Paper · arXiv 2411.19103
VARCO-VISION: Expanding Frontiers in Korean Vision-Language Models
Jeongho Ju, Daeyoung Kim, SunYoung Park, Youngjune Kim
An open-source Korean-English vision-language model, VARCO-VISION, is introduced and demonstrates superior performance in bilingual image-text tasks compared to similar models, incorporating a step-by-step training strategy and supporting grounding, referring, and OCR.
Abstract
In this paper, we introduce an open-source Korean-English vision-language model (VLM), VARCO-VISION. We incorporate a step-by-step training strategy that allows a model learn both linguistic and visual information while preserving the backbone model's knowledge. Our model demonstrates outstanding performance in diverse settings requiring bilingual image-text understanding and generation abilities compared to models of similar size. VARCO-VISION is also capable of grounding, referring, and OCR, expanding its usage and potential applications for real-world scenarios. In addition to the model, we release five Korean evaluation datasets, including four closed-set and one openset benchmarks. We anticipate that our milestone will broaden the opportunities for AI researchers aiming to train VLMs. VARCO-VISION is available at https://huggingface.co/NCSOFT/VARCO-VISION-14B.