Tootfinder

ClustViT: Clustering-based Token Merging for Semantic Segmentation
Fabio Montello, Ronja G\"uldenring, Lazaros Nalpantidis
https://arxiv.org/abs/2510.01948 https://

ClustViT: Clustering-based Token Merging for Semantic Segmentation
Vision Transformers can achieve high accuracy and strong generalization across various contexts, but their practical applicability on real-world robotic systems is limited due to their quadratic attention complexity. Recent works have focused on dynamically merging tokens according to the image complexity. Token merging works well for classification but is less suited to dense prediction. We propose ClustViT, where we expand upon the Vision Transformer (ViT) backbone and address semantic segmen…

Suppression of inverse magnetic energy transfer in collisionless marginally magnetized plasmas
Zhuo Liu, Muni Zhou, Nuno F. G. Loureiro
https://arxiv.org/abs/2510.01573 https://…

Suppression of inverse magnetic energy transfer in collisionless marginally magnetized plasmas
We investigate the inverse cascade of magnetic energy in decaying, collisionless plasmas with moderate to high-$β$ values via first-principles numerical simulations and analytical theory. We find that pressure-anisotropy-driven instabilities, in particular the firehose instability, suppress reconnection-driven coalescence of magnetic structures (i.e., inverse transfer) by nullifying magnetic tension. This suppression leaves such structures elongated and confined to scales comparable to the Lar…