Demonstrating and Reducing Shortcuts in Vision-Language Representation Learningby Maurits Bleeker, Mariya Hendriksen, Andrew Yates, Maarten…
MV-Swin-T: Mammogram Classification with Multi-view Swin Transformerby Sushmita Sarker, Prithul Sarker, George Bebis, Alireza TavakkoliFirst…
Layer-wise Regularized Dropout for Neural Language Modelsby Shiwen Ni, Min Yang, Ruifeng Xu, Chengming Li,…
How Do Humans Write Code? Large Models Do It the Same Way Tooby Long Li,…
EMIFF: Enhanced Multi-scale Image Feature Fusion for Vehicle-Infrastructure Cooperative 3D Object Detectionby Zhe Wang, Siqi…
Gradual Residuals Alignment: A Dual-Stream Framework for GAN Inversion and Image Attribute Editingby Hao Li,…
Multi-scale Spatio-temporal Transformer-based Imbalanced Longitudinal Learning for Glaucoma Forecasting from Irregular Time Series Imagesby Xikai…
Unsupervised Text Style Transfer via LLMs and Attention Masking with Multi-way Interactionsby Lei Pan, Yunshi…
Heterogeneous Graph Reasoning for Fact Checking over Texts and Tablesby Haisong Gong, Weizhi Xu, Shu…
Identifying Semantic Induction Heads to Understand In-Context Learningby Jie Ren, Qipeng Guo, Hang Yan, Dongrui…