mlsanityData to 14 Oct 2026

Real-Time Execution of Action Chunking Flow Policies

arXiv 2506.07339 ↗First posted 9 Jun 2025cs.RO cs.AI cs.LGcited by 216

Not on the map. Why?

Cited by 118 in Vision-language-action models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Modern AI systems, especially those interacting with the physical world, increasingly require real-time performance. However, the high latency of state-of-the-art generalist models, including recent vision-language action models (VLAs), poses a significant challenge. While action chunking has enabled temporal consistency in high-frequency control tasks, it does not fully address the latency problem, leading to pauses or out-of-distribution jerky movements at chunk boundaries. This paper presents a novel inference-time algorithm that enables smooth asynchronous execution of action chunking policies. Our method, real-time chunking (RTC), is applicable to any diffusion- or flow-based VLA out of the box with no re-training. It generates the next action chunk while executing the current one, "freezing" actions guaranteed to execute and "inpainting" the rest. To test RTC, we introduce a new benchmark of 12 highly dynamic tasks in the Kinetix simulator, as well as evaluate 6 challenging real-world bimanual manipulation tasks. Results demonstrate that RTC is fast, performant, and uniquely robust to inference delay, significantly improving task throughput and enabling high success rates in precise tasks unicodex2013 such as lighting a match unicodex2013 even in the presence of significant latency. See https://pi.website/research/realtimechunking for videos.

Key facts. Cited by 216 papers in the map (data through 14 Oct 2026). Builds on 54 of its 70 references that are in the map. First posted on arXiv 9 Jun 2025.

Builds on

54 of 70 references.

References · 54

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2020Scaling Laws for Neural Language Modelscited by 6,586
  3. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  4. 2022Flow Matching for Generative Modelingcited by 5,702
  5. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  6. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 3,080
  7. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,887
  8. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  9. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,407
  10. 2023Consistency Modelscited by 1,822
  11. 2025π0.5: a Vision-Language-Action Model with Open-World Generalizationcited by 1,761
  12. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
38 more
  1. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,568
  2. 2024Octo: An Open-Source Generalist Robot Policycited by 1,484
  3. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,446
  4. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,430
  5. 2023AWQ: Activation-aware Weight Quantization for LLM Compression and Accelerationcited by 1,298
  6. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,225
  7. 2022Planning with Diffusion for Flexible Behavior Synthesiscited by 1,061
  8. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Successcited by 883
  9. 2015Automatic differentiation in machine learning: a surveycited by 855
  10. 2024DROID: A Large-Scale In-The-Wild Robot Manipulation Datasetcited by 852
  11. 2024RDT-1B: a Diffusion Foundation Model for Bimanual Manipulationcited by 691
  12. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Modelscited by 665
  13. 2023BridgeData V2: A Dataset for Robot Learning at Scalecited by 657
  14. 2025BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agentscited by 647
  15. 2022Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learningcited by 562
  16. 2022Is Conditional Generative Modeling all you need for Decision-Making?cited by 516
  17. 2022Temporal Difference Learning for Model Predictive Controlcited by 397
  18. 2024Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robotscited by 394
  19. 2024One Step Diffusion via Shortcut Modelscited by 391
  20. 20243D-VLA: A 3D Vision-Language-Action Generative World Modelcited by 328
  21. 2018Sim-to-Real: Learning Agile Locomotion For Quadruped Robotscited by 319
  22. 2024TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policiescited by 304
  23. 2024GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulationcited by 296
  24. 2023Imitating Human Behaviour with Diffusion Modelscited by 263
  25. 2023A Variational Perspective on Solving Inverse Problems with Diffusion Modelscited by 222
  26. 2024NaVILA: Legged Robot Vision-Language-Action Model for Navigationcited by 211
  27. 2018RoboTurk: A Crowdsourcing Platform for Robotic Skill Learning through Imitationcited by 204
  28. 2023RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shotcited by 183
  29. 2024Consistency Policy: Accelerated Visuomotor Policies via Consistency Distillationcited by 166
  30. 2024Behavior Generation with Latent Actionscited by 160
  31. 2024ALOHA Unleashed: A Simple Recipe for Robot Dexteritycited by 134
  32. 2024DexMimicGen: Automated Data Generation for Bimanual Dexterous Manipulation via Imitation Learningcited by 116
  33. 2023Training-free Linear Image Inverses via Flowscited by 72
  34. 2024Riemannian Flow Matching Policy for Robot Motion Learningcited by 63
  35. 2024Streaming Diffusion Policy: Fast Policy Synthesis with Variable Noise Diffusion Modelscited by 56
  36. 2024QueST: Self-Supervised Skill Abstractions for Learning Continuous Controlcited by 53
  37. 2024Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Taskscited by 45
  38. 2022Real-time Neural-MPC: Deep Learning Model Predictive Control for Quadrotors and Agile Robotic Platformscited by 41

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 29; 2026: 187.

216 papers.

