AI News HubLIVE
原文2 min read

VL-MemKnG: Hybrid Memory with a Spatio-Temporal Knowledge Graph for Question Answering over Long Egocentric Navigation Trajectories

This paper presents VL-MemKnG, a hybrid memory framework that combines a spatio-temporal knowledge graph with persistent segment-level contextual memory for question answering over long egocentric navigation videos. It improves Top-1 retrieval accuracy from 58% to 67% and Recall@1 from 34.50% to 40.55% on the WalkieKnowledgeT+ benchmark, outperforming methods including Gemini 2.5 Pro and Qwen 3.5+.

SourcearXiv RoboticsAuthor: Svetlana Lukina, Mohamad Al Mdfaa, Gloria Haro, Sergey Zagoruyko, Gonzalo Ferrer

[2606.17183] VL-MemKnG: Hybrid Memory with a Spatio-Temporal Knowledge Graph for Question Answering over Long Egocentric Navigation Trajectories

[Submitted on 15 Jun 2026]

Title:VL-MemKnG: Hybrid Memory with a Spatio-Temporal Knowledge Graph for Question Answering over Long Egocentric Navigation Trajectories

View a PDF of the paper titled VL-MemKnG: Hybrid Memory with a Spatio-Temporal Knowledge Graph for Question Answering over Long Egocentric Navigation Trajectories, by Svetlana Lukina and 4 other authors

View PDF HTML (experimental)

Abstract:Answering navigation-relevant questions over long egocentric videos requires retrieving and organizing evidence distributed across distant temporal moments while maintaining spatial and contextual consistency. Although long-context vision--language models can achieve strong answer quality, they are computationally expensive for long trajectories and inefficient for repeated querying. Recent graph-based approaches such as VL-KnG address this challenge through persistent spatio-temporal knowledge graphs, but graph-centric retrieval alone may underrepresent broader temporal continuity and contextual cues. We present VL-MemKnG, a hybrid memory framework that extends VL-KnG by combining a spatio-temporal knowledge graph with persistent segment-level contextual memory. The knowledge graph captures structured relational information and long-range object associations, while segment-level memory preserves broader temporal context for long-horizon evidence retrieval. A hybrid retrieval-and-reasoning module jointly operates over both memory representations to produce evidence-grounded answers and temporally organized supporting evidence. We also introduce WalkieKnowledgeT+, an extension of WalkieKnowledge for long-horizon navigation-oriented video question answering. The benchmark includes temporally distributed reasoning tasks requiring evidence aggregation across multiple non-cooccurring moments. On WalkieKnowledgeT+, VL-MemKnG improves Top-1 retrieval accuracy from 58% to 67% and Recall@1 from 34.50% to 40.55%, outperforming all compared methods, including Gemini 2.5 Pro and Qwen 3.5+. The gains are particularly pronounced on temporal-global and temporally scattered aggregation questions, demonstrating the benefits of combining structured relational memory with segment-level contextual memory while maintaining efficient query-time inference.

Subjects:

Robotics (cs.RO)

Cite as: arXiv:2606.17183 [cs.RO]

(or arXiv:2606.17183v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2606.17183

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Svetlana Lukina [view email] [v1] Mon, 15 Jun 2026 18:21:14 UTC (3,038 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled VL-MemKnG: Hybrid Memory with a Spatio-Temporal Knowledge Graph for Question Answering over Long Egocentric Navigation Trajectories, by Svetlana Lukina and 4 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?)