arxiv
PublishedJuly 21, 2026 at 4:00 AM
Spatiotemporal Knowledge Graphs as Persistent Scene Memory for Embodied Question Answering
Publisher summary· verbatim
arXiv:2510.01483v3 Announce Type: replace-cross Abstract: Vision-language models (VLMs) demonstrate strong image-level scene understanding, but reasoning over long egocentric video remains costly: because VLMs maintain no persistent memory or explicit spatial representation, all sampled frames must
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivTeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents1darxivNatural Language Access to Domain-Specific Metadata: A Reusable Framework for LLM Query Generation1darxivSPECTRA: Band-Routed Embedding and Stage-Wise LoRA for Cross-Sensor Fine-Tuning of Geospatial Foundation Models1darxivTowards a Deterministic Math Solver for Clinical Language Models1dThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