Saved in:
Bibliographic Details
Main Authors: Ju, Jeongho, Kim, Daeyoung, Park, SunYoung, Kim, Youngjune
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.19103
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915039603064832
author Ju, Jeongho
Kim, Daeyoung
Park, SunYoung
Kim, Youngjune
author_facet Ju, Jeongho
Kim, Daeyoung
Park, SunYoung
Kim, Youngjune
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2411_19103
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle VARCO-VISION: Expanding Frontiers in Korean Vision-Language Models
Ju, Jeongho
Kim, Daeyoung
Park, SunYoung
Kim, Youngjune
Computer Vision and Pattern Recognition
Computation and Language
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.
title VARCO-VISION: Expanding Frontiers in Korean Vision-Language Models
topic Computer Vision and Pattern Recognition
Computation and Language
url https://arxiv.org/abs/2411.19103