Large pretrained models, coupled with fine-tuning, are slowly becoming established as the dominant architecture in machine learning. Even though these models offer impressive performance, their practical application is often limited by the prohibitive amount of resources required for every inference. Early-exiting dynamic neural networks (EDNN) circumvent this issue by allowing a model to make some of its predictions from intermediate layers (i.e., early-exit). Training an EDNN architecture is challenging as it consists of two intertwined components: the gating mechanism (GM) that controls early-exiting decisions and the intermediate inference modules (IMs) that perform inference from intermediate representations. As a result, most existing approaches rely on thresholding confidence metrics for the gating mechanism and strive to improve the underlying backbone network and the inference modules. Although successful, this approach has two fundamental shortcomings: 1) the GMs and the IMs are decoupled during training, leading to a train-test mismatch; and 2) the thresholding gating mechanism introduces a positive bias into the predictive probabilities, making it difficult to readily extract uncertainty information. We propose a novel architecture that connects these two modules. This leads to significant performance improvements on classification datasets and enables better uncertainty characterization capabilities. The dominant approach to improve machine learning models is to develop larger networks that can handle every potential sample. As a result, despite very impressive performance, the resource overhead is huge (Scao et al., 2023). The push for larger model size is often driven by the need to handle a small percentage of samples that are particularly challenging to infer (Bolukbasi et al., 2017); most inferences do not need the full power of a large network to be successfully executed. Nonetheless, most traditional neural network (NN) models have a fixed processing pipeline. This means that every sample, simple or complex, is processed the same way. To tackle this inefficiency, dynamic networks have been introduced (see (Han et al., 2022a) for a review).