{"id":"60baf2b0-6ba2-4513-b404-d86f93516a60","slug":"hf-model-seerray-lab-icm-r2-8jes07-i","name":"ICM-r2","description":"Hugging Face model SeerRay-Lab/ICM-r2. Task: image text to text. Library: transformers. 56 downloads. 4 likes.","capabilities":["transformers","safetensors","qwen2_5_vl","image-text-to-text","gui","gui-agent","critic-model","vision-language-model","test-time-scaling","best-of-n","qwen2.5-vl","arxiv:2601.18197","conversational","en","dataset:SeerRay-Lab/GAIA-Dataset-v1.0","base_model:Qwen/Qwen2.5-VL-7B-Instruct","base_model:finetune:Qwen/Qwen2.5-VL-7B-Instruct","license:apache-2.0","text-generation-inference","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":35.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:03.625Z"}