Wonderful Matrices: More Efficient and Effective Architecture for Language Modeling Tasksby Jingze Shi, Bingheng Wu,…
Efficient Visual Transformer by Learnable Token Mergingby Yancheng Wang, Yingzhen YangFirst submitted to arxiv on:…
ColorMAE: Exploring data-independent masking strategies in Masked AutoEncodersby Carlos Hinojosa, Shuming Liu, Bernard GhanemFirst submitted…
DropKAN: Regularizing KANs by masking post-activationsby Mohammed Ghaith AltarabichiFirst submitted to arxiv on: 17 Jul…
SES: Bridging the Gap Between Explainability and Prediction of Graph Neural Networksby Zhenhua Huang, Kunhao…
Lite-SAM Is Actually What You Need for Segment Everythingby Jianhai Fu, Yuanjie Yu, Ningchuan Li,…
GraphMamba: An Efficient Graph Structure Learning Vision Mamba for Hyperspectral Image Classificationby Aitao Yang, Min…
Knowledge distillation to effectively attain both region-of-interest and global semantics from an image where multiple…
Urban Waterlogging Detection: A Challenging Benchmark and Large-Small Model Co-Adapterby Suqi Song, Chenxu Zhang, Peng…
The Solution for the sequential task continual learning track of the 2nd Greater Bay Area…