MOSAIC is a scaling-aware data selection framework that outperforms baselines in training end-to-end autonomous driving planners, achieving comparable or better EPDMS scores with up to 80% less data.
Scaling vision transformers
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
AsymLoc uses teacher-student distillation with geometry-driven matching to enable efficient nearest-neighbor feature matching, achieving 95% of teacher accuracy with 10x smaller models on localization benchmarks.
citing papers explorer
-
Scaling-Aware Data Selection for End-to-End Autonomous Driving Systems
MOSAIC is a scaling-aware data selection framework that outperforms baselines in training end-to-end autonomous driving planners, achieving comparable or better EPDMS scores with up to 80% less data.
-
AsymLoc: Towards Asymmetric Feature Matching for Efficient Visual Localization
AsymLoc uses teacher-student distillation with geometry-driven matching to enable efficient nearest-neighbor feature matching, achieving 95% of teacher accuracy with 10x smaller models on localization benchmarks.