Metraipolis › archive › dc_135cae94fa70

LT-Mem: Volatility-Aware Spatio-Temporal Memory for Lifelong Scene Understanding — arXiv:2608.19059

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.19059
License (as archived)
CC0-1.0
Archived
2026-10-18T14:06:38.718Z
SHA-256 of the archived text
9bfcd738800ffdac99163fa1ba69b655c4956accb9c233dc2fa742b022a4726f
Stable URL of this page
https://metraipolis.com/documento/dc_135cae94fa70

How to cite

LT-Mem: Volatility-Aware Spatio-Temporal Memory for Lifelong Scene Understanding — arXiv:2608.19059 — arXiv (en), https://arxiv.org/abs/2608.19059 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_135cae94fa70 (Metraipolis archive dc_135cae94fa70, sha256 9bfcd738800ffdac99163fa1ba69b655c4956accb9c233dc2fa742b022a4726f)
BibTeX
@misc{dc135cae94fa70,
  title = {LT-Mem: Volatility-Aware Spatio-Temporal Memory for Lifelong Scene Understanding — arXiv:2608.19059},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.19059},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_135cae94fa70; sha256 9bfcd738800ffdac99163fa1ba69b655c4956accb9c233dc2fa742b022a4726f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.19059. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-20 in cs.CV).
Categorie arXiv: Robotics (cs.RO) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.19059 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T14:00:22.606Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-20?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).