The rapid adoption of AI in Earth system science promises unprecedented speed and fidelity in the generation of climate information. However, this technological prowess rests on a fragile and unequal ...
Mechanistic interpretability aims to break models into meaningful parts; verifying that two such parts implement the same computation is a prerequisite. Existing similarity measures evaluate either em...
A random $n\times k$ matrix $S$ is an \emph{$(r,α)$-oblivious subspace injection} (OSI) if $\Exp\|S^\top x\|_2^2=\|x\|_2^2$ for every $x\in\R^n$, and for every fixed $r$-dimensional subspace $V\subset...
Vision-based autonomous driving has gained much attention due to its low costs and excellent performance. Compared with dense BEV (Bird's Eye View) or sparse query models, Gaussian-centric method is a...