VARCO-VISION-2.0 Technical Report

• URL: http://arxiv.org/abs/2509.10105v2
• Date: Tue, 16 Sep 2025 01:21:28 GMT
• Title: VARCO-VISION-2.0 Technical Report
• Authors: Young-rok Cha, Jeongho Ju, SunYoung Park, Jong-Hyeon Lee, Younghyun Yu, Youngjune Kim,
• Abstract summary: We introduce VARCO-VISION-2.0, an open-weight bilingual vision-language model (VLM) for Korean and English with improved capabilities.<n>The model supports multi-image understanding for complex inputs such as documents, charts, and tables, and delivers layoutaware OCR.<n>Two variants of VARCO-VISION-2.0 are available at Hugging Face: a full-scale 14B model and a lightweight 1.7B model.
• Score: 5.50851195473534
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We introduce VARCO-VISION-2.0, an open-weight bilingual vision-language model (VLM) for Korean and English with improved capabilities compared to the previous model VARCO-VISION-14B. The model supports multi-image understanding for complex inputs such as documents, charts, and tables, and delivers layoutaware OCR by predicting both textual content and its spatial location. Trained with a four-stage curriculum with memory-efficient techniques, the model achieves enhanced multimodal alignment, while preserving core language abilities and improving safety via preference optimization. Extensive benchmark evaluations demonstrate strong spatial grounding and competitive results for both languages, with the 14B model achieving 8th place on the OpenCompass VLM leaderboard among models of comparable scale. Alongside the 14B-scale model, we release a 1.7B version optimized for on-device deployment. We believe these models advance the development of bilingual VLMs and their practical applications. Two variants of VARCO-VISION-2.0 are available at Hugging Face: a full-scale 14B model and a lightweight 1.7B model.

Related papers

• MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe [68.04078852416248]
  MiniCPM-V 4.5 is an 8B parameter model designed for high efficiency and strong performance.<n>We introduce three core improvements in model architecture, data strategy and training method.<n>MiniCPM-V 4.5 achieves state-of-the-art performance among models under 30B size.
  arXiv  Detail & Related papers  (2025-09-16T19:41:48Z)
• Seed-X: Building Strong Multilingual Translation LLM with 7B Parameters [53.59868121093848]
  We introduce Seed-X, a family of open-source language models (LLMs) with 7B parameter size.<n>The base model is pre-trained on a diverse, high-quality dataset encompassing both monolingual and bilingual content across 28 languages.<n>The instruct model is then finetuned to translate by Chain-of-Thought (CoT) reasoning and further enhanced through reinforcement learning (RL) to achieve better generalization across diverse language pairs.
  arXiv  Detail & Related papers  (2025-07-18T03:19:43Z)
• Bielik 11B v2 Technical Report [0.0]
  Bielik 11B v2 is a state-of-the-art language model optimized for Polish text processing.<n>It is built on the Mistral 7B v0.2 architecture and scaled to 11B parameters using depth up-scaling.<n>We introduce two key technical innovations: Weighted Instruction Cross-Entropy Loss and Adaptive Learning Rate.
  arXiv  Detail & Related papers  (2025-05-05T07:03:41Z)
• Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling [128.24325909395188]
  We introduce InternVL 2.5, an advanced multimodal large language model (MLLM) series that builds upon InternVL 2.0.<n>InternVL 2.5 exhibits competitive performance, rivaling leading commercial models such as GPT-4o and Claude-3.5-Sonnet.<n>We hope this model contributes to the open-source community by setting new standards for developing and applying multimodal AI systems.
  arXiv  Detail & Related papers  (2024-12-06T18:57:08Z)
• VARCO-VISION: Expanding Frontiers in Korean Vision-Language Models [7.343894708908458]
  We introduce an open-source Korean-English vision-language model (VLM), VARCO-VISION.<n>We incorporate a step-by-step training strategy that allows a model learn both linguistic and visual information.<n>VARCO-VISION is capable of grounding, referring, and OCR, expanding its usage and potential applications.
  arXiv  Detail & Related papers  (2024-11-28T12:38:42Z)
• VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks [60.5257456681402]
  We study the potential for building universal embeddings capable of handling a wide range of downstream tasks.<n>We build a series of VLM2Vec models on SoTA VLMs like Phi-3.5-V, LLaVA-1.6 and evaluate them on MMEB's evaluation split.<n>Our results show that VLM2Vec achieves an absolute average improvement of 10% to 20% over existing multimodal embedding models.
  arXiv  Detail & Related papers  (2024-10-07T16:14:05Z)
• Compact Language Models via Pruning and Knowledge Distillation [61.56557874432008]
  Minitron models exhibit up to a 16% improvement in MMLU scores compared to training from scratch. Deriving 8B and 4B models from an already pretrained 15B model using our approach requires up to 40x fewer training tokens per model compared to training from scratch.
  arXiv  Detail & Related papers  (2024-07-19T21:47:57Z)
• ML-SUPERB 2.0: Benchmarking Multilingual Speech Models Across Modeling Constraints, Languages, and Datasets [106.7760874400261]
  This paper presents ML-SUPERB2.0, which is a new benchmark for evaluating pre-trained SSL and supervised speech models. We find performance improvements over the setup of ML-SUPERB, but performance depends on the downstream model design. Also, we find large performance differences between languages and datasets, suggesting the need for more targeted approaches.
  arXiv  Detail & Related papers  (2024-06-12T21:01:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.