This article examines how human and social capital affect the production of medical innovation outputs along the translational research continuum. Despite efforts like the National Institutes of Health Clinical and Translational Sciences Award program to institutionalize translational research, significant gaps exist between the different stages of the translational process due in large part to the compartmentalization of medical careers and disciplinary specialization. Applying human and social capital theories, the article develops tests hypotheses using a multilevel model and data from a network survey of researchers at the University of Illinois at Chicago to explain production of translational innovation (dissemination, new clinical activity, and new intervention). Findings show that human capital variables are less important than social capital variables. Effects of cross-disciplinarity and translational network size are weak and only associated to one of the innovation types. By contrast, exchange of a variety of resources across the collaborative relationship is consistently important for the production innovations.