Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Kalman-Inspired Runtime Stability and Recovery in Hybrid Reasoning Systems
Barak Or
Hybrid reasoning systems that combine learned components with model-based inference are increasingly deployed in tool-augmented decision loops, yet their runtime behavior under par…
cs.LG2026
Automatic Stability and Recovery for Neural Network Training
Barak Or
Training modern neural networks is increasingly fragile, with rare but severe destabilizing updates often causing irreversible divergence or silent performance degradation. Existin…
cs.LG2024
Learning-Based Speed Estimation from Accelerometer-Only Inertial Sensing
Barak Or
The proposed model, CarSpeedNet, estimates scalar vehicle speed from a window of three-axis smartphone acceleration, without gyroscope, wheel-odometry, vehicle-bus, or positioning…