mlsanityData to 7 Oct 2026

jina-vlm: Small Multilingual Vision Language Model

arXiv 2512.04032 ↗First posted 3 Dec 2025cs.CL cs.AI cs.CVcited by 1

On the map: Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning

Abstract (arXiv)

We present jina-vlm, a token-efficient 2.4B parameter vision-language model that achieves state-of-the-art multilingual VQA performance among open 2B-scale VLMs. The model couples a SigLIP2 vision encoder with a Qwen3 language decoder and makes use of image tiling and attention-pooling for token-efficient processing of arbitrary-resolution images. To understand the contribution of different training data categories, we conduct a leave-one-out data mixture ablation study-systematically removing task, domain, modality, and language categories-to diagnose which data types are necessary versus redundant and whether task benefits transfer across domains. Model weights and code are publicly released at https://huggingface.co/jinaai/jina-vlm.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 84 of its 87 references that are in the map. First posted on arXiv 3 Dec 2025.

Builds on

84 of 87 references.

Closest ancestors · 15

Same direction, newest first

  1. 2025FineVision: Open Data Is All You Need20 Oct
  2. 2025Multilingual Vision-Language Models, A Survey26 Sep
  3. 2024NVILA: Efficient Frontier Visual Language Models5 Dec
  4. 2024PaliGemma 2: A Family of Versatile VLMs for Transfer4 Dec
  5. 2024Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models25 Sep
  6. 2024PaliGemma: A versatile 3B VLM for transfer10 Jul
  7. 2024We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?1 Jul
  8. 2024What matters when building vision-language models?3 May
  9. 2024Are We on the Right Way for Evaluating Large Vision-Language Models?29 Mar
  10. 2024MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?21 Mar
  11. 2024Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset22 Feb
  12. 2024MobileVLM V2: Faster and Stronger Baseline for Vision Language Model6 Feb
3 more
  1. 2023MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts3 Oct
  2. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond24 Aug
  3. 2022Flamingo: a Visual Language Model for Few-Shot Learning29 Apr

Other references · 69

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  3. 2025Qwen3 Technical Reportcited by 8,195
  4. 2023Visual Instruction Tuningcited by 7,792
  5. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  6. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
  7. 2025Qwen2.5-VL Technical Reportcited by 5,418
  8. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,710
  9. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
  10. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  11. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,151
  12. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,018
38 more
  1. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,669
  2. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,534
  3. 2016Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answeringcited by 2,498
  4. 2023MMBench: Is Your Multi-modal Model an All-around Player?cited by 2,105
  5. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,044
  6. 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,883
  7. 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,769
  8. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,758
  9. 2020GLU Variants Improve Transformercited by 1,724
  10. 2019Towards VQA Models That Can Readcited by 1,696
  11. 2023Evaluating Object Hallucination in Large Vision-Language Modelscited by 1,696
  12. 2023MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Modelscited by 1,624
  13. 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scalingcited by 1,573
  14. 2022ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoningcited by 1,449
  15. 2016CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoningcited by 1,445
  16. 2025InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiencycited by 1,419
  17. 2020DocVQA: A Dataset for VQA on Document Imagescited by 1,288
  18. 2025SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Featurescited by 1,127
  19. 2024MiniCPM-V: A GPT-4V Level MLLM on Your Phonecited by 1,061
  20. 2024How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suitescited by 1,033
  21. 2024Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMscited by 822
  22. 2016A Diagram Is Worth A Dozen Imagescited by 793
  23. 2022PaLI: A Jointly-Scaled Multilingual Language-Image Modelcited by 762
  24. 2024An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Modelscited by 629
  25. 2023HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Modelscited by 572
  26. 2024LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Modelscited by 571
  27. 2024BLINK: Multimodal Large Language Models Can See but Not Perceivecited by 529
  28. 2020PathVQA: 30000+ Questions for Medical Visual Question Answeringcited by 467
  29. 2023OCRBench: On the Hidden Mystery of OCR in Large Multimodal Modelscited by 466
  30. 2024VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Modelscited by 443
  31. 2021InfographicVQAcited by 430
  32. 2021TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Financecited by 402
  33. 2024LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Modelscited by 394
  34. 2024VisionZip: Longer is Better but Not Necessary in Vision Language Modelscited by 298
  35. 2024MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?cited by 284
  36. 2024PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reductioncited by 283
  37. 2024LogicVista: Multimodal LLM Logical Reasoning Benchmark in Visual Contextscited by 240
  38. 2023Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolutioncited by 226

50 most cited of 69 All 69 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026ThermEval: A Structured Benchmark for Evaluation of Vision-Language Models on Thermal Imagerycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025VLURes: Benchmarking VLM Visual and Linguistic Understanding in Low-Resource Languages
  2. 2025A Survey on Efficient Vision-Language Models
  3. 2023Synthesize, Diagnose, and Optimize: Towards Fine-Grained Vision-Language Understanding
  4. 2025Behind Maya: Building a Multilingual Vision Language Model
  5. 2024LM4LV: A Frozen Large Language Model for Low-level Vision Tasks
  6. 2025Rethinking Multilingual Vision-Language Translation: Dataset, Evaluation, and Adaptation
  7. 202620/20 Vision Language Models: A Prescription for Better VLMs through Data Curation Alone
  8. 2025Centurio: On Drivers of Multilingual Ability of Large Vision-Language Model