{"id":"6a24eb1a-2bc4-4056-9d3b-113f2dcd609a","slug":"hf-model-xiaomi-research-onevl-visual-decoder-pt-v0i8ae-13","name":"OneVL_visual_decoder_pt","description":"Hugging Face model xiaomi-research/OneVL_visual_decoder_pt. Task: image text to text. 28 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":34,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:52.032Z"}