A Task Descriptions and Training Settings

We provide a detailed description of all tasks and some additional details on the training of MDEQ. CIFAR-10 is a well-known computer vision dataset that consists of 60,000 color images, each of size 32 32 [31]. There are 10 object classes and 6,000 images per class. The entire dataset is divided into training (50K images) and testing (10K) sets. We use two different training settings for evaluating the MDEQ model on CIFAR-10. Following Dupont et al. [18], we compare MDEQ-small with other implicit models on CIFAR-10 images without data augmentation (i.e., the original, raw images), using approximately 170K learnable parameters in the model.