6 accepted papers
Despite recent successes, *test-time scaling* $-$i.e., dynamically expanding the token budget during inference as needed$-$ remains brittle for vision-language models (VLMs): unstructured chains-of-thought about images entangle perception and reasoning, leading to long, disorganized contexts where s…
While Large Vision-Language Models (VLMs) excel at interpolation, they suffer catastrophic failures in systematic generalization, most notably in visual counting beyond training distributions. In this work, we investigate this extrapolation bottleneck by deconstructing visual counting into three cog…
Despite strong performance in visual understanding and language-based reasoning, Vision-Language Models (VLMs) struggle with tasks requiring integrated perception and symbolic computation. We study this limitation through visual equation solving, where mathematical equations are embedded in images,
Visuals are valuable tools for teaching math word problems (MWPs), helping young learners interpret textual descriptions into mathematical expressions before solving them.However, creating such visuals is labor-intensive and there is a lack of automated methods to support this process. In this paper…
Indoor positioning in environments where GPS cannot be used is a fundamental technology for robot navigation and human-robot interaction. However, existing vision-based localization systems cannot work in low-visibility environments, and existing wireless or acoustic localization systems require spe
Educational chatbots are a promising tool for assisting student learning. However, the development of effective chatbots in education has been challenging, as high-quality data is seldom available in this domain. In this paper, we propose a framework for generating synthetic teacher-student interact…