mlsanityData to 7 Oct 2026

DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control

arXiv 2502.05855 ↗First posted 9 Feb 2025cs.RO cs.CVcited by 191

On the map: Multimodal LLMs / vision-language models → Embodied and 3D vision-language models

also in 1 more
Abstract (arXiv)

Enabling robots to perform diverse tasks across varied environments is a central challenge in robot learning. While vision-language-action (VLA) models have shown promise for generalizable robot skills, realizing their full potential requires addressing limitations in action representation and efficient training. Current VLA models often focus on scaling the vision-language model (VLM) component, while the action space representation remains a critical bottleneck. This paper introduces DexVLA, a novel framework designed to enhance the efficiency and generalization capabilities of VLAs for complex, long-horizon tasks across diverse robot embodiments. DexVLA features a novel diffusion-based action expert, scaled to one billion parameters, designed for cross-embodiment learning. A novel embodiment curriculum learning strategy facilitates efficient training: (1) pre-training the diffusion expert that is separable from the VLA on cross-embodiment data, (2) aligning the VLA model to specific embodiments, and (3) post-training for rapid adaptation to new tasks. We conduct comprehensive experiments across multiple embodiments, including single-arm, bimanual, and dexterous hand, demonstrating DexVLA's adaptability to challenging tasks without task-specific adaptation, its ability to learn dexterous skills on novel embodiments with limited data, and its capacity to complete complex, long-horizon tasks using only direct language prompting, such as laundry folding. In all settings, our method demonstrates superior performance compared to state-of-the-art models like Octo, OpenVLA, and Diffusion Policy.

Key facts. Cited by 191 papers in the map (data through 7 Oct 2026). Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 57 of its 72 references that are in the map. First posted on arXiv 9 Feb 2025.

Builds on

57 of 72 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025Improving Vision-Language-Action Model with Online Reinforcement Learning28 Jan
  2. 2024Yell At Your Robot: Improving On-the-Fly from Language Corrections19 Mar
  3. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control28 Jul

Other references · 54

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2023Visual Instruction Tuningcited by 7,792
  3. 2022Scalable Diffusion Models with Transformerscited by 5,931
  4. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  5. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
  6. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,151
  7. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,777
  8. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  9. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  10. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  11. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,530
  12. 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
38 more
  1. 2023Training Diffusion Models with Reinforcement Learningcited by 939
  2. 2023Open X-Embodiment: Robotic Learning Datasets and RT-X Modelscited by 849
  3. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Modelscited by 643
  4. 2024Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusioncited by 634
  5. 2022Compositional Visual Generation with Composable Diffusion Modelscited by 619
  6. 2020SAPIEN: A SimulAted Part-based Interactive ENvironmentcited by 584
  7. 2024Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robotscited by 373
  8. 2024TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulationcited by 331
  9. 20243D-VLA: A 3D Vision-Language-Action Generative World Modelcited by 320
  10. 2024Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representationscited by 279
  11. 20243D Diffuser Actor: Policy Diffusion with 3D Scene Representationscited by 278
  12. 2023Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Modelscited by 264
  13. 2024Diffusion Policy Policy Optimizationcited by 255
  14. 2022Real-World Robot Learning with Masked Visual Pre-trainingcited by 241
  15. 2023TidyBot: Personalized Robot Assistance with Large Language Modelscited by 219
  16. 2024RT-H: Action Hierarchies Using Languagecited by 204
  17. 2021DexMV: Imitation Learning for Dexterous Manipulation from Human Videoscited by 194
  18. 2024HumanPlus: Humanoid Shadowing and Imitation from Humanscited by 164
  19. 2023Look Before You Leap: Unveiling the Power of GPT-4V in Robotic Vision-Language Planningcited by 161
  20. 2024Consistency Policy: Accelerated Visuomotor Policies via Consistency Distillationcited by 159
  21. 2023Scaling Up and Distilling Down: Language-Guided Robot Skill Acquisitioncited by 156
  22. 2024Scaling Proprioceptive-Visual Learning with Heterogeneous Pre-trained Transformerscited by 145
  23. 2024Data Scaling Laws in Imitation Learning for Robotic Manipulationcited by 144
  24. 2024Fine-Tuning of Continuous-Time Diffusion Models as Entropy-Regularized Controlcited by 136
  25. 2024Multimodal Diffusion Transformer: Learning Versatile Behavior from Multimodal Goalscited by 131
  26. 2024ALOHA Unleashed: A Simple Recipe for Robot Dexteritycited by 128
  27. 2017Robotic Pick-and-Place of Novel Objects in Clutter with Multi-Affordance Grasping and Cross-Domain Image Matchingcited by 124
  28. 2024GRAPE: Generalizing Robot Policy via Preference Alignmentcited by 106
  29. 2023RoboCook: Long-Horizon Elasto-Plastic Object Manipulation with Diverse Toolscited by 75
  30. 2024The Ingredients for Robotic Diffusion Transformerscited by 72
  31. 2024Learning Visuotactile Skills with Two Multifingered Handscited by 71
  32. 2024UMI on Legs: Making Manipulation Policies Mobile with Manipulation-Centric Whole-body Controllerscited by 67
  33. 2024Diffusion-VLA: Generalizable and Interpretable Robot Foundation Model via Self-Generated Reasoningcited by 57
  34. 2024Sparse Diffusion Policy: A Sparse, Reusable, and Flexible Policy for Robot Learningcited by 56
  35. 2024Feedback Efficient Online Fine-Tuning of Diffusion Modelscited by 52
  36. 2021Learning to See before Learning to Act: Visual Pre-training for Manipulationcited by 50
  37. 2024PoCo: Policy Composition from and for Heterogeneous Robot Learningcited by 42
  38. 2024Scaling Diffusion Policy in Transformer to 1 Billion Parameters for Robotic Manipulationcited by 38

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 88; 2026: 103.

