Lightweight model stitching preserves over 91% of driving performance in cross-domain perception updates for end-to-end autonomous driving, cutting adaptation time from 22 hours to under 1 hour.
Latent space translation via inverse relative projection
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
λ-Orthogonality regularization enables distribution-specific adaptation of representations via affine transformations while retaining original learned structures.
Learned anchors as semantic prototypes combined with whitened inner products improve relative representations, enabling nearly lossless zero-shot communication between heterogeneous neural models on vision and language tasks.
citing papers explorer
-
A Stitch in Time Saves Nine: Preserving Policy Compatibility Under Perception Updates in End-to-End Autonomous Driving
Lightweight model stitching preserves over 91% of driving performance in cross-domain perception updates for end-to-end autonomous driving, cutting adaptation time from 22 hours to under 1 hour.
-
$\boldsymbol{\lambda}$-Orthogonality Regularization for Compatible Representation Learning
λ-Orthogonality regularization enables distribution-specific adaptation of representations via affine transformations while retaining original learned structures.
-
Improving Relative Representations with Learned Anchors and Whitened Inner Products
Learned anchors as semantic prototypes combined with whitened inner products improve relative representations, enabling nearly lossless zero-shot communication between heterogeneous neural models on vision and language tasks.