{"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.","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"],"protocols":[],"safetyScore":80,"overallRank":35.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:03.968Z"}