VBGS-SLAM uses variational inference on conjugate Gaussian properties to couple 3DGS map refinement and pose tracking with closed-form updates and posterior uncertainty, reducing drift compared to deterministic methods.
Catastrophic forgetting in connectionist networks
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 2polarities
background 2representative citing papers
Parameter-difference and model-inversion attacks can identify forgotten classes after machine unlearning on standard image datasets.
Proposes a domain incremental continual learning benchmark for ICU time series model transportability across US regions and evaluates data replay and EWC methods.
BGG adapts vision foundation models using multi-granularity dilated convolutions and frequency-domain patch aggregation to achieve state-of-the-art cross-view geo-localization on University-1652 and SUES-200 with low training cost.
citing papers explorer
-
VBGS-SLAM: Variational Bayesian Gaussian Splatting Simultaneous Localization and Mapping
VBGS-SLAM uses variational inference on conjugate Gaussian properties to couple 3DGS map refinement and pose tracking with closed-form updates and posterior uncertainty, reducing drift compared to deterministic methods.
-
Label Leakage Attacks in Machine Unlearning: A Parameter and Inversion-Based Approach
Parameter-difference and model-inversion attacks can identify forgotten classes after machine unlearning on standard image datasets.
-
A Domain Incremental Continual Learning Benchmark for ICU Time Series Model Transportability
Proposes a domain incremental continual learning benchmark for ICU time series model transportability across US regions and evaluates data replay and EWC methods.
-
BGG: Bridging the Geometric Gap between Cross-View images by Vision Foundation Model Adaptation for Geo-Localization
BGG adapts vision foundation models using multi-granularity dilated convolutions and frequency-domain patch aggregation to achieve state-of-the-art cross-view geo-localization on University-1652 and SUES-200 with low training cost.