Pith Number

pith:GPYBQFOR

pith:2025:GPYBQFOREE7CMKJRK2JLMO2X7M

not attested not anchored not stored refs resolved

Real-Time Execution of Action Chunking Flow Policies

Kevin Black, Manuel Y. Galliker, Sergey Levine

Real-time chunking generates the next action chunk while executing the current one by freezing committed steps and inpainting the rest, letting any diffusion- or flow-based vision-language-action model run smoothly under latency.

arxiv:2506.07339 v2 · 2025-06-09 · cs.RO · cs.AI · cs.LG

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{GPYBQFOREE7CMKJRK2JLMO2X7M}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

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, significantly improving task throughput and enabling high success rates in precise tasks even in the presence of significant latency.

C2weakest assumption

That the inpainting step for uncertain future actions in the next chunk preserves task-relevant consistency and does not introduce errors that degrade performance on precise or dynamic tasks when inference delay is present.

C3one line summary

Real-time chunking (RTC) allows diffusion- and flow-based action chunking policies to execute smoothly and asynchronously, maintaining high success rates on dynamic tasks even with significant inference latency.

References

71 extracted · 71 resolved · 27 Pith anchors

[1] Is Conditional Generative Modeling all you need for Decision-Making? 2022 · arXiv:2211.15657

[2] Automatic differentiation in machine learning: a survey.Journal of machine learning research, 18(153):1–43, 2018 2018

[3] Minivla: A better vla with a smaller footprint, 2024 2024

[4] GR00T N1: An Open Foundation Model for Generalist Humanoid Robots 2025 · arXiv:2503.14734

[5] $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control 2024 · arXiv:2410.24164

Formal links

2 machine-checked theorem links

Cited by

30 papers in Pith

Abstraction for Offline Goal-Conditioned Reinforcement Learning

Learning Native Continuation for Action Chunking Flow Policies

OxyGen: Unified KV Cache Management for VLA Inference under Multi-Task Parallelism

Implicit Action Chunking for Smooth Continuous Control

Towards a Multi-Embodied Grasping Agent

Receipt and verification

First computed	2026-05-17T23:38:52.366665Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

33f01815d1213e2629315692b63b57fb1fc1462674d41b44a62b08e98e93d496

Aliases

arxiv: 2506.07339 · arxiv_version: 2506.07339v2 · doi: 10.48550/arxiv.2506.07339 · pith_short_12: GPYBQFOREE7C · pith_short_16: GPYBQFOREE7CMKJR · pith_short_8: GPYBQFOR

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/GPYBQFOREE7CMKJRK2JLMO2X7M \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 33f01815d1213e2629315692b63b57fb1fc1462674d41b44a62b08e98e93d496

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "4cf2bad1c8855d55c1ceaf996849ce90448efbc6c0dbd03dce64fdb28e882895",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.RO",
    "submitted_at": "2025-06-09T01:01:59Z",
    "title_canon_sha256": "46feacdc1ae6f195d07398757a5ee16b93a705e05086813442c6baf5d78beee1"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2506.07339",
    "kind": "arxiv",
    "version": 2
  }
}