Understanding document images (eg, invoices) is a core but challenging task since it requires
complex functions such as reading text and a holistic understanding of the document. …

Many new proposals for scene text recognition (STR) models have been introduced in recent
years. While each claim to have pushed the boundary of the technology, a holistic and fair …

Assessing long-form responses generated by Vision-Language Models (VLMs) is challenging.
It not only requires checking whether the VLM follows the given instruction but also …

Understanding document images (eg, invoices) has been an important research topic and
has many applications in document processing automation. Through the latest advances in …

Vision-Language adaptation (VL adaptation) transforms Large Language Models (LLMs)
into Large Vision-Language Models (LVLMs) for multimodal tasks, but this process often …

A real-world information extraction (IE) system for semi-structured document images often
involves a long pipeline of multiple modules, whose complexity dramatically increases its …

This paper presents a simple yet effective approach for weakly supervised text localization
in end-to-end visual document understanding (VDU) models. The traditional approach in …

Speech and audio encoders developed over years of community effort are routinely excluded
from video understanding pipelines, not because they fail, but because benchmarks never …

Recent advances in Large Language Models (LLMs) have stimulated a surge of research
aimed at extending their applications to the visual domain. While these models exhibit promise …

Frontier model evaluations are shifting from foundational capabilities (eg, instruction following
and reasoning) toward compositional, agentic ones, but Korean agentic benchmarks …