# LT-Mem: Volatility-Aware Spatio-Temporal Memory for Lifelong Scene Understanding

arXiv: https://arxiv.org/abs/2608.19059 · HTML: https://mlsanity.com/paper/2608.19059/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 19 references that are in the map.
- First posted on arXiv 19 Aug 2026.

## Builds on (most cited first, 16 of 16)

- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [SAM 3: Segment Anything with Concepts](https://mlsanity.com/paper/2511.16719/) (2025)
- [Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Age](https://mlsanity.com/paper/1606.05830/) (2016)
- [ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning](https://mlsanity.com/paper/2309.16650/) (2023)
- [MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors](https://mlsanity.com/paper/2412.12392/) (2024)
- [RIO: 3D Object Instance Re-Localization in Changing Indoor Environments](https://mlsanity.com/paper/1908.06109/) (2019)
- [3D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning](https://mlsanity.com/paper/2411.17735/) (2024)
- [ReMEmbR: Building and Reasoning Over Long-Horizon Spatio-Temporal Memory for Robot Navigation](https://mlsanity.com/paper/2409.13682/) (2024)
- [Khronos: A Unified Approach for Spatio-Temporal Metric-Semantic SLAM in Dynamic Environments](https://mlsanity.com/paper/2402.13817/) (2024)
- [General Place Recognition Survey: Towards Real-World Autonomy](https://mlsanity.com/paper/2405.04812/) (2024)
- [Describe Anything Anywhere At Any Moment](https://mlsanity.com/paper/2512.00565/) (2025)
- [LT-mapper: A Modular Framework for LiDAR-based Lifelong Mapping](https://mlsanity.com/paper/2107.07712/) (2021)
- [POCD: Probabilistic Object-Level Change Detection and Volumetric Mapping in Semi-Static Scenes](https://mlsanity.com/paper/2205.01202/) (2022)
- [Searching in Space and Time: Unified Memory-Action Loops for Open-World Object Retrieval](https://mlsanity.com/paper/2511.14004/) (2025)
- [MR.ScaleMaster: Scale-Consistent Collaborative Mapping from Crowd-Sourced Monocular Videos](https://mlsanity.com/paper/2604.11372/) (2026)

## Built on by (most cited first, 1 of 1)

- [In-Context Learning for Robots: Methods and Applications](https://mlsanity.com/paper/2609.36012/) (2026)

## Abstract (arXiv)

Long-term robot operation in evolving environments requires object-level understanding that persists across repeated revisits. Existing systems either overwrite history to maintain an up-to-date map or store semantic snapshots without consistent cross-session object identity, resulting in temporal amnesia: the systematic loss of object history that prevents answering queries such as "Where has the green chair been across all sessions?" We propose LT-Mem, a volatility-aware memory evolution framework that unifies spatially aligned instance-level 3D perception with volatility-conditioned temporal reasoning. First, a multi-session SLAM backbone provides spatially aligned per-object observations across sessions. Second, a reasoning layer governs how object memory evolves: deterministic evidence scoring preserves cross-session identity, and a volatility-aware policy selects among overwrite, hold, and multi-hypothesis actions based on each object's dynamics. Third, the resulting Tri-Memory structure (Live, Delta, Meta) preserves both current states and event histories, enabling longitudinal object-centric reasoning. We further introduce LT-VQA, a dataset and evaluation suite comprising multi-session recordings, persistent identity annotations, and temporal QA pairs. Experiments show that LT-Mem consistently outperforms baselines across all metrics while consuming an order of magnitude fewer tokens, and ablations confirm that gains are driven by the structured memory architecture rather than LLM capacity.