mlsanityData to 7 Oct 2026

GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Data

arXiv 2505.03233 ↗First posted 6 May 2025cs.ROcited by 120

On the map: Vision-language-action models → Human-video and latent-action pretraining

Abstract (arXiv)

Embodied foundation models are gaining increasing attention for their zero-shot generalization, scalability, and adaptability to new tasks through few-shot post-training. However, existing models rely heavily on real-world data, which is costly and labor-intensive to collect. Synthetic data offers a cost-effective alternative, yet its potential remains largely underexplored. To bridge this gap, we explore the feasibility of training Vision-Language-Action models entirely with large-scale synthetic action data. We curate SynGrasp-1B, a billion-frame robotic grasping dataset generated in simulation with photorealistic rendering and extensive domain randomization. Building on this, we present GraspVLA, a VLA model pretrained on large-scale synthetic action data as a foundational model for grasping tasks. GraspVLA integrates autoregressive perception tasks and flow-matching-based action generation into a unified Chain-of-Thought process, enabling joint training on synthetic action data and Internet semantics data. This design helps mitigate sim-to-real gaps and facilitates the transfer of learned actions to a broader range of Internet-covered objects, achieving open-vocabulary generalization in grasping. Extensive evaluations across real-world and simulation benchmarks demonstrate GraspVLA's advanced zero-shot generalizability and few-shot adaptability to specific human preferences. We will release SynGrasp-1B dataset and pre-trained weights to benefit the community.

Key facts. Cited by 120 papers in the map (data through 7 Oct 2026). Placed in Human-video and latent-action pretraining, one of 13 directions in Vision-language-action models. Builds on 69 of its 85 references that are in the map. First posted on arXiv 6 May 2025.

Builds on

69 of 85 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Latent Action Pretraining from Videos15 Oct

Other references · 68

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  4. 2022Flow Matching for Generative Modelingcited by 5,426
  5. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
  6. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,048
  7. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  8. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,777
  9. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  10. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,297
  11. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,037
  12. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
38 more
  1. 2025π0.5: a Vision-Language-Action Model with Open-World Generalizationcited by 1,653
  2. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
  3. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,490
  4. 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
  5. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,338
  6. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,167
  7. 2023Kosmos-2: Grounding Multimodal Large Language Models to the Worldcited by 1,075
  8. 2023Open X-Embodiment: Robotic Learning Datasets and RT-X Modelscited by 849
  9. 2024DROID: A Large-Scale In-The-Wild Robot Manipulation Datasetcited by 801
  10. 2018QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulationcited by 730
  11. 2024PaliGemma: A versatile 3B VLM for transfercited by 679
  12. 2024RDT-1B: a Diffusion Foundation Model for Bimanual Manipulationcited by 670
  13. 2018On Evaluation of Embodied Navigation Agentscited by 526
  14. 2025CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Modelscited by 440
  15. 2024CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulationcited by 411
  16. 2024InternLM2 Technical Reportcited by 391
  17. 2025AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systemscited by 390
  18. 2024Robotic Control via Embodied Chain-of-Thought Reasoningcited by 340
  19. 2024Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Modelscited by 336
  20. 20243D-VLA: A 3D Vision-Language-Action Generative World Modelcited by 320
  21. 2023MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrationscited by 308
  22. 2024GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulationcited by 290
  23. 2017Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metricscited by 259
  24. 2023PaLI-X: On Scaling up a Multilingual Vision and Language Modelcited by 254
  25. 2023Orbit: A Unified Simulation Framework for Interactive Robot Learning Environmentscited by 239
  26. 20196-DOF GraspNet: Variational Grasp Generation for Object Manipulationcited by 237
  27. 2024NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigationcited by 222
  28. 2018Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluidscited by 219
  29. 2022AnyGrasp: Robust and Efficient Grasp Perception in Spatial and Temporal Domainscited by 205
  30. 2023Scaling Robot Learning with Semantically Imagined Experiencecited by 175
  31. 2024Predictive Inverse Dynamics Models are Scalable Learners for Robotic Manipulationcited by 159
  32. 2023ManipLLM: Embodied Multimodal Large Language Model for Object-Centric Robotic Manipulationcited by 157
  33. 2023Open-World Object Manipulation using Pre-trained Vision-Language Modelscited by 155
  34. 2024Scaling Proprioceptive-Visual Learning with Heterogeneous Pre-trained Transformerscited by 145
  35. 2024Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulationcited by 142
  36. 2017Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Graspingcited by 138
  37. 2024RVT-2: Learning Precise Manipulation from Few Demonstrationscited by 135
  38. 2020ACRONYM: A Large-Scale Grasp Dataset Based on Simulationcited by 115

50 most cited of 68 All 68 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 51; 2026: 69.

120 papers.

