A growing body of work proposes dynamic expert-skipping methods for Mixture-of-Experts (MoE) models that adjust the number of experts activated per token during inference, aiming to preserve model quality while further reducing the number of active parameters. These methods have added calibrated importance scores, inte...
Jakob Steimle, T. Elsken, Daniel Ehrhardt et al.· 0 citations
This work introduces VideoReloc, whose adaptive clips use odometry to gather spatial evidence until object and motion criteria are met, adapting query length to the observed scene, and reframes sparse-map relocalization as verification of spatially extended video queries.
Qian-Ru Li, Xu-Yang Chen, Xu-Qin Wang et al.· 0 citations
This work shows that the overconfidence appears on unseen scenes even when the model reaches its loss's optimum, andfits a power law on the confidence with two constants per backbone--dataset pair and releases the audit protocol, its results, and the fitted constants per backbone-dataset pair.
Na Deng, Qing Cheng, Niclas Zeller et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.