Compute-Efficient Medical Image Classification with Softmax-Free Transformers and Sequence Normalizationby Firas Khader, Omar S. M.…
Sparse Concept Bottleneck Models: Gumbel Tricks in Contrastive Learningby Andrei Semenov, Vladimir Ivanov, Aleksandr Beznosikov,…
Towards Out-of-Distribution Detection for breast cancer classification in Point-of-Care Ultrasound Imagingby Jennie Karlsson, Marisa Wodrich,…
PIDformer: Transformer Meets Control Theoryby Tam Nguyen, César A. Uribe, Tan M. Nguyen, Richard G.…
Multi-scale Spatio-temporal Transformer-based Imbalanced Longitudinal Learning for Glaucoma Forecasting from Irregular Time Series Imagesby Xikai…
Is It a Free Lunch for Removing Outliers during Pretraining?by Baohao Liao, Christof MonzFirst submitted…
Partially Recentralization Softmax Loss for Vision-Language Models Robustnessby Hao Wang, Jinzhe Jiang, Xin Zhang, Chen…
Lower bounds on transformers with infinite precisionby Alexander KozachinskiyFirst submitted to arxiv on: 28 Dec…
ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routingby Ziteng Wang, Jun Zhu, Jianfei ChenFirst submitted to…
Simulating Hard Attention Using Soft Attentionby Andy Yang, Lena Strobl, David Chiang, Dana AngluinFirst submitted…