Sort:

By area:

  1. 2025RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulationcited by 477
  2. 2025DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledgecited by 203
  3. 2025LIBERO-PRO: Towards Robust and Fair Evaluation of Vision-Language-Action Models Beyond Memorizationcited by 166
  4. 2025VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Modelcited by 140
  5. 2025Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Modelcited by 125
  6. 2026VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Modelcited by 104
  7. 2025Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videoscited by 94
  8. 2025F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actionscited by 85
  9. 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applicationscited by 82
  10. 2025ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceivercited by 80
  11. 2025Vision-Language-Action (VLA) Models: Concepts, Progress, Applications and Challengescited by 72
  12. 2025InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to Manipulationcited by 71
38 more
  1. 2025Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Surveycited by 66
  2. 2025A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learningcited by 66
  3. 2025WorldEval: World Model as Real-World Robot Policies Evaluatorcited by 64
  4. 2025Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videoscited by 63
  5. 2025ChatVLA-2: Vision-Language-Action Model with Open-World Embodied Reasoning from Pretrained Knowledgecited by 49
  6. 2026InternVLA-A1: Unifying Understanding, Generation and Action for Robotic Manipulationcited by 48
  7. 2025Pure Vision Language Action (VLA) Models: A Comprehensive Surveycited by 46
  8. 2025InternData-A1: Pioneering High-Fidelity Synthetic Data for Pre-training Generalist Policycited by 46
  9. 2026World Action Models: The Next Frontier in Embodied AIcited by 46
  10. 2025A Survey on Efficient Vision-Language-Action Modelscited by 34
  11. 2025dVLA: Diffusion Vision-Language-Action Model with Multimodal Chain-of-Thoughtcited by 30
  12. 2026ACoT-VLA: Action Chain-of-Thought for Vision-Language-Action Modelscited by 30
  13. 2026When Vision Overrides Language: Evaluating and Mitigating Counterfactual Failures in VLAscited by 27
  14. 2025Mixture of Horizons in Action Chunkingcited by 20
  15. 2026PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulationcited by 20
  16. 2026Latent Reasoning VLA: Latent Thinking and Prediction for Vision-Language-Action Modelscited by 19
  17. 2026Global Prior Meets Local Consistency: Dual-Memory Augmented Vision-Language-Action Model for Efficient Robotic Manipulationcited by 19
  18. 2026Utonia: Toward One Encoder for All Point Cloudscited by 18
  19. 2025Parallels Between VLA Model Post-Training and Human Motor Learning: Progress, Challenges, and Trendscited by 17
  20. 2025ActiveUMI: Robotic Manipulation with Active Perception from Robot-Free Human Demonstrationscited by 17
  21. 2025Seeing to Act, Prompting to Specify: A Bayesian Factorization of Vision Language Action Policycited by 17
  22. 2025Chain-of-Action: Trajectory Autoregressive Modeling for Robotic Manipulationcited by 16
  23. 2025TrackVLA++: Unleashing Reasoning and Memory Capabilities in VLA Models for Embodied Visual Trackingcited by 16
  24. 2025StereoVLA: Enhancing Vision-Language-Action Models with Stereo Visioncited by 16
  25. 2025A Step Toward World Models: A Survey on Robotic Manipulationcited by 15
  26. 2026NoRD: A Data-Efficient Vision-Language-Action Model that Drives without Reasoningcited by 15
  27. 2025Opening the Sim-to-Real Door for Humanoid Pixel-to-Action Policy Transfercited by 13
  28. 2026Any3D-VLA: Enhancing VLA Robustness via Diverse Point Cloudscited by 13
  29. 2025EMMA: Generalizing Real-World Robot Manipulation via Generative Visual Transfercited by 12
  30. 2025MM-ACT: Learn from Multimodal Parallel Generation to Actcited by 12
  31. 2026RoboInter: A Holistic Intermediate Representation Suite Towards Robotic Manipulationcited by 12
  32. 2025Web2Grasp: Learning Functional Grasps from Web Images of Hand-Object Interactionscited by 10
  33. 2025Spatial-Aware VLA Pretraining through Visual-Physical Alignment from Human Videoscited by 10
  34. 2026SimVLA: A Simple VLA Baseline for Robotic Manipulationcited by 10
  35. 2025MoTVLA: A Vision-Language-Action Model with Unified Fast-Slow Reasoningcited by 9
  36. 2026Goal2Skill: Long-Horizon Manipulation with Adaptive Planning and Reflectioncited by 9
  37. 2026Dexora: Open-source VLA for High-DoF Bimanual Dexteritycited by 9
  38. 2025DM1: MeanFlow with Dispersive Regularization for 1-Step Robotic Manipulationcited by 8

50 most cited of 120 All 120 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026CometVLA: Co-Training on an Embodied Data Pyramid towards Physical Understanding
  2. 2025Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Survey
  3. 2025CronusVLA: Towards Efficient and Robust Manipulation via Multi-Frame Vision-Language-Action Modeling
  4. 2026JoyAI-RA 0.1: A Foundation Model for Robotic Autonomy
  5. 2026From Knowing to Doing Precisely: A General Self-Correction and Termination Framework for VLA models
  6. 2026Cross-Hand Latent Representation for Vision-Language-Action Models
  7. 2026PokeVLA: Empowering Pocket-Sized Vision-Language-Action Model with Comprehensive World Knowledge Guidance
  8. 2026VLA-REPLICA: A Low-Cost, Reproducible Benchmark for Real-World Evaluation of Vision-Language-Action Models