ScenePilot is a boundary-driven RL framework that generates physically valid yet autonomy-failing driving scenarios by combining an RSS feasibility score with an online AV-risk predictor and feasibility-aware shielding.
Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
STELLAR trains up to 500M-parameter multi-modal models on 50M driving scenes and reports empirical scaling trends plus new state-of-the-art results on the Waymo Open Dataset.
citing papers explorer
-
ScenePilot: Controllable Boundary-Driven Critical Scenario Generation for Autonomous Driving
ScenePilot is a boundary-driven RL framework that generates physically valid yet autonomy-failing driving scenarios by combining an RSS feasibility score with an online AV-risk predictor and feasibility-aware shielding.
-
STELLAR: Scaling 3D Perception Large Models for Autonomous Driving
STELLAR trains up to 500M-parameter multi-modal models on 50M driving scenes and reports empirical scaling trends plus new state-of-the-art results on the Waymo Open Dataset.