AI News HubLIVE
原文

GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation

GEM-4D is a geometry-grounded video world model that improves robot manipulation by injecting dense 4D correspondence supervision distilled from a pretrained geometry foundation model. It jointly captures appearance and geometric structure without additional inference cost. An inverse dynamics module converts consistent video rollouts into executable robot trajectories. GEM-4D achieves state-of-the-art performance on video prediction and geometric consistency, boosting real-world manipulation success from 61% to 81%.

Article intelligence

EngineersAdvanced

Key points

  • GEM-4D enhances video world models with dense 4D correspondence supervision for geometric consistency.
  • It maintains a single-stream architecture with no extra inference cost.
  • An inverse dynamics module translates video rollouts into robot trajectories.
  • Real-world manipulation success rate improves from 61% to 81%.

Why it matters

This matters because GEM-4D enhances video world models with dense 4D correspondence supervision for geometric consistency.

Technical impact

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

[2605.22882] GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation

[Submitted on 20 May 2026]

Title:GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation

View a PDF of the paper titled GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation, by Kaichen Zhou and 10 other authors

View PDF HTML (experimental)

Abstract:Video world models can generate realistic futures from a single instruction, but they often fail to preserve consistent point-level motion over time. As a result, the generated videos appear plausible, yet lack the physical grounding required for reliable action execution, such as robot manipulation. We present GEM-4D, a geometry-grounded video world model that resolves this limitation by injecting dense 4D correspondence supervision, distilled from a pretrained geometry foundation model, into the video generative backbone during training. This supervision enables the model to jointly capture appearance and geometric structure while retaining a single-stream architecture with no additional inference cost. We further introduce an inverse dynamics module that converts correspondence-consistent video rollouts into executable robot trajectories, enabling direct deployment in both real-world and simulated manipulation. GEM-4D achieves state-of-the-art performance on both video prediction and geometric consistency across simulation and realistic scenarios and improves real-world manipulation success from 61% to 81%. Additional results are available at the project page: this https URL.

Comments: Robotic World Model, Video Generative Model

Subjects:

Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)

Cite as: arXiv:2605.22882 [cs.CV]

(or arXiv:2605.22882v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2605.22882

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Kaichen Zhou [view email] [v1] Wed, 20 May 2026 21:36:44 UTC (3,896 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation, by Kaichen Zhou and 10 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CV

new | recent | 2026-05

Change to browse by:

cs cs.RO

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?)