Large Stepsize Gradient Descent for Logistic Loss: Non-Monotonicity of the Loss Improves Optimization Efficiencyby Jingfeng…
Unmasking Dementia Detection by Masking Input Gradients: A JSM Approach to Model Interpretability and Precisionby…
CoRelation: Boosting Automatic ICD Coding Through Contextualized Code Relation Learningby Junyu Luo, Xiaochen Wang, Jiaqi…
Prompt Perturbation Consistency Learning for Robust Language Modelsby Yao Qiang, Subhrangshu Nandi, Ninareh Mehrabi, Greg…
Differentially Private Fair Binary Classificationsby Hrad Ghoukasian, Shahab AsoodehFirst submitted to arxiv on: 23 Feb…
Hierarchical Invariance for Robust and Interpretable Vision Tasks at Larger Scalesby Shuren Qi, Yushu Zhang,…
United We Pretrain, Divided We Fail! Representation Learning for Time Series by Pretraining on 75…
Classification Under Strategic Self-Selectionby Guy Horowitz, Yonatan Sommer, Moran Koren, Nir RosenfeldFirst submitted to arxiv…
Understanding Oversmoothing in Diffusion-Based GNNs From the Perspective of Operator Semigroup Theoryby Weichen Zhao, Chenguang…
Attention-Guided Masked Autoencoders For Learning Image Representationsby Leon Sick, Dominik Engel, Pedro Hermosilla, Timo RopinskiFirst…