mlsanityData to 7 Oct 2026

"Inctelegi Romanecste?'' A Recipe for Romanian Vision-Language Models

arXiv 2605.31401 ↗First posted 29 May 2026cs.CLcited by 0

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

Abstract (arXiv)

Vision-Language Models (VLMs) largely follow the text-only LLM trajectory, excelling on English benchmarks but sharply degrading on low-resource languages, where neither large-scale image-text corpora nor culturally grounded evaluations exist. We present a systematic study of building a language-specific VLM for Romanian, covering the full pipeline from data construction to architectural choices. We translate established English VLM training and evaluation corpora into Romanian, applying machine translation to textual annotations and to in-image text, preserving visual grounding while adapting the textual content. Using this data, we train and ablate a series of VLMs to isolate the contribution of (i) vision backbones of varying scale and pretraining, (ii) language backbones from multilingual to Romanian-adapted LLMs, and (iii) OCR-style image-text data. We further curate HoraVQA, a culturally native evaluation set grounded in Romanian everyday scenes. Romanian-adapted VLMs consistently outperform their same-sized counterparts and, across all evaluated benchmarks, even surpass models from the next larger size category.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 22 of its 32 references that are in the map. First posted on arXiv 29 May 2026.

Builds on

22 of 32 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024Benchmarking Vision Language Models for Cultural Understanding15 Jul
  2. 2024Why do LLaVA Vision-Language Models Reply to Images in English?2 Jul
  3. 2024CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark10 Jun

Other references · 19

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  3. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,151
  4. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  5. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,048
  6. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,855
  7. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,044
  8. 2025InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiencycited by 1,419
  9. 2025SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Featurescited by 1,127
  10. 2022PaLI: A Jointly-Scaled Multilingual Language-Image Modelcited by 762
  11. 2023PaLI-X: On Scaling up a Multilingual Vision and Language Modelcited by 254
  12. 2021Visually Grounded Reasoning across Languages and Culturescited by 188
7 more
  1. 2022Crossmodal-3600: A Massively Multilingual Multimodal Evaluation Datasetcited by 100
  2. 2022AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilitiescited by 84
  3. 2025Scaling Text-Rich Image Understanding via Code-Guided Synthetic Multimodal Data Generationcited by 54
  4. 2024PALO: A Polyglot Large Multimodal Model for 5B Peoplecited by 34
  5. 2025Aya Vision: Advancing the Frontier of Multilingual Multimodalitycited by 31
  6. 2024RoMemes: A multimodal meme corpus for the Romanian languagecited by 3
  7. 2025LLMic: Romanian Foundation Language Modelcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Behind Maya: Building a Multilingual Vision Language Model
  2. 2026Annotation-Efficient Vision-Language Model Adaptation to the Polish Language Using the LLaVA Framework
  3. 2025Rethinking Multilingual Vision-Language Translation: Dataset, Evaluation, and Adaptation
  4. 2024Exploring the Frontier of Vision-Language Models: A Survey of Current Methodologies and Future Directions
  5. 2024An Introduction to Vision-Language Modeling
  6. 2026Scaling Vision-Language Models Is Not Enough to Mitigate Bias
  7. 2024Building and better understanding vision-language models: insights and future directions
  8. 2025VLURes: Benchmarking VLM Visual and Linguistic Understanding in Low-Resource Languages