LVMem: Image-Augmented Memory for Long-Horizon Question Answering
arXiv:2610.27104v1 Announce Type: new Abstract: Reliable language-guided perception is essential for embodied agents, where questions about objects, events, and their locations must be answered from long observation histories. Unlike conventional visual question answering, realistic robotic setting…
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-10-21 04:00 · arXiv cs.CV
LVMem: Image-Augmented Memory for Long-Horizon Question Answering