Sparse autoencoders decompose the latent space of end-to-end autonomous driving models into interpretable concepts whose causal influence on trajectory scoring can be measured and intervened upon to improve driving performance.
Vadv2: End-to-end vectorized autonomous driving via probabilistic planning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Driving the Wrong Way: Leveraging Interpretability in End2End Autonomous Driving Models
Sparse autoencoders decompose the latent space of end-to-end autonomous driving models into interpretable concepts whose causal influence on trajectory scoring can be measured and intervened upon to improve driving performance.