DREAM-Chunk: Reactive Action Chunking with Latent World Model
DREAM-Chunk is a test-time scaling method that augments chunking-based policies with a lightweight latent world model, without additional policy fine-tuning. It samples multiple candidate action chunks, rolls out predicted latent futures, and selects actions from the chunk whose predicted state best matches observed rollout, improving robustness under stochastic dynamics. Validated on Kinetix benchmark and multiple robot platforms.
[2606.18589] DREAM-Chunk: Reactive Action Chunking with Latent World Model
[Submitted on 17 Jun 2026]
Title:DREAM-Chunk: Reactive Action Chunking with Latent World Model
View a PDF of the paper titled DREAM-Chunk: Reactive Action Chunking with Latent World Model, by Wenxi Chen and 8 other authors
View PDF HTML (experimental)
Abstract:Action chunking has become a common interface for vision-language-action (VLA) models, enabling low-frequency policy inference to drive high-frequency robot execution. However, once an action chunk is committed, its open-loop execution can be brittle under stochastic dynamics, hardware execution errors, and partial observability. We propose DREAM-Chunk, a test-time scaling method that augments chunking-based policies with a lightweight latent world model, without requiring additional policy fine-tuning. At test time, DREAM-Chunk samples multiple candidate action chunks, rolls out their predicted latent futures, and selects actions from the chunk whose predicted state best matches the observed rollout. In this way, DREAM-Chunk uses additional test-time computation to cover multiple plausible stochastic futures and improve reactivity during long-horizon chunk execution. On the Kinetix benchmark, DREAM-Chunk improves robustness under increasing action noise and benefits from larger candidate sample sizes, especially when demonstrations contain corrective behaviors. We further validate DREAM-Chunk on four manipulation tasks across two robot platforms and two VLA policies under various sources of stochasticity. Across simulation and hardware experiments, DREAM-Chunk improves the robustness of action-chunking policies in stochastic dynamics.
Subjects:
Robotics (cs.RO)
Cite as: arXiv:2606.18589 [cs.RO]
(or arXiv:2606.18589v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2606.18589
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Wenxi Chen [view email] [v1] Wed, 17 Jun 2026 01:28:07 UTC (591 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled DREAM-Chunk: Reactive Action Chunking with Latent World Model, by Wenxi Chen and 8 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.RO
new | recent | 2026-06
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
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
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)