{"id":"bc508666-b8b0-4672-8643-9a1967656328","slug":"hf-model-shravvvv-vise-shfrfn-d","name":"VISE","description":"Hugging Face model shravvvv/VISE. Task: image text to text. Library: peft. 32 downloads.","capabilities":["peft","safetensors","lora","vise","self-evolving","multimodal","vision-language","lmm","visual-grounding","image-captioning","qwen3-vl","unsupervised","image-text-to-text","conversational","en","arxiv:2606.27373","base_model:Qwen/Qwen3-VL-2B-Instruct","base_model:adapter:Qwen/Qwen3-VL-2B-Instruct","license:apache-2.0"],"protocols":[],"safetyScore":80,"overallRank":34,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:38.255Z"}