024Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robotscited by 394
  19. 2024Robotic Control via Embodied Chain-of-Thought Reasoningcited by 346
  20. 20243D-VLA: A 3D Vision-Language-Action Generative World Modelcited by 328
  21. 2022Rectified Flow: A Marginal Preserving Approach to Optimal Transportcited by 283
  22. 2019RoboNet: Large-Scale Multi-Robot Learningcited by 270
  23. 2017Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metricscited by 264
  24. 2021Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasetscited by 250
  25. 2022Masked Visual Pre-training for Motor Controlcited by 248
  26. 2023ViNT: A Foundation Model for Visual Navigationcited by 222
  27. 2025Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Modelscited by 221
  28. 2023Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?cited by 218
  29. 2022AnyGrasp: Robust and Efficient Grasp Perception in Spatial and Temporal Domainscited by 208
  30. 2024PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMscited by 190
  31. 2023RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shotcited by 183
  32. 2025HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Modelcited by 181
  33. 2022GNM: A General Navigation Model to Drive Any Robotcited by 171
  34. 2023RoboAgent: Generalization and Efficiency in Robot Manipulation via Semantic Augmentations and Action Chunkingcited by 169
  35. 2023Open-World Object Manipulation using Pre-trained Vision-Language Modelscited by 156
  36. 2024Data Scaling Laws in Imitation Learning for Robotic Manipulationcited by 145
  37. 2025Magma: A Foundation Model for Multimodal AI Agentscited by 139
  38. 2024Yell At Your Robot: Improving On-the-Fly from Language Correctionscited by 124

50 most cited of 67 All 67 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 319; 2026: 1442.

1,761 papers.

Sort:

By area:

  1. 2025V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planningcited by 809
  2. 2026World Action Models are Zero-shot Policiescited by 465
  3. 2025WorldVLA: Towards Autoregressive Action World Modelcited by 367
  4. 2026Fast-WAM: Do World Action Models Need Test-time Future Imagination?cited by 349
  5. 2025X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Modelcited by 303
  6. 2025π*0.6: a VLA That Learns From Experiencecited by 303
  7. 2026Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planningcited by 300
  8. 2025Motus: A Unified Latent Action World Modelcited by 251
  9. 2025Real-Time Execution of Action Chunking Flow Policiescited by 216
  10. 2025DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledgecited by 213
  11. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 180
  12. 2025DreamGen: Unlocking Generalization in Robot Learning through Video World Modelscited by 179
38 more
  1. 2025LIBERO-PRO: Towards Robust and Fair Evaluation of Vision-Language-Action Models Beyond Memorizationcited by 179
  2. 2025Ctrl-World: A Controllable Generative World Model for Robot Manipulationcited by 167
  3. 2026Cosmos 3: Omnimodal World Models for Physical AIcited by 165
  4. 2025SimpleVLA-RL: Scaling VLA Training via Reinforcement Learningcited by 151
  5. 2025Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Bettercited by 146
  6. 2025Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tailcited by 146
  7. 2025VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Modelcited by 145
  8. 2025mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAscited by 142
  9. 2026GigaWorld-Policy: An Efficient Action-Centered World--Action Modelcited by 139
  10. 2026π0.7: a Steerable Generalist Robotic Foundation Model with Emergent Capabilitiescited by 138
  11. 2025Training Agents Inside of Scalable World Modelscited by 136
  12. 2025Interactive Post-Training for Vision-Language-Action Modelscited by 135
  13. 2025EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videoscited by 128
  14. 2025GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Datacited by 123
  15. 2026VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Modelcited by 118
  16. 2025GR-3 Technical Reportcited by 111
  17. 2025What Can RL Bring to VLA Generalization? An Empirical Studycited by 108
  18. 2025OneTwoVLA: A Unified Vision-Language-Action Model with Adaptive Reasoningcited by 107
  19. 2026A Pragmatic VLA Foundation Modelcited by 103
  20. 2026ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learningcited by 103
  21. 2025Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videoscited by 102
  22. 2025A Survey on Vision-Language-Action Models: An Action Tokenization Perspectivecited by 96
  23. 2025Galaxea Open-World Dataset and G0 Dual-System VLA Modelcited by 92
  24. 2025ForceVLA: Enhancing VLA Models with a Force-aware MoE for Contact-rich Manipulationcited by 91
  25. 2025Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policiescited by 90
  26. 2026CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulationcited by 88
  27. 2025DriveMoE: Mixture-of-Experts for Vision-Language-Action Model in End-to-End Autonomous Drivingcited by 86
  28. 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applicationscited by 84
  29. 2025InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policycited by 84
  30. 2025BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Modelscited by 80
  31. 2025SAFE: Multitask Failure Detection for Vision-Language-Action Modelscited by 80
  32. 2026RoboCasa365: A Large-Scale Simulation Framework for Training and Benchmarking Generalist Robotscited by 79
  33. 2025Self-Improving Vision-Language-Action Models with Data Generation via Residual RLcited by 78
  34. 2026WorldArena: A Unified Benchmark for Evaluating Perception and Functional Utility of Embodied World Modelscited by 76
  35. 2026DiT4DiT: Jointly Modeling Video Dynamics and Actions for Generalizable Robot Controlcited by 76
  36. 2026Being-H0.7: A Latent World-Action Model from Egocentric Videoscited by 75
  37. 2025Vision-Language-Action (VLA) Models: Concepts, Progress, Applications and Challengescited by 74
  38. 2025CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsificationcited by 74

50 most cited of 1,761 All 1,761 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
  2. 2025REALM: A Real-to-Sim Validated Benchmark for Generalization in Robotic Manipulation
  3. 2023Programmatically Grounded, Compositionally Generalizable Robotic Manipulation
  4. 2026Vision-Language-Action Models: Experimental Insights from a Real-World UR5 Platform
  5. 2026GeneralVLA: Generalizable Vision-Language-Action Models with Knowledge-Guided Trajectory Planning
  6. 2025Emergence of Human to Robot Transfer in Vision-Language-Action Models
  7. 2025Exploring the Limits of Vision-Language-Action Manipulations in Cross-task Generalization
  8. 2026AWM-VLA: AlignedWorld Modeling for Efficient and Explainable Vision-Language-Action Policies