Skip to content
AI News HubLIVE
Original source2 min read

Learning Latent Goal Costs for Visual World-Model Planning with an Expanding Curriculum

Summary

Researchers propose fitting a small residual adapter on frozen visual world model embeddings to improve latent goal costs for image-goal planning. Using an expanding curriculum and trajectory order, the method boosts success rates from 54% to 98% on DotWall and 82% to 96% on PointMaze without task-specific progress labels.

SourcearXiv RoboticsAuthor: Konstantinos Mylonas, Thrasyvoulos Spyropoulos
Learning Latent Goal Costs for Visual World-Model Planning with an Expanding Curriculum
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 12 Nov 2026]

Title:Learning Latent Goal Costs for Visual World-Model Planning with an Expanding Curriculum

View a PDF of the paper titled Learning Latent Goal Costs for Visual World-Model Planning with an Expanding Curriculum, by Konstantinos Mylonas and Thrasyvoulos Spyropoulos

View PDF HTML (experimental)

Abstract:Image-goal planning with a frozen visual world model depends on how predicted observations are scored against the goal. Mean-squared error (MSE) between embeddings from a pretrained visual encoder can provide a useful signal near a goal, yet favor states across an obstacle that are visually similar to the goal and difficult to reach. We fit a small residual adapter on top of frozen I-JEPA embeddings to improve this latent goal cost. Starting near each goal, a planner collects trajectories from progressively wider regions of initial states. The adapter learns from the order of observations along successful trajectories, with additional comparisons inferred from failed rollouts. No task-specific progress labels are used for fitting, so the procedure can be applied to other goal-reaching tasks. DotWall and PointMaze are used in this work. In paired 50-case evaluations with identical starts, goals, world models, and planner settings, success increases from 54% to 98% in DotWall and from 82% to 96% in PointMaze. On 16 unseen DotWall layout-goal cases, the adapter fitted on one fixed layout improves agreement between latent-cost ordering and shortest legal-path ordering from 71.9% to 85.8%. The results indicate that planning experience can improve a frozen visual representation's goal cost without retraining the encoder or the world model.

Subjects:

Robotics (cs.RO); Machine Learning (cs.LG)

Cite as: arXiv:2611.17529 [cs.RO]

(or arXiv:2611.17529v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2611.17529

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Konstantinos Mylonas [view email] [v1] Thu, 12 Nov 2026 21:28:35 UTC (1,053 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Learning Latent Goal Costs for Visual World-Model Planning with an Expanding Curriculum, by Konstantinos Mylonas and Thrasyvoulos Spyropoulos

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.RO

new | recent | 2026-11

Change to browse by:

cs cs.LG

References & Citations

SciX

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?)

Key points and analysis

Article intelligence

InvestorsAdvanced

Key points

  • A residual adapter is fitted on frozen I-JEPA embeddings to refine goal-cost scoring.
  • The adapter learns from observation order in successful trajectories and comparisons from failed rollouts, using an expanding curriculum.
  • Success increases from 54% to 98% on DotWall and from 82% to 96% on PointMaze in paired evaluations.
  • On unseen layouts, latent-cost ordering agreement with shortest legal-path ordering improves from 71.9% to 85.8%.

Highlights and analysis are generated automatically and may contain errors. Check the original source.