191 papers.

Sort:

By area:

  1. 2025π0.5: a Vision-Language-Action Model with Open-World Generalizationcited by 1,653
  2. 2025SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Roboticscited by 507
  3. 2025RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulationcited by 477
  4. 2026Fast-WAM: Do World Action Models Need Test-time Future Imagination?cited by 311
  5. 2025MolmoAct: Action Reasoning Models that can Reason in Spacecited by 189
  6. 2025MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulationcited by 183
  7. 2025Ctrl-World: A Controllable Generative World Model for Robot Manipulationcited by 149
  8. 2025Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Bettercited by 142
  9. 2025ChatVLA: Unified Multimodal Understanding and Robot Control with Vision-Language-Action Modelcited by 112
  10. 2025OneTwoVLA: A Unified Vision-Language-Action Model with Adaptive Reasoningcited by 105
  11. 2025What Can RL Bring to VLA Generalization? An Empirical Studycited by 102
  12. 2025PointVLA: Injecting the 3D World into Vision-Language-Action Modelscited by 101
38 more
  1. 2025Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policiescited by 90
  2. 2025EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Modelscited by 89
  3. 2025ForceVLA: Enhancing VLA Models with a Force-aware MoE for Contact-rich Manipulationcited by 87
  4. 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applicationscited by 82
  5. 2025OpenHelix: A Short Survey, Empirical Analysis, and Open-Source Dual-System VLA Model for Robotic Manipulationcited by 79
  6. 2025Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policycited by 73
  7. 2025Vision-Language-Action (VLA) Models: Concepts, Progress, Applications and Challengescited by 72
  8. 2025RynnVLA-002: A Unified Vision-Language-Action and World Modelcited by 70
  9. 2026Being-H0.7: A Latent World-Action Model from Egocentric Videoscited by 68
  10. 2025Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Surveycited by 66
  11. 2025WorldEval: World Model as Real-World Robot Policies Evaluatorcited by 64
  12. 2025RoboArena: Distributed Real-World Evaluation of Generalist Robot Policiescited by 63
  13. 2025Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videoscited by 63
  14. 2025WorldGym: World Model as An Environment for Policy Evaluationcited by 61
  15. 2026Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalizationcited by 61
  16. 2025Hume: Introducing System-2 Thinking in Visual-Language-Action Modelcited by 56
  17. 2026MEM: Multi-Scale Embodied Memory for Vision Language Action Modelscited by 55
  18. 2025Training Strategies for Efficient Embodied Reasoningcited by 53
  19. 2025ChatVLA-2: Vision-Language-Action Model with Open-World Embodied Reasoning from Pretrained Knowledgecited by 49
  20. 2025Long-VLA: Unleashing Long-Horizon Capability of Vision Language Action Model for Robot Manipulationcited by 48
  21. 2025Pure Vision Language Action (VLA) Models: A Comprehensive Surveycited by 46
  22. 2026MolmoAct2: Action Reasoning Models for Real-world Deploymentcited by 45
  23. 2026Xiaomi-Robotics-0: An Open-Sourced Vision-Language-Action Model with Real-Time Executioncited by 42
  24. 2025H-RDT: Human Manipulation Enhanced Bimanual Robotic Manipulationcited by 41
  25. 2026RMBench: Memory-Dependent Robotic Manipulation Benchmark with Insights into Policy Designcited by 40
  26. 2026VLM4VLA: Revisiting Vision-Language-Models in Vision-Language-Action Modelscited by 38
  27. 2025Emergence of Human to Robot Transfer in Vision-Language-Action Modelscited by 36
  28. 2025VLA-OS: Structuring and Dissecting Planning Representations and Paradigms in Vision-Language-Action Modelscited by 34
  29. 2025A Survey on Efficient Vision-Language-Action Modelscited by 34
  30. 2025Action-aware Dynamic Pruning for Efficient Vision-Language-Action Manipulationcited by 32
  31. 2025Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarkscited by 31
  32. 2025dVLA: Diffusion Vision-Language-Action Model with Multimodal Chain-of-Thoughtcited by 30
  33. 2025HiF-VLA: Hindsight, Insight and Foresight through Motion Representation for Vision-Language-Action Modelscited by 30
  34. 2026Native Video-Action Pretraining for Generalizable Robot Controlcited by 30
  35. 2025Fast-in-Slow: A Dual-System Foundation Model Unifying Fast Manipulation within Slow Reasoningcited by 28
  36. 2025RLinf-VLA: A Unified and Efficient Framework for Reinforcement Learning of Vision-Language-Action Modelscited by 26
  37. 2025LoHoVLA: A Unified Vision-Language-Action Model for Long-Horizon Embodied Taskscited by 25
  38. 2025RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulationcited by 24

50 most cited of 191 All 191 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025MoS-VLA: A Vision-Language-Action Model with One-Shot Skill Adaptation
  2. 2025Vision Language Action Models in Robotic Manipulation: A Systematic Review
  3. 2025LLaDA-VLA: Vision Language Diffusion Action Models
  4. 2024Benchmarking Vision, Language, & Action Models on Robotic Learning Tasks
  5. 2025VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model
  6. 2024CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation
  7. 2025X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model
  8. 2025From Intention to Execution: Probing the Generalization Boundaries of Vision-Language-Action Models