Retrospective Open-Vocabulary Memory for Long-Term Object Search

arXiv:2610.00330v1 Announce Type: cross Abstract: Long-term object search requires learning where objects usually appear from repeated but uneven observations of a changing environment. We formulate retrospective open-vocabulary memory as probabilistic inference from censored observations, where the key idea is to reason with evidence per opportunity: a detection or non-detection should influence belief only in proportion to the robot's opportunity to observe the corresponding location. We introduce ECROM, which uses this principle to estimate long-term prevalence for concepts specified only at query time and converts the resulting belief directly into an active-search prior. To evaluate this problem, we introduce a controlled long-term benchmark in ten HM3D homes that independently varies object placement and observation opportunity across repeated traversals. ECROM improves support-level AP on held-out queries by 4.5 points and search SPL by 4.2 points over the strongest competing memory in each metric. The benchmark, dataset, and code will be open-sourced.

Related

• OpenBelief-Nav: Evidence-Preserving Object Memory for Open-Vocabulary Language-Guided Navigation
• Modeling Long-Term Memory and Temporal Attention Shifts for Video Salient Object Ranking with a New Benchmark
• D^2-VLA: Dual-Memory Dual-Frequency Vision-Language-Action Model For Long Dynamic Manipulation
• AnchorVLN: Geometry-Anchored Vision-Language Grounding Reasoning for Open-Vocabulary Navigation

Source: arXiv cs.CV | 2026-10-02