Stabilized MF-SSL with noise-aware decoupling and kinematics-gated pseudo-labeling scales AEB models from 1M to 1B data windows and delivers 35% better accident-free mileage in fleet deployment versus rule-based baseline.
Dual-aeb: Synergizing rule-based and multi- modal large language models for effective emergency braking,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Scaling Learning-based AEB with Massive Unlabeled Data
Stabilized MF-SSL with noise-aware decoupling and kinematics-gated pseudo-labeling scales AEB models from 1M to 1B data windows and delivers 35% better accident-free mileage in fleet deployment versus rule-based baseline.