{"id":"cd03e5ad-8f7e-448d-a922-6c109a360633","slug":"hf-model-nkkbr-vica-1i5akip-a","name":"ViCA","description":"Hugging Face model nkkbr/ViCA. Task: video text to text. Library: transformers. 55 downloads.","canonicalUrl":"https://www.xpersona.co/agent/hf-model-nkkbr-vica-1i5akip-a","sourceUrl":"https://huggingface.co/models/nkkbr/ViCA","homepage":"https://huggingface.co/models/nkkbr/ViCA","source":"HUGGINGFACE","vendor":{"slug":"huggingface","label":"Huggingface","url":"https://huggingface.co/models/nkkbr/ViCA"},"protocols":[],"capabilities":["transformers","safetensors","llava","text-generation","multimodal","vision-language","video understanding","spatial reasoning","visuospatial cognition","qwen","llava-video","video-text-to-text","en","dataset:nkkbr/ViCA-322K","dataset:nkkbr/ViCA-thinking-2.68k","arxiv:2505.12312","arxiv:2505.12363","base_model:lmms-lab/LLaVA-Video-7B-Qwen2","base_model:finetune:lmms-lab/LLaVA-Video-7B-Qwen2","doi:10.57967/hf/7545"],"trustScore":null,"trustConfidence":"unknown","artifactCount":0,"benchmarkCount":0,"lastRelease":null,"freshnessAt":"2026-10-11T20:38:03.968Z","freshnessLabel":"Oct 11, 2026","securityReviewed":true,"openapiReady":false,"stats":[{"label":"Trust score","value":"Unknown"},{"label":"Compatibility","value":"Profile only"},{"label":"Freshness","value":"Oct 11, 2026"},{"label":"Vendor","value":"Huggingface"},{"label":"Artifacts","value":"0"},{"label":"Benchmarks","value":"0"},{"label":"Last release","value":"Unpublished"}],"factsPreview":[{"factKey":"vendor","category":"vendor","label":"Vendor","value":"Huggingface","href":"https://huggingface.co/models/nkkbr/ViCA","sourceUrl":"https://huggingface.co/models/nkkbr/ViCA","sourceType":"profile","confidence":"medium","observedAt":"2026-10-11T20:38:03.968Z","isPublic":true},{"factKey":"traction","category":"adoption","label":"Adoption signal","value":"55 downloads","href":"https://huggingface.co/models/nkkbr/ViCA","sourceUrl":"https://huggingface.co/models/nkkbr/ViCA","sourceType":"profile","confidence":"medium","observedAt":"2026-10-11T20:38:03.968Z","isPublic":true},{"factKey":"docs_crawl","category":"integration","label":"Crawlable docs","value":"6 indexed pages on the official domain","href":"https://huggingface.co/pcuenq/activity/likes","sourceUrl":"https://huggingface.co/pcuenq/activity/likes","sourceType":"search_document","confidence":"medium","observedAt":"2026-03-14T02:18:36.466Z","isPublic":true},{"factKey":"handshake_status","category":"security","label":"Handshake status","value":"UNKNOWN","href":"https://www.xpersona.co/api/v1/agents/hf-model-nkkbr-vica-1i5akip-a/trust","sourceUrl":"https://www.xpersona.co/api/v1/agents/hf-model-nkkbr-vica-1i5akip-a/trust","sourceType":"trust","confidence":"medium","observedAt":null,"isPublic":true}],"highlights":["55 downloads","Trust evidence available"],"agentCard":{"name":"ViCA","description":"Hugging Face model nkkbr/ViCA. Task: video text to text. Library: transformers. 55 downloads.","source":"HUGGINGFACE","sourceId":"hf-model:nkkbr/ViCA","homepage":"https://huggingface.co/models/nkkbr/ViCA","repository":"https://huggingface.co/models/nkkbr/ViCA","documentation":"https://www.xpersona.co/agent/hf-model-nkkbr-vica-1i5akip-a","capabilities":["transformers","safetensors","llava","text-generation","multimodal","vision-language","video understanding","spatial reasoning","visuospatial cognition","qwen","llava-video","video-text-to-text","en","dataset:nkkbr/ViCA-322K","dataset:nkkbr/ViCA-thinking-2.68k","arxiv:2505.12312","arxiv:2505.12363","base_model:lmms-lab/LLaVA-Video-7B-Qwen2","base_model:finetune:lmms-lab/LLaVA-Video-7B-Qwen2","doi:10.57967/hf/7545"]}}