Sort:

By area:

  1. 2026Causal World Modeling for Robot Controlcited by 321
  2. 2025Ctrl-World: A Controllable Generative World Model for Robot Manipulationcited by 167
  3. 2026π0.7: a Steerable Generalist Robotic Foundation Model with Emergent Capabilitiescited by 138
  4. 2025A Survey on Vision-Language-Action Models: An Action Tokenization Perspectivecited by 96
  5. 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applicationscited by 84
  6. 2026Unified 4D World Action Modeling from Video Priors with Asynchronous Denoisingcited by 71
  7. 2025Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Surveycited by 69
  8. 2025VL-JEPA: Joint Embedding Predictive Architecture for Vision-languagecited by 68
  9. 2025Training-Time Action Conditioning for Efficient Real-Time Chunkingcited by 64
  10. 2026MEM: Multi-Scale Embodied Memory for Vision Language Action Modelscited by 61
  11. 2025VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inferencecited by 58
  12. 2026Motubrain: An Advanced World Action Model for Robot Controlcited by 57
38 more
  1. 2026Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Modelscited by 50
  2. 2025Pure Vision Language Action (VLA) Models: A Comprehensive Surveycited by 49
  3. 2025Leave No Observation Behind: Real-time Correction for VLA Action Chunkscited by 46
  4. 2026AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routingcited by 46
  5. 2026Xiaomi-Robotics-0: An Open-Sourced Vision-Language-Action Model with Real-Time Executioncited by 45
  6. 2025FailSafe: Reasoning and Recovery from Failures in Vision-Language-Action Modelscited by 35
  7. 2025ContextVLA: Vision-Language-Action Model with Amortized Multi-Frame Contextcited by 35
  8. 2026DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulationcited by 34
  9. 2025Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Surveycited by 26
  10. 2026Light-WAM: Efficient World Action Models with State-Fusion Action Decodingcited by 23
  11. 2026HoloBrain-0 Technical Reportcited by 21
  12. 2026FASTER: Rethinking Real-Time Flow VLAscited by 21
  13. 2025VLA-RAIL: A Real-Time Asynchronous Inference Linker for VLA Models and Robotscited by 19
  14. 2026Learning Native Continuation for Action Chunking Flow Policiescited by 19
  15. 2026How Fast Can I Run My VLA? Demystifying VLA Inference Performance with VLA-Perfcited by 19
  16. 2026Flash-WAM: Modality-Aware Distillation for World Action Modelscited by 19
  17. 2025Task adaptation of Vision-Language-Action model: 1st Place Solution for the 2025 BEHAVIOR Challengecited by 15
  18. 2025Vidarc: Embodied Video Diffusion Model for Closed-loop Controlcited by 15
  19. 2025Can AI Perceive Physical Danger and Intervene?cited by 14
  20. 2025On-Device Diffusion Transformer Policy for Efficient Robot Manipulationcited by 13
  21. 2025Point What You Mean: Visually Grounded Instruction Policycited by 10
  22. 2026ABPolicy: Asynchronous B-Spline Flow Policy for Real-Time and Smooth Robotic Manipulationcited by 10
  23. 2026GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention Specializationcited by 10
  24. 2026FutureRTC: Real-Time Robot Execution with Anticipatory-Conditioned Action Chunkingcited by 10
  25. 2026TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAMcited by 10
  26. 2026DeMaVLA: A Vision-Language-Action Foundation Model for Generalizable Deformable Manipulationcited by 9
  27. 2026Shallow-π: Knowledge Distillation for Flow-based VLAscited by 8
  28. 2026VLA Knows Its Limits: Adaptive Execution Horizons for Robot Policiescited by 8
  29. 2026SpatialVAM:Spatial-Aware Multi-View Video Diffusion as a Data-Efficient Robot Policycited by 8
  30. 2026Realtime-VLA FLASH: Speculative Inference Framework for Diffusion-based VLAscited by 8
  31. 2026PACE: Phase-Aware Chunk Execution for Robot Policies with Action Chunkingcited by 8
  32. 2026DSWAM: A Dual-System World Action Foundation Model for Fine-Grained Robot Manipulationcited by 8
  33. 2025Survey of Vision-Language-Action Models for Embodied Manipulationcited by 7
  34. 2025FILIC: Dual-Loop Force-Guided Imitation Learning with Impedance Torque Control for Contact-Rich Manipulation Taskscited by 7
  35. 2026π, But Make It Fly: Physics-Guided Transfer of VLA Models to Aerial Manipulationcited by 7
  36. 2026Characterizing Vision-Language-Action Models across XPUs: Constraints and Acceleration for On-Robot Deploymentcited by 7
  37. 2026Revisiting Embodied Chain-of-Thought for Generalizable Robot Manipulationcited by 7
  38. 2026SEAM: Smooth Execution of Action-Chunked Motion for Vision-Language-Action Policiescited by 7

50 most cited of 216 All 216 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Adaptive Action Chunking at Inference-time for Vision-Language-Action Models
  2. 2026When to Switch: Reliable Action-Chunk Extension for Vision-Language-Action Models
  3. 2025PD-VLA: Accelerating Vision-Language-Action Model Integrated with Action Chunking via Parallel Decoding
  4. 2026Accelerating VLA Inference with Perturbation Informed Execution
  5. 2026Barrier-Constrained Guidance For Real-time Asynchronous VLA Execution
  6. 2026Dynamic Execution Horizon Prediction for Chunk-based Robot Policies
  7. 2026Open-Loop Planning, Closed-Loop Verification: Speculative Verification for VLA
  8. 2025LiPo: A Lightweight Post-optimization Framework for Smoothing Action Chunks Generated by Learned Policies