Skip to content
AI News HubLIVE
Original source2 min read

VICTR: Value-Informed In-Context Learning for Vision-Language-Action Models

Summary

VICTR introduces progress-informed context retrieval for vision-language-action models via an In-Context Value Function Estimator (IC-VFE). By estimating task-relative progress from a reference demonstration, a language instruction, and the current observation, VICTR selects demonstration chunks at matching execution stages for a π0.5 policy post-trained for in-context action generation. On unseen out-of-domain real-world manipulation tasks, it raises success from 6.2% to 23.8% and task progress from 28.9% to 55.5%.

SourcearXiv RoboticsAuthor: Luca Macesanu, Tianluo Zhang, Aditya Patil, Archit Sharma, Kevin Angers, Christopher M. Clark, Chen Feng, Juexiao Zhang
VICTR: Value-Informed In-Context Learning for Vision-Language-Action Models
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 5 Nov 2026]

Title:VICTR: Value-Informed In-Context Learning for Vision-Language-Action Models

View a PDF of the paper titled VICTR: Value-Informed In-Context Learning for Vision-Language-Action Models, by Luca Macesanu and 7 other authors

View PDF HTML (experimental)

Abstract:Recent advances in robot foundation models have highlighted the potential of in-context learning (ICL) for adapting robot behavior from demonstrations without further fine-tuning. Previous work has used retrieval-based post-training to equip pretrained vision-language-action (VLA) models with the capability for ICL by teaching them to condition action predictions on retrieved visually-relevant demonstration chunks. However, the effectiveness of retrieval hinges on selecting context relevant to the current execution stage, which visual similarity alone may not capture. We introduce VICTR, a framework enabling in-context learning in VLAs via progress-informed context retrieval built around an In-Context Value Function Estimator (IC-VFE). IC-VFE conditions on a reference demonstration video, a language instruction and the current observation to estimate task-relative progress. By conditioning progress estimation on a reference demonstration, IC-VFE can align the current state with a demonstrated execution even for tasks unseen during training. VICTR uses the estimated progress to select demonstration chunks at corresponding stages of execution and supplies them to a $\pi_{0.5}$ policy post-trained for in-context action generation. On unseen out-of-domain real-world manipulation tasks, VICTR raises the success rate from 6.2% for a fine-tuned $\pi_{0.5}$ baseline to 23.8% and more than doubles the task progress rate, from 28.9% to 55.5%. Project page with code, data and videos: this https URL

Comments: 11 pages, 8 figures, 4 tables. Project page: this https URL

Subjects:

Robotics (cs.RO)

Cite as: arXiv:2611.08698 [cs.RO]

(or arXiv:2611.08698v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2611.08698

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Juexiao Zhang [view email] [v1] Thu, 5 Nov 2026 20:54:52 UTC (5,676 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled VICTR: Value-Informed In-Context Learning for Vision-Language-Action Models, by Luca Macesanu and 7 other authors

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

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

EngineersAdvanced

Key points

  • IC-VFE estimates task-relative progress by conditioning on a reference demonstration video, language instruction, and current observation.
  • VICTR retrieves demonstration chunks at corresponding execution stages and supplies them to a π0.5 policy post-trained for in-context action generation.
  • On unseen out-of-domain real-world manipulation tasks, VICTR improves success rate from 6.2% to 23.8% and task progress rate from 28.9% to 55.5%.

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