In real-world settings, vision language models (VLMs) should robustly handle naturalistic, noisy visual content as well as domain-specific language and concepts. For example, K-12 educators using digital learning platforms may need to examine and provide feedback across many images of students' math work. To assess the potential of VLMs to support…

Online learning environments are challenging for deaf and hard of hearing (DHH) individuals. A major concern is split attention, which occurs when one simultaneously attends to multiple stimuli, a situation that characterizes most multimedia presentations and instruction that combines sound, text, images, graphs or charts, and video. Needing to…

Visuals play an important role in the teaching and learning of science and should be embedded within and supportive of authentic science inquiry. Both researchers and teachers believe that visuals have a great deal of potential to help students understand science, but in practice, these visuals do not always live up to their promise. Teachers need…