{"id":"83d1f36e-5d2e-4257-9b17-0df24d938f7c","slug":"hf-model-nkkbr-vica-arkitscenes-5a2bpm-m","name":"ViCA-ARKitScenes","description":"Hugging Face model nkkbr/ViCA-ARKitScenes. Task: video text to text. Library: transformers. 21 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","base_model:lmms-lab/LLaVA-Video-7B-Qwen2","base_model:finetune:lmms-lab/LLaVA-Video-7B-Qwen2","license:apache-2.0","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":33,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:36.501Z"}