See vision-language model on Wiktionary
{
"forms": [
{
"form": "vision-language models",
"tags": [
"plural"
]
},
{
"form": "VLM",
"tags": [
"abbreviation"
]
}
],
"head_templates": [
{
"args": {
"abbr": "VLM",
"head": "vision-language model"
},
"expansion": "vision-language model (plural vision-language models, abbreviation VLM)",
"name": "en-noun"
}
],
"lang": "English",
"lang_code": "en",
"pos": "noun",
"senses": [
{
"categories": [
{
"kind": "other",
"name": "English entries with incorrect language header",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "Pages with 1 entry",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "Pages with entries",
"parents": [],
"source": "w"
},
{
"kind": "other",
"langcode": "en",
"name": "Machine learning",
"orig": "en:Machine learning",
"parents": [],
"source": "w"
}
],
"coordinate_terms": [
{
"word": "large language model"
},
{
"word": "small language model"
}
],
"examples": [
{
"bold_text_offsets": [
[
2,
23
]
],
"ref": "2025 February 25, Rina Diane Caballar, Cole Stryker, “What are vision language models (VLMs)?”, in IBM Think:",
"text": "A visual language model can partition an image into segments based on the spatial features that it has learned about and extracted from the image.",
"type": "quotation"
}
],
"glosses": [
"A generative AI model capable of interpreting text, images and video."
],
"id": "en-vision-language_model-en-noun-97hQ6zGF",
"links": [
[
"machine learning",
"machine learning"
],
[
"generative AI",
"generative AI"
]
],
"qualifier": "machine learning",
"raw_glosses": [
"(machine learning) A generative AI model capable of interpreting text, images and video."
]
}
],
"word": "vision-language model"
}
{
"forms": [
{
"form": "vision-language models",
"tags": [
"plural"
]
},
{
"form": "VLM",
"tags": [
"abbreviation"
]
}
],
"head_templates": [
{
"args": {
"abbr": "VLM",
"head": "vision-language model"
},
"expansion": "vision-language model (plural vision-language models, abbreviation VLM)",
"name": "en-noun"
}
],
"lang": "English",
"lang_code": "en",
"pos": "noun",
"senses": [
{
"categories": [
"English countable nouns",
"English entries with incorrect language header",
"English lemmas",
"English multiword terms",
"English nouns",
"English terms with quotations",
"Pages with 1 entry",
"Pages with entries",
"en:Machine learning"
],
"coordinate_terms": [
{
"word": "large language model"
},
{
"word": "small language model"
}
],
"examples": [
{
"bold_text_offsets": [
[
2,
23
]
],
"ref": "2025 February 25, Rina Diane Caballar, Cole Stryker, “What are vision language models (VLMs)?”, in IBM Think:",
"text": "A visual language model can partition an image into segments based on the spatial features that it has learned about and extracted from the image.",
"type": "quotation"
}
],
"glosses": [
"A generative AI model capable of interpreting text, images and video."
],
"links": [
[
"machine learning",
"machine learning"
],
[
"generative AI",
"generative AI"
]
],
"qualifier": "machine learning",
"raw_glosses": [
"(machine learning) A generative AI model capable of interpreting text, images and video."
]
}
],
"word": "vision-language model"
}
Download raw JSONL data for vision-language model meaning in All languages combined (1.4kB)
This page is a part of the kaikki.org machine-readable All languages combined dictionary. This dictionary is based on structured data extracted on 2026-10-30 from the enwiktionary dump dated 2026-10-01 using wiktextract (19f9a30 and 6f96ddf). The data shown on this site has been post-processed and various details (e.g., extra categories) removed, some information disambiguated, and additional data merged from other sources. See the raw data download page for the unprocessed wiktextract data.
If you use this data in academic research, please cite Tatu Ylonen: Wiktextract: Wiktionary as Machine-Readable Structured Data, Proceedings of the 13th Conference on Language Resources and Evaluation (LREC), pp. 1317-1325, Marseille, 20-25 June 2022. Linking to the relevant page(s) under https://kaikki.org would also be greatly appreciated.