Multi-modal Masked Siamese Network Improves Chest X-Ray Representation Learningby Saeed Shurrab, Alejandro Guerra-Manzanares, Farah E.…
PDiscoFormer: Relaxing Part Discovery Constraints with Vision Transformersby Ananthu Aniraj, Cassio F.Dantas, Dino Ienco, Diego…
Learning Scalable Model Soup on a Single GPU: An Efficient Subspace Training Strategyby Tao Li,…
Tarsier: Recipes for Training and Evaluating Large Video Description Modelsby Jiawei Wang, Liping Yuan, Yuchen…
Improving robustness to corruptions with multiplicative weight perturbationsby Trung Trinh, Markus Heinonen, Luigi Acerbi, Samuel…
Probabilistic Conceptual Explainers: Trustworthy Conceptual Explanations for Vision Foundation Modelsby Hengyi Wang, Shiwei Tan, Hao…
Towards Efficient Pareto Set Approximation via Mixture of Experts Based Model Fusionby Anke Tang, Li…
DistilDoc: Knowledge Distillation for Visually-Rich Document Applicationsby Jordy Van Landeghem, Subhajit Maity, Ayan Banerjee, Matthew…
Image and Video Tokenization with Binary Spherical Quantizationby Yue Zhao, Yuanjun Xiong, Philipp KrähenbühlFirst submitted…
Adapting Pretrained ViTs with Convolution Injector for Visuo-Motor Controlby Dongyoon Hwang, Byungkun Lee, Hojoon Lee,…