4 papers
Visual Dependence Does Not Imply Answerability: A Systematic Analysis of Answerability Signals in Frozen InstructBLIP
Minjun Kim, Hyunmin Song, Changwon Lim
Visual question answering models often produce plausible responses even when the available visual evidence is insufficient to support a valid answer. Although prior work has introd…
VEHME: A Vision-Language Model For Evaluating Handwritten Mathematics Expressions
Thu Phuong Nguyen, Duc M. Nguyen, Hyotaek Jeon +4
Automatically assessing handwritten mathematical solutions is an important problem in educational technology with practical applications, but it remains a significant challenge due…
Towards Human-like Multimodal Conversational Agent by Generating Engaging Speech
Taesoo Kim, Yongsik Jo, Hyunmin Song +1
Human conversation involves language, speech, and visual cues, with each medium providing complementary information. For instance, speech conveys a vibe or tone not fully captured…
RingFormer: Rethinking Recurrent Transformer with Adaptive Level Signals
Jaemu Heo, Eldor Fozilov, Hyunmin Song +1
Transformers have achieved great success in effectively processing sequential data such as text. Their architecture consisting of several attention and feedforward blocks can model…