Real-Time Execution of Action Chunking Flow Policies

• URL: http://arxiv.org/abs/2506.07339v1
• Date: Mon, 09 Jun 2025 01:01:59 GMT
• Title: Real-Time Execution of Action Chunking Flow Policies
• Abstract summary: This paper presents a novel inference-time algorithm that enables asynchronous execution of action interacting systems.<n>It is applicable to any diffusion- or VLA-based systems executing out of the box with no re-training.<n>Results show that RTC is fast, performant, and uniquely robust to inference manipulation.
• Score: 49.1574468325115
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 $\unicode{x2013}$ such as lighting a match $\unicode{x2013}$ even in the presence of significant latency. See https://pi.website/research/real_time_chunking for videos.

Related papers

• FlashVLA: Streaming Action Decoding for Fast and Asynchronous VLA Inference [13.128933240091419]
  FlashVLA is a streaming action decoding framework for Vision-Language-Action (VLA) models.<n>It substantially improves inference speed while maintaining strong task performance.<n>It can achieve $geq$30,Hz control frequency on a single GPU with smooth asynchronous inference in real-world deployment.
  arXiv  Detail & Related papers  (2026-08-27T17:19:29Z)
• Training-Free Acceleration for Vision-Language-Action Models with Action Caching and Refinement [1.0279917564173053]
  Vision-Language-Action (VLA) models have emerged as a promising approach for generalizable robotic manipulations.<n>We propose ActionCache, a plug-and-play external cache that opportunistically reuses past intermediate actions to warm-start generations.<n> Experimental results in simulation and real-world environments demonstrate that ActionCache maintains high task success rates in a low-latency regime.
  arXiv  Detail & Related papers  (2026-07-07T15:10:15Z)
• DiscreteRTC: Discrete Diffusion Policies are Natural Asynchronous Executors [57.944744187489185]
  We propose DiscreteRTC, which replaces external corrections with native unmasking.<n>DiscreteRTC is simpler to implement with 0 lines of code for async inpainting, faster at inference with only 0.7x computation compared with generating actions from scratch, and better at execution with 50% higher success rate in real-world dynamic pick task compared with flow-based RTC.
  arXiv  Detail & Related papers  (2026-04-27T23:04:03Z)
• DexWorldModel: Causal Latent World Modeling towards Automated Learning of Embodied Tasks [54.32016216994156]
  We introduce the Causal Latent World Model (CLWM), which employs DINOv3 features as generative targets to disentangle interaction semantics from visual noise.<n>To overcome memory scaling, CLWM features a Dual-State Test-Time Training (TTT) Memory that guarantees a strict $mathcalO(1)$ footprint for long-horizon tasks.<n>We present EmbodiChain, an online framework that establishes the Efficiency Law by injecting an infinite flow of physics-grounded trajectories during training.
  arXiv  Detail & Related papers  (2026-04-13T03:19:36Z)
• FASTER: Rethinking Real-Time Flow VLAs [82.58822112377923]
  Real-time execution is crucial for deploying Vision-Language-Action (VLA) models in the physical world.<n>We show that reaction time follows a uniform distribution determined jointly by the Time to First Action (TTFA) and the execution horizon.<n>We propose Fast Action Sampling for ImmediaTE Reaction (FASTER) to overcome this issue.
  arXiv  Detail & Related papers  (2026-03-19T17:51:37Z)
• Closed-Loop Action Chunks with Dynamic Corrections for Training-Free Diffusion Policy [52.106797722292896]
  We present DCDP, a Dynamic Closed-Loop Diffusion Policy framework that integrates chunk-based action generation with real-time correction.<n>In dynamic PushT simulations, DCDP improves adaptability by 19% without retraining while requiring only 5% additional computation.
  arXiv  Detail & Related papers  (2026-03-02T15:04:18Z)
• AdaSpot: Spend Resolution Where It Matters for Precise Event Spotting [59.31340724915079]
  Event Spotting is a key task for applications in sports analytics, robotics, and autonomous systems.<n>bfAdaSpot achieves state-of-the-art performance under strict evaluation metrics.
  arXiv  Detail & Related papers  (2026-02-25T16:24:48Z)
• Learning Native Continuation for Action Chunking Flow Policies [40.56048312294812]
  Action chunking enables Vision Language Action (VLA) models to run in real time, but naive chunked execution often exhibits discontinuities at chunk boundaries.<n>We propose Legato, a training-time continuation method for action-chunked flow-based VLA policies.<n>Legato produces smoother trajectories and reduces spurious multimodal switching during execution, leading to less hesitation and shorter task completion time.
  arXiv  Detail & Related papers  (2026-02-13T14:56:06Z)
• Real-Time Robot Execution with Masked Action Chunking [38.37108371991901]
  Real-time execution is essential for cyber-physical systems such as robots.<n>Asynchronous inference has recently emerged as a system-level paradigm for real-time robot manipulation.<n>We propose REMAC, which learns corrective adjustments on the pretrained policy through masked action chunking.
  arXiv  Detail & Related papers  (2026-01-27T23:48:32Z)
• VLA-RAIL: A Real-Time Asynchronous Inference Linker for VLA Models and Robots [5.308743386891208]
  Vision-Language-Action (VLA) models have achieved remarkable breakthroughs in robotics.<n>The strategies for fusing a queue of successive action chunks have a profound impact on the overall performance of VLA models.<n>Existing methods suffer from jitter, stalling, or even pauses in robotic action execution.<n>This paper introduces VLA-RAIL, a novel framework designed to conduct model inference and robot motion control asynchronously.
  arXiv  Detail & Related papers  (2025-12-31T06:59:42Z)
• Training-Time Action Conditioning for Efficient Real-Time Chunking [45.91723746443767]
  We propose simulating inference delay at training time and conditioning on action prefixes directly, eliminating inference-time overhead.<n>In simulated experiments, we find that training-time RTC outperforms inference-time RTC at higher inference delays.<n>Our results suggest that training-time action conditioning is a practical drop-in replacement for inference-time inpainting in real-time robot control.
  arXiv  Detail & Related papers  (2025-12-05T18:57:28Z)
• Leave No Observation Behind: Real-time Correction for VLA Action Chunks [36.13271200613596]
  Asynchronous Action Chunk Correction (A2C2) is a lightweight real-time chunk correction head that runs every control step.<n>We show that A2C2 is an effective plug-in mechanism for deploying high-capacity chunking policies in real-time control.
  arXiv  Detail & Related papers  (2025-09-27T10:07:49Z)
• Towards Low-Latency Event Stream-based Visual Object Tracking: A Slow-Fast Approach [32.91982063297922]
  We propose a novel Slow-Fast Tracking paradigm that flexibly adapts to different operational requirements, termed SFTrack.<n>The proposed framework supports two complementary modes, i.e., a high-precision slow tracker for scenarios with sufficient computational resources, and an efficient fast tracker tailored for latency-aware, resource-constrained environments.<n>Our framework first performs graph-based representation learning from high-temporal-resolution event streams, and then integrates the learned graph-structured information into two FlashAttention-based vision backbones.
  arXiv  Detail & Related papers  (2025-05-19T09:37:23Z)
• Handling Delay in Real-Time Reinforcement Learning [24.869578892204792]
  We present a theoretically motivated solution that leverages temporal skip connections combined with history-augmented observations.<n>We demonstrate parallel neuron computation can accelerate inference by 6-350% on standard hardware.
  arXiv  Detail & Related papers  (2025-03-30T15:30:27Z)
• Faster Diffusion Action Segmentation [9.868244939496678]
  Temporal Action Classification (TAS) is an essential task in video analysis, aiming to segment and classify continuous frames into distinct action segments. Recent advances in diffusion models have demonstrated substantial success in TAS tasks due to their stable training process and high-quality generation capabilities. We propose EffiDiffAct, an efficient and high-performance TAS algorithm.
  arXiv  Detail & Related papers  (2024-08-04T13:23:18Z)
• StreamFlow: Streamlined Multi-Frame Optical Flow Estimation for Video Sequences [31.210626775505407]
  Occlusions between consecutive frames have long posed a significant challenge in optical flow estimation. We present a Streamlined In-batch Multi-frame (SIM) pipeline tailored to video input, attaining a similar level of time efficiency to two-frame networks. StreamFlow not only excels in terms of performance on challenging KITTI and Sintel datasets, with particular improvement in occluded areas.
  arXiv  Detail & Related papers  (2023-11-28T07:53:51Z)
• Prompt-augmented Temporal Point Process for Streaming Event Sequence [18.873915278172095]
  We present a novel framework for continuous monitoring of a Neural Temporal Point Processes (TPP) model. PromptTPP consistently achieves state-of-the-art performance across three real user behavior datasets.
  arXiv  Detail & Related papers  (2023-10-08T03:41:16Z)
• Latency-aware Unified Dynamic Networks for Efficient Image Recognition [72.8951331472913]
  LAUDNet is a framework to bridge the theoretical and practical efficiency gap in dynamic networks. It integrates three primary dynamic paradigms-spatially adaptive computation, dynamic layer skipping, and dynamic channel skipping. It can notably reduce the latency of models like ResNet by over 50% on platforms such as V100,3090, and TX2 GPUs.
  arXiv  Detail & Related papers  (2023-08-30T10:57:41Z)
• AEGNN: Asynchronous Event-based Graph Neural Networks [54.528926463775946]
  Event-based Graph Neural Networks generalize standard GNNs to process events as "evolving"-temporal graphs. AEGNNs are easily trained on synchronous inputs and can be converted to efficient, "asynchronous" networks at test time.
  arXiv  Detail & Related papers  (2022-03-31T16:21:12Z)
• Argus++: Robust Real-time Activity Detection for Unconstrained Video Streams with Overlapping Cube Proposals [85.76513755331318]
  Argus++ is a robust real-time activity detection system for analyzing unconstrained video streams. The overall system is optimized for real-time processing on standalone consumer-level hardware.
  arXiv  Detail & Related papers  (2022-01-14T03:35:22Z)
• End-to-end Temporal Action Detection with Transformer [86.80289146697788]
  Temporal action detection (TAD) aims to determine the semantic label and the boundaries of every action instance in an untrimmed video. Here, we construct an end-to-end framework for TAD upon Transformer, termed textitTadTR. Our method achieves state-of-the-art performance on HACS Segments and THUMOS14 and competitive performance on ActivityNet-1.3.
  arXiv  Detail & Related papers  (2021-06-18T17:58:34Z)
• A Real-time Action Representation with Temporal Encoding and Deep Compression [115.3739774920845]
  We propose a new real-time convolutional architecture, called Temporal Convolutional 3D Network (T-C3D), for action representation. T-C3D learns video action representations in a hierarchical multi-granularity manner while obtaining a high process speed. Our method achieves clear improvements on UCF101 action recognition benchmark against state-of-the-art real-time methods by 5.4% in terms of accuracy and 2 times faster in terms of inference speed with a less than 5MB storage model.
  arXiv  Detail & Related papers  (2020-06-17T06:30:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.