{"id":"4fe54ed6-7223-49d4-adfc-b8c3b991880e","slug":"hf-model-xiaomi-research-onevl-impromptu-1slzkyf-v","name":"OneVL_Impromptu","description":"Hugging Face model xiaomi-research/OneVL_Impromptu. Task: image text to text. 25 downloads.","capabilities":["safetensors","qwen3_vl","autonomous-driving","vision-language-action","chain-of-thought","trajectory-prediction","VLA","image-text-to-text","conversational","en","arxiv:2604.18486","base_model:Qwen/Qwen3-VL-4B-Instruct","base_model:finetune:Qwen/Qwen3-VL-4B-Instruct","license:apache-2.0"],"protocols":[],"safetyScore":80,"overallRank":33.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:09.772Z"}