mlsanityData to 7 Oct 2026

Mean-Flow based One-Step Vision-Language-Action

arXiv 2603.01469 ↗First posted 2 Mar 2026cs.RO cs.AIcited by 7

On the map: Vision-language-action models → Efficient VLA inference and adaptation

also in 1 more
Abstract (arXiv)

Recent advances in FlowMatching-based Vision-Language-Action (VLA) frameworks have demonstrated remarkable advantages in generating high-frequency action chunks, particularly for highly dexterous robotic manipulation tasks. Despite these notable achievements, their practical applications are constrained by prolonged generation latency, which stems from inherent iterative sampling requirements and architectural limitations. To address this critical bottleneck, we propose a Mean-Flow based One-Step VLA approach. Specifically, we resolve the noise-induced issues in the action generation process, thereby eliminating the consistency constraints inherent to conventional Flow-Matching methods. This significantly enhances generation efficiency and enables one-step action generation. Real-world robotic experiments show that the generation speed of the proposed Mean-Flow based One-Step VLA is 8.7 times and 83.9 times faster than that of SmolVLA and Diffusion Policy, respectively. These results elucidate its great potential as a high-efficiency backbone for VLA-based robotic manipulation.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Placed in Efficient VLA inference and adaptation, one of 13 directions in Vision-language-action models. Builds on 27 of its 29 references that are in the map. First posted on arXiv 2 Mar 2026.

Builds on

27 of 29 references.

References · 27

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2022Flow Matching for Generative Modelingcited by 5,426
  4. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  5. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,048
  6. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  7. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  8. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,297
  9. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  10. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,961
  11. 2023Consistency Modelscited by 1,778
  12. 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
15 more
  1. 2022Building Normalizing Flows with Stochastic Interpolantscited by 964
  2. 2025Mean Flows for One-step Generative Modelingcited by 524
  3. 2025SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Roboticscited by 507
  4. 2024One Step Diffusion via Shortcut Modelscited by 373
  5. 2025SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Modelcited by 307
  6. 2024Simplifying, Stabilizing and Scaling Continuous-Time Consistency Modelscited by 276
  7. 2023Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Modelscited by 232
  8. 2025SmolVLM: Redefining small and efficient multimodal modelscited by 226
  9. 2024Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generationcited by 211
  10. 2024Consistency Flow Matching: Defining Straight Flows with Velocity Consistencycited by 101
  11. 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applicationscited by 82
  12. 2025Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Surveycited by 66
  13. 2024Diffusion-VLA: Generalizable and Interpretable Robot Foundation Model via Self-Generated Reasoningcited by 57
  14. 2025Pure Vision Language Action (VLA) Models: A Comprehensive Surveycited by 46
  15. 2025MP1: MeanFlow Tames Policy Learning in 1-step for Robotic Manipulationcited by 32

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 7.

7 papers.

  1. 2026FASTER: Rethinking Real-Time Flow VLAscited by 20
  2. 2026Realtime-VLA FLASH: Speculative Inference Framework for Diffusion-based VLAscited by 8
  3. 2026DriftingVLA: Native One-Step Vision-Language-Action Generation via Per-Dimension Temporal Driftingcited by 2
  4. 2026Decoupling Vision, Language, and Action for Efficient Multi-Task Robot Policiescited by 2
  5. 2026LexiconVLA: Learning Reusable Atomic Action Codebooks for Unseen Taskscited by 0
  6. 2026DriftOPD: Sequence-Level Reverse-KL Distillation for One-Step VLA Policiescited by 0
  7. 2026Kinematic MeanFlow: One-Step Action Generation Policy for Robotic Foundation Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026ReactVLA: Fast and Lightweight Reactive Robot Manipulation via Improved Mean Flow Action Generation
  2. 2026SnapFlow: One-Step Action Generation for Flow-Matching VLAs via Progressive Self-Distillation
  3. 2026DFM-VLA: Iterative Action Refinement for Robot Manipulation via Discrete Flow Matching
  4. 2026Let It Be Simple: One-Step Action Generation for Vision-Language-Action Models
  5. 2026StairVLA: Stage-Aware Hierarchical Action Generation for Vision-Language-Action Models
  6. 2026A1: A Fully Transparent Open-Source, Adaptive and Efficient Truncated Vision-Language-Action Model
  7. 2026Catch Me If You Can: Real-Time Feedback Denoising for Responsive VLAs
  8. 2025PD-VLA: Accelerating Vision-Language-Action Model Integrated with Action Chunking via Parallel Decoding