SCAR: Self-Supervised Continuous Action Representation Learning
SCAR proposes a self-supervised framework that learns unified action representations across embodiments from visual transitions using joint inverse-forward dynamics. It leverages a pretrained generative backbone, an inverse dynamics model, and a forward dynamics model, with Gaussian prior regularization and adversarial invariance to enhance transferability. Experiments show that this action representation outperforms embodiment-specific raw actions, enabling better cross-embodiment low-data adaptation and cross-task transfer.
[2605.16412] SCAR: Self-Supervised Continuous Action Representation Learning
[Submitted on 13 May 2026]
Title:SCAR: Self-Supervised Continuous Action Representation Learning
View a PDF of the paper titled SCAR: Self-Supervised Continuous Action Representation Learning, by Hongjia Liu and 5 other authors
View PDF HTML (experimental)
Abstract:Despite the central role of action in embodied intelligence, learning transferable action representations from visual transitions remains a fundamental challenge, particularly when world models must generalize across embodiments under limited data. We argue that action is not merely an auxiliary conditioning signal, but a distinct representational factor that decouples the controllable change from embodiment-specific actuation. In this work, we propose SCAR, a joint inverse-forward dynamics framework for learning unified action representations across embodiments from visual transitions. Built on a pretrained generative backbone, SCAR uses an inverse dynamics model (IDM) to infer latent actions from latent observation pairs and a forward dynamics model (FDM) to predict future dynamics conditioned on them. To make the latent space transferable rather than a generic visual bottleneck, we regularize the latent action posterior toward a standard Gaussian prior to limit arbitrary visual encoding, and introduce adversarial invariance to suppress embodiment- and environment-specific nuisance factors. Experiments on the Procgen and Robotwin dataset show that the learned unified latent action representation serves as a stronger conditioning interface for world modeling than embodiment-specific raw actions, yielding improved cross-embodiment low-data adaptation and cross-task transfer. Taken together, these results suggest that action can be learned as a shared representation of controllable change across embodiments, providing an interface for more transferable and generalizable world models.
Subjects:
Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
Cite as: arXiv:2605.16412 [cs.RO]
(or arXiv:2605.16412v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2605.16412
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Hongjia Liu [view email] [v1] Wed, 13 May 2026 16:23:11 UTC (22,327 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled SCAR: Self-Supervised Continuous Action Representation Learning, by Hongjia Liu and 5 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.RO
new | recent | 2026-05
Change to browse by:
cs cs.CV
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?)