{"slug": "evenvlm-a-text-and-multimodal-dataset-for-the-even-language-with-vision-language", "title": "EvenVLM: A Text and Multimodal Dataset for the Even Language with Vision-Language Fine-Tuning", "summary": "Researchers released EvenVLM, described as the first text and multimodal (VQA) dataset for Even (Lamut), an endangered Northern Tungusic language spoken by approximately 6,800 people in Siberia. The dataset contains 50,521 structured Even-Russian entries extracted from dictionary and phrasebook sources via GPT-4o Mini-based processing, and is paired with vision-language fine-tuning.", "body_md": "We present EvenVLM, the first text and multimodal (VQA) dataset for Even (Lamut), an endangered Northern Tungusic language spoken by approximately 6,800 people in Siberia. Our dataset comprises 50,521 structured Even-Russian entries extracted from dictionary and phrasebook sources via GPT-4o Mini-ba", "url": "https://wpnews.pro/news/evenvlm-a-text-and-multimodal-dataset-for-the-even-language-with-vision-language", "canonical_source": "https://aiflash.com/news/152695/", "published_at": "2026-11-16 20:00:18+00:00", "updated_at": "2026-11-16 20:20:55.987304+00:00", "lang": "en", "topics": ["natural-language-processing", "large-language-models", "ai-research", "computer-vision"], "entities": ["EvenVLM", "Even language", "Lamut", "GPT-4o Mini"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/evenvlm-a-text-and-multimodal-dataset-for-the-even-language-with-vision-language", "markdown": "https://wpnews.pro/news/evenvlm-a-text-and-multimodal-dataset-for-the-even-language-with-vision-language.md", "text": "https://wpnews.pro/news/evenvlm-a-text-and-multimodal-dataset-for-the-even-language-with-vision-language.txt", "jsonld": "https://wpnews.pro/news/evenvlm-a-text-and-multimodal-dataset-for-the-even-language-with-vision-language.jsonld"}}