DAWN couples a world predictor with a world-conditioned action denoiser in latent space so that each refines the other recursively, yielding strong planning and safety results on autonomous driving benchmarks.
CausalVAD: De-confounding End-to-End Autonomous Driving via Causal Intervention
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
abstract
Planning-oriented end-to-end driving models show great promise, yet they fundamentally learn statistical correlations instead of true causal relationships. This vulnerability leads to causal confusion, where models exploit dataset biases as shortcuts, critically harming their reliability and safety in complex scenarios. To address this, we introduce CausalVAD, a de-confounding training framework that leverages causal intervention. At its core, we design the sparse causal intervention scheme (SCIS), a lightweight, plug-and-play module to instantiate the backdoor adjustment theory in neural networks. SCIS constructs a dictionary of prototypes representing latent driving contexts. It then uses this dictionary to intervene on the model's sparse vectorized queries. This step actively eliminates spurious associations induced by confounders, thereby eliminating spurious factors from the representations for downstream tasks. Extensive experiments on benchmarks like nuScenes show CausalVAD achieves state-of-the-art planning accuracy and safety. Furthermore, our method demonstrates superior robustness against both data bias and noisy scenarios configured to induce causal confusion.
citation-role summary
background 3
citation-polarity summary
fields
cs.CV 3years
2026 3verdicts
UNVERDICTED 3roles
background 3polarities
background 3representative citing papers
DINO-VO achieves state-of-the-art monocular visual odometry accuracy and generalization by training a differentiable patch selector together with multi-task features and inverse-depth bundle adjustment.
EponaV2 advances perception-free driving world models by forecasting comprehensive future 3D geometry and semantic representations, achieving SOTA planning performance on NAVSIM benchmarks.
citing papers explorer
-
The DAWN of World-Action Interactive Models
DAWN couples a world predictor with a world-conditioned action denoiser in latent space so that each refines the other recursively, yielding strong planning and safety results on autonomous driving benchmarks.
-
DINO-VO: Learning Where to Focus for Enhanced State Estimation
DINO-VO achieves state-of-the-art monocular visual odometry accuracy and generalization by training a differentiable patch selector together with multi-task features and inverse-depth bundle adjustment.
-
EponaV2: Driving World Model with Comprehensive Future Reasoning
EponaV2 advances perception-free driving world models by forecasting comprehensive future 3D geometry and semantic representations, achieving SOTA planning performance on NAVSIM benchmarks.