mlsanityData to 7 Oct 2026

DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Grasping

arXiv 2502.20900 ↗First posted 28 Feb 2025cs.RO cs.AIcited by 87

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

Abstract (arXiv)

Dexterous grasping remains a fundamental yet challenging problem in robotics. A general-purpose robot must be capable of grasping diverse objects in arbitrary scenarios. However, existing research typically relies on restrictive assumptions, such as single-object settings or limited environments, showing constrained generalization. We present DexGraspVLA, a hierarchical framework for robust generalization in language-guided general dexterous grasping and beyond. It utilizes a pre-trained Vision-Language model as the high-level planner and learns a diffusion-based low-level Action controller. The key insight to achieve generalization lies in iteratively transforming diverse language and visual inputs into domain-invariant representations via foundation models, where imitation learning can be effectively applied due to the alleviation of domain shift. Notably, our method achieves a 90+% dexterous grasping success rate under thousands of challenging unseen cluttered scenes. Empirical analysis confirms the consistency of internal model behavior across environmental variations, validating our design. DexGraspVLA also, for the first time, simultaneously demonstrates free-form long-horizon prompt execution, robustness to adversarial objects and human disturbance, and failure recovery. Extended application to nonprehensile grasping further proves its generality. Project website: https://dexgraspvla.github.io.

Key facts. Cited by 87 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 92 of its 108 references that are in the map. First posted on arXiv 28 Feb 2025.

Builds on

92 of 108 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Latent Action Pretraining from Videos15 Oct

Other references · 91

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Denoising Diffusion Implicit Modelscited by 9,655
  3. 2023Segment Anythingcited by 8,158
  4. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  5. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  6. 2022Scalable Diffusion Models with Transformerscited by 5,931
  7. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  8. 2024GPT-4o System Cardcited by 4,467
  9. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,048
  10. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  11. 2024SAM 2: Segment Anything in Images and Videoscited by 2,784
  12. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,777
38 more
  1. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  2. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  3. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,297
  4. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,179
  5. 2024Depth Anything V2cited by 1,385
  6. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,346
  7. 2023Open X-Embodiment: Robotic Learning Datasets and RT-X Modelscited by 849
  8. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Successcited by 844
  9. 2024DROID: A Large-Scale In-The-Wild Robot Manipulation Datasetcited by 801
  10. 2023VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Modelscited by 733
  11. 2019Solving Rubik's Cube with a Robot Handcited by 699
  12. 2017Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrationscited by 685
  13. 2024RDT-1B: a Diffusion Foundation Model for Bimanual Manipulationcited by 670
  14. 2021How to train your ViT? Data, Augmentation, and Regularization in Vision Transformerscited by 562
  15. 2024ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulationcited by 305
  16. 2024GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulationcited by 290
  17. 2023Any-point Trajectory Modeling for Policy Learningcited by 207
  18. 2021DexMV: Imitation Learning for Dexterous Manipulation from Human Videoscited by 194
  19. 2023Putting the Object Back into Video Object Segmentationcited by 182
  20. 2021A System for General In-Hand Object Re-Orientationcited by 155
  21. 2023Open-World Object Manipulation using Pre-trained Vision-Language Modelscited by 155
  22. 2024DexCap: Scalable and Portable Mocap Data Collection System for Dexterous Manipulationcited by 149
  23. 2022DeXtreme: Transfer of Agile In-hand Manipulation from Simulation to Realitycited by 136
  24. 2023AnyTeleop: A General Vision-Based Dexterous Robot Arm-Hand Teleoperation Systemcited by 136
  25. 2023RT-Trajectory: Robotic Task Generalization via Hindsight Trajectory Sketchescited by 131
  26. 2022DexGraspNet: A Large-Scale Robotic Dexterous Grasp Dataset for General Objects Based on Simulationcited by 129
  27. 2024Flow as the Cross-Domain Manipulation Interfacecited by 126
  28. 2022Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learningcited by 113
  29. 2019DexPilot: Vision Based Teleoperation of Dexterous Robotic Hand-Arm Systemcited by 105
  30. 2022From Play to Policy: Conditional Behavior Generation from Uncurated Robot Datacited by 103
  31. 2022In-Hand Object Rotation via Rapid Motor Adaptationcited by 102
  32. 2023UniDexGrasp++: Improving Dexterous Grasping Policy Learning via Geometry-aware Curriculum and Iterative Generalist-Specialist Learningcited by 101
  33. 2024CoPa: General Robotic Manipulation through Spatial Constraints of Parts with Foundation Modelscited by 97
  34. 2020State-Only Imitation Learning for Dexterous Manipulationcited by 90
  35. 2021Reset-Free Reinforcement Learning via Multi-Task Learning: Learning Dexterous Manipulation Behaviors without Human Interventioncited by 90
  36. 2023General In-Hand Object Rotation with Vision and Touchcited by 87
  37. 2022DexVIP: Learning Dexterous Grasping with Human Hand Pose Priors from Videocited by 83
  38. 2020Learning Dexterous Grasping with Object-Centric Visual Affordancescited by 80

50 most cited of 91 All 91 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 43; 2026: 44.

87 papers.

Sort:

By area:

  1. 2025A Survey on Vision-Language-Action Models: An Action Tokenization Perspectivecited by 96
  2. 2025Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videoscited by 94
  3. 2025Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policiescited by 90
  4. 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applicationscited by 82
  5. 2025Vision-Language-Action (VLA) Models: Concepts, Progress, Applications and Challengescited by 72
  6. 2025SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learningcited by 69
  7. 2026Being-H0.7: A Latent World-Action Model from Egocentric Videoscited by 68
  8. 2025Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Surveycited by 66
  9. 2025Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videoscited by 63
  10. 2025VideoVLA: Video Generators Can Be Generalizable Robot Manipulatorscited by 61
  11. 2026Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalizationcited by 61
  12. 2025A Survey: Learning Embodied Intelligence from Physical Simulators and World Modelscited by 50
38 more
  1. 2025TrackVLA: Embodied Visual Tracking in the Wildcited by 46
  2. 2025Pure Vision Language Action (VLA) Models: A Comprehensive Surveycited by 46
  3. 2025Vision Language Action Models in Robotic Manipulation: A Systematic Reviewcited by 38
  4. 2025Exploring the Limits of Vision-Language-Action Manipulations in Cross-task Generalizationcited by 31
  5. 2025EmbodieDreamer: Advancing Real2Sim2Real Transfer for Policy Training via Embodied World Modelingcited by 29
  6. 2025VLA-Arena: An Open-Source Framework for Benchmarking Vision-Language-Action Modelscited by 28
  7. 2025JARVIS-VLA: Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mousecited by 27
  8. 2025SPIDER: Scalable Physics-Informed Dexterous Retargetingcited by 25
  9. 2026Adaptive Action Chunking at Inference-time for Vision-Language-Action Modelscited by 24
  10. 2025Align-Then-stEer: Adapting the Vision-Language Action Models through Unified Latent Guidancecited by 18
  11. 2025Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approachcited by 18
  12. 2025Parallels Between VLA Model Post-Training and Human Motor Learning: Progress, Challenges, and Trendscited by 17
  13. 2026VP-VLA: Visual Prompting as an Interface for Vision-Language-Action Modelscited by 17
  14. 2025TrackVLA++: Unleashing Reasoning and Memory Capabilities in VLA Models for Embodied Visual Trackingcited by 16
  15. 2026Flash-WAM: Modality-Aware Distillation for World Action Modelscited by 16
  16. 2025Physical Autoregressive Model for Robotic Manipulation without Action Pretrainingcited by 11
  17. 2025Spatial-Aware VLA Pretraining through Visual-Physical Alignment from Human Videoscited by 10
  18. 2026DeltaVLA: Prior-Guided Vision-Language-Action Models via World Knowledge Variationcited by 9
  19. 2026Dexora: Open-source VLA for High-DoF Bimanual Dexteritycited by 9
  20. 2025cVLA: Towards Efficient Camera-Space VLAscited by 8
  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 8
  22. 2026TC-IDM: Grounding Video Generation for Executable Zero-shot Robot Motioncited by 8
  23. 2025Survey of Vision-Language-Action Models for Embodied Manipulationcited by 7
  24. 2026HiVLA: A Visual-Grounded-Centric Hierarchical Embodied Manipulation Systemcited by 7
  25. 2026μVLA: On Recurrent Memory for Partially Observable Manipulation in VLA Modelscited by 7
  26. 2025ROCKET-2: Steering Visuomotor Policy via Cross-View Goal Alignmentcited by 6
  27. 2025Focusing on What Matters: Object-Agent-centric Tokenization for Vision Language Action modelscited by 6
  28. 2026FlowHOI: Flow-based Semantics-Grounded Generation of Hand-Object Interactions for Dexterous Robot Manipulationcited by 6
  29. 2025PhysiAgent: An Embodied Agent Framework in Physical Worldcited by 5
  30. 2026ReViP: Mitigating False Completion in Vision-Language-Action Models with Vision-Proprioception Rebalancecited by 5
  31. 2026DexHiL: A Human-in-the-Loop Framework for Vision-Language-Action Model Post-Training in Dexterous Manipulationcited by 5
  32. 2026UniSteer: Unified Noise Steering for Efficient Human-Guided VLA Adaptationcited by 5
  33. 2026See What Matters: Differentiable Grid Sample Pruning for Generalizable Vision-Language-Action Modelcited by 5
  34. 2025PosA-VLA: Enhancing Action Generation via Pose-Conditioned Anchor Attentioncited by 4
  35. 2025GR-Dexter Technical Reportcited by 4
  36. 2026Action-Sketcher: From Reasoning to Action via Visual Sketches for Long-Horizon Robotic Manipulationcited by 4
  37. 2026DextER: Language-driven Dexterous Grasp Generation with Embodied Reasoningcited by 4
  38. 2026When Attention Betrays: Erasing Backdoor Attacks in Robotic Policies by Reconstructing Visual Tokenscited by 4

50 most cited of 87 All 87 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025DexVLG: Dexterous Vision-Language-Grasp Model at Scale
  2. 2024DexDiff: Towards Extrinsic Dexterity Manipulation of Ungraspable Objects in Unrestricted Environments
  3. 2026AdaClearGrasp: Learning Adaptive Clearing for Zero-Shot Robust Dexterous Grasping in Densely Cluttered Environments ↗
  4. 2025ObjectVLA: End-to-End Open-World Object Manipulation Without Demonstration
  5. 2025GR-RL: Going Dexterous and Precise for Long-Horizon Robotic Manipulation
  6. 2025DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control
  7. 2025Object-Focus Actor for Data-efficient Robot Generalization Dexterous Manipulation
  8. 2025Dexterous Grasping with Real-World Robotic Reinforcement Learning