Pre-trained vision foundation models (VFMs), such as DINO and CLIP, provide strong transferable semantic representations. However, their patch-level features are usually spatially coarse because ...
Abstract: In this work, a high-performance circular phased array microstrip antenna is designed and presented. The proposed antenna would be printed on an Epoxy FR4 substrate, with a permittivity of 4 ...
Giulio Antonini are with the UAq EMC Laboratory, Dipartimento di Ingegneria Industriale e dell’Informazione e di Economia, Università degli Studi dell’Aquila, L’Aquila, Italy Giulio Antonini (Fellow, ...
Triton kernels for causal depthwise separable convolutions with per-token (dynamic) convolution weights. The following example shows how to add low-rank dynamic short convolutions to the queries, keys ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results