vix.ing · top · new · best · stats

Jina-VLM: Small Multilingual Vision Language Model

2025/12/03 by Koukounas, Andreas, Mastrapas, Georgios, Hönicke, Florian +4
#68T50 #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #I.2.7

paper · doi:10.48550/arxiv.2512.04032

Abstract

We present Jina-VLM, a 2.4B parameter vision-language model that achieves state-of-the-art multilingual visual question answering among open 2B-scale VLMs. The model couples a SigLIP2 vision encoder with a Qwen3 language backbone through an attention-pooling connector that enables token-efficient processing of arbitrary-resolution images. The model achieves leading results on standard VQA benchmarks and multilingual evaluations while preserving competitive text-only performance. Model weights and code are publicly released at https://huggingface.co/jinaai/jina-vlm .

Citations

Related