Preprint
Aug 2026
LT-Mem: Volatility-Aware Spatio-Temporal Memory for Lifelong Scene Understanding
LT-Mem is proposed, a volatility-aware memory evolution framework that unifies spatially aligned instance-level 3D perception with volatility-conditioned temporal reasoning and introduces LT-VQA, a dataset and evaluation suite comprising multi-session recordings, persistent identity annotations, and temporal QA pairs.
Yumin Lee, Hyoseok Ju, Giseop Kim
· 0 citations