2026-07-27 04:00 UTCOriginal source2 min readUpdated: 2026-07-27 08:40 UTC

Ordered Action Tokens for Visuomotor Policy Learning

This paper introduces Ordered Action Tokenization (OAT), a learned action tokenizer that maps continuous robot action chunks to an ordered sequence of discrete tokens, achieving high compression, total decodability, and ordered token space. It demonstrates strong performance across various tasks and backbones.

SourcearXiv RoboticsAuthor: Chaoqi Liu, Yue Zhao, Haonan Chen, Xiaoshen Han, Jiawei Gao, Ehsan Adeli, Yilun Du

Article intelligence

EngineersAdvanced

Key points

OAT uses a transformer with registers, finite scalar quantization, and ordering-inducing training to discretize action chunks into an ordered token sequence. Early tokens encode coarse control, later tokens refine details.
OAT is validated on autoregressive policies and token co-training policies, offering anytime tradeoff between inference cost and action fidelity.
Across 60+ tasks on five simulation benchmarks and real-world settings, OAT achieves strong policy performance with greater inference flexibility.

Why it matters

This matters because OAT uses a transformer with registers, finite scalar quantization, and ordering-inducing training to discretize action chunks into an ordered token sequence. Early tokens encode coarse control, later tokens refine details.

Technical impact

May affect model selection, inference cost, product capability, and evaluation benchmarks.

This panel is AI-generated and reviewed for accuracy.

-->

[Submitted on 23 Jul 2026]

Title:Ordered Action Tokens for Visuomotor Policy Learning

View a PDF of the paper titled Ordered Action Tokens for Visuomotor Policy Learning, by Chaoqi Liu and 6 other authors

View PDF

Abstract:Action tokenization maps continuous robot action chunks to discrete tokens and has become an important interface for modern visuomotor policies. Existing approaches either rely on analytical discretization methods that produce prohibitively long token sequences or learned latent tokenizers that lack structure, limiting their compatibility with downstream policies. In this work, we identify three desiderata for action tokenization - high compression, total decodability, and an ordered token space - and introduce Ordered Action Tokenization (OAT), a learned action tokenizer that satisfies all three. OAT discretizes action chunks into an ordered sequence of tokens using a transformer with registers, finite scalar quantization, and ordering-inducing training mechanisms. By training each token prefix to decode into a valid action chunk, OAT places coarse control information in early tokens and uses later tokens to refine residual detail, yielding an anytime tradeoff between inference cost and action fidelity. We validate OAT in two prevailing uses of action tokens: autoregressive policies that generate tokens for control, and token co-training policies that use token losses to shape the vision-language model context consumed by a flow-based action expert. Across three policy backbones and more than 60 tasks spanning five simulation benchmarks and real-world settings, OAT consistently delivers strong policy performance while offering significantly greater flexibility at inference time.

Subjects:

Robotics (cs.RO); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)

Cite as: arXiv:2607.21670 [cs.RO]

(or arXiv:2607.21670v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2607.21670

arXiv-issued DOI via DataCite

Submission history

From: Chaoqi Liu [view email] [v1] Thu, 23 Jul 2026 07:04:51 UTC (7,077 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Ordered Action Tokens for Visuomotor Policy Learning, by Chaoqi Liu and 6 other authors

View PDF

TeX Source

view license

Current browse context:

cs.RO

new | recent | 2026-07

Change to browse by:

cs cs.AI cs.LG

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)