Reproduce “Weather Adaptive Autonomous Driving” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Nicholas Taylor, Alexander Picon, Sudip Dhakal
The paper proposes a decision rule for frozen YOLOv8x that lets users trade false alarms against missed objects. Gradient-boosted trees estimate whether each candidate box is real, and a user-set cost determines which boxes are kept. In DAWN, per-weather conformal risk control met a 20% miss budget, while one global threshold exceeded it in fog; the guarantee assumes within-bin exchangeability.